MSAT and cellular hybrid networking

NASA Astrophysics Data System (ADS)

Baranowsky, Patrick W., II

Westinghouse Electric Corporation is developing both the Communications Ground Segment and the Series 1000 Mobile Phone for American Mobile Satellite Corporation's (AMSC's) Mobile Satellite (MSAT) system. The success of the voice services portion of this system depends, to some extent, upon the interoperability of the cellular network and the satellite communication circuit switched communication channels. This paper will describe the set of user-selectable cellular interoperable modes (cellular first/satellite second, etc.) provided by the Mobile Phone and described how they are implemented with the ground segment. Topics including roaming registration and cellular-to-satellite 'seamless' call handoff will be discussed, along with the relevant Interim Standard IS-41 Revision B Cellular Radiotelecommunications Intersystem Operations and IOS-553 Mobile Station - Land Station Compatibility Specification.

Shuttle Payload Ground Command and Control: An Experiment Implementation Combustion Module-2 Software Development, STS-107

NASA Technical Reports Server (NTRS)

Carek, David Andrew

2003-01-01

This presentation covers the design of a command and control architecture developed by the author for the Combustion Module-2 microgravity experiment, which flew aboard the STS-107 Shuttle mission, The design was implemented to satisfy a hybrid network that utilized TCP/IP for both the onboard segment and ground segment, with an intermediary unreliable transport for the space to ground segment. With the infusion of Internet networking technologies into Space Shuttle, Space Station, and spacecraft avionics systems, comes the need for robust methodologies for ground command and control. Considerations of high bit error links, and unreliable transport over intermittent links must be considered in such systems. Internet protocols applied to these systems, coupled with the appropriate application layer protections, can provide adequate communication architectures for command and control. However, there are inherent limitations and additional complexities added by the use of Internet protocols that must be considered during the design. This presentation will discuss the rationale for the: framework and protocol algorithms developed by the author. A summary of design considerations, implantation issues, and learned lessons will be will be presented. A summary of mission results using this communications architecture will be presented. Additionally, areas of further needed investigation will be identified.

Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning.

PubMed

Looney, Pádraig; Stevenson, Gordon N; Nicolaides, Kypros H; Plasencia, Walter; Molloholli, Malid; Natsis, Stavros; Collins, Sally L

2018-06-07

We present a new technique to fully automate the segmentation of an organ from 3D ultrasound (3D-US) volumes, using the placenta as the target organ. Image analysis tools to estimate organ volume do exist but are too time consuming and operator dependant. Fully automating the segmentation process would potentially allow the use of placental volume to screen for increased risk of pregnancy complications. The placenta was segmented from 2,393 first trimester 3D-US volumes using a semiautomated technique. This was quality controlled by three operators to produce the "ground-truth" data set. A fully convolutional neural network (OxNNet) was trained using this ground-truth data set to automatically segment the placenta. OxNNet delivered state-of-the-art automatic segmentation. The effect of training set size on the performance of OxNNet demonstrated the need for large data sets. The clinical utility of placental volume was tested by looking at predictions of small-for-gestational-age babies at term. The receiver-operating characteristics curves demonstrated almost identical results between OxNNet and the ground-truth). Our results demonstrated good similarity to the ground-truth and almost identical clinical results for the prediction of SGA.

Multiple supervised residual network for osteosarcoma segmentation in CT images.

PubMed

Zhang, Rui; Huang, Lin; Xia, Wei; Zhang, Bo; Qiu, Bensheng; Gao, Xin

2018-01-01

Automatic and accurate segmentation of osteosarcoma region in CT images can help doctor make a reasonable treatment plan, thus improving cure rate. In this paper, a multiple supervised residual network (MSRN) was proposed for osteosarcoma image segmentation. Three supervised side output modules were added to the residual network. The shallow side output module could extract image shape features, such as edge features and texture features. The deep side output module could extract semantic features. The side output module could compute the loss value between output probability map and ground truth and back-propagate the loss information. Then, the parameters of residual network could be modified by gradient descent method. This could guide the multi-scale feature learning of the network. The final segmentation results were obtained by fusing the results output by the three side output modules. A total of 1900 CT images from 15 osteosarcoma patients were used to train the network and a total of 405 CT images from another 8 osteosarcoma patients were used to test the network. Results indicated that MSRN enabled a dice similarity coefficient (DSC) of 89.22%, a sensitivity of 88.74% and a F1-measure of 0.9305, which were larger than those obtained by fully convolutional network (FCN) and U-net. Thus, MSRN for osteosarcoma segmentation could give more accurate results than FCN and U-Net. Copyright © 2018 Elsevier Ltd. All rights reserved.

Locally excitatory, globally inhibitory oscillator networks: theory and application to scene segmentation

NASA Astrophysics Data System (ADS)

Wang, DeLiang; Terman, David

1995-01-01

A novel class of locally excitatory, globally inhibitory oscillator networks (LEGION) is proposed and investigated analytically and by computer simulation. The model of each oscillator corresponds to a standard relaxation oscillator with two time scales. The network exhibits a mechanism of selective gating, whereby an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing other oscillators from jumping up. We show analytically that with the selective gating mechanism the network rapidly achieves both synchronization within blocks of oscillators that are stimulated by connected regions and desynchronization between different blocks. Computer simulations demonstrate LEGION's promising ability for segmenting multiple input patterns in real time. This model lays a physical foundation for the oscillatory correlation theory of feature binding, and may provide an effective computational framework for scene segmentation and figure/ground segregation.

Preliminary Results from NASA/GSFC Ka-Band High Rate Demonstration for Near-Earth Communications

NASA Technical Reports Server (NTRS)

Wong, Yen; Gioannini, Bryan; Bundick, Steven N.; Miller, David T.

2004-01-01

In early 2000, the National Aeronautics and Space Administration (NASA) commenced the Ka-Band Transition Project (KaTP) as another step towards satisfying wideband communication requirements of the space research and earth exploration-satellite services. The KaTP team upgraded the ground segment portion of NASA's Space Network (SN) in order to enable high data rate space science and earth science services communications. The SN ground segment is located at the White Sands Complex (WSC) in New Mexico. NASA conducted the SN ground segment upgrades in conjunction with space segment upgrades implemented via the Tracking and Data Relay Satellite (TDRS)-HIJ project. The three new geostationary data relay satellites developed under the TDRS-HIJ project support the use of the inter-satellite service (ISS) allocation in the 25.25-27.5 GHz band (the 26 GHz band) to receive high speed data from low earth-orbiting customer spacecraft. The TDRS H spacecraft (designated TDRS-8) is currently operational at a 171 degrees west longitude. TDRS I and J spacecraft on-orbit testing has been completed. These spacecraft support 650 MHz-wide Ka-band telemetry links that are referred to as return links. The 650 MHz-wide Ka-band telemetry links have the capability to support data rates up to at least 1.2 Gbps. Therefore, the TDRS-HIJ spacecraft will significantly enhance the existing data rate elements of the NASA Space Network that operate at S-band and Ku-band.

Technology Infusion of CodeSonar into the Space Network Ground Segment (RII07)

NASA Technical Reports Server (NTRS)

Benson, Markland

2008-01-01

The NASA Software Assurance Research Program (in part) performs studies as to the feasibility of technologies for improving the safety, quality, reliability, cost, and performance of NASA software. This study considers the application of commercial automated source code analysis tools to mission critical ground software that is in the operations and sustainment portion of the product lifecycle.

The American mobile satellite system

NASA Technical Reports Server (NTRS)

Garner, William B.

1990-01-01

During 1989, the American Mobile Satellite Corporation (AMSC) was authorized to construct, launch, and operate satellites to provide mobile satellite services (MSS) to the U.S. and Puerto Rico. The AMSC has undertaken three major development programs to bring a full range of MSS services to the U.S. The first program is the space segment program that will result in the construction and launch of the satellites as well as the construction and installation of the supporting ground telemetry and command system. The second segment will result in the specification, design, development, construction, and installation of the Network Control System necessary for managing communications access to the satellites, and the specification and development of ground equipment for standard circuit switched and packet switched communications services. The third program is the Phase 1 program to provide low speed data services within the U.S. prior to availability of the AMSC satellites and ground segment. Described here are the present status and plans for these three programs as well as an update on related business arrangements and regulatory matters.

Automated analysis of Physarum network structure and dynamics

NASA Astrophysics Data System (ADS)

Fricker, Mark D.; Akita, Dai; Heaton, Luke LM; Jones, Nick; Obara, Boguslaw; Nakagaki, Toshiyuki

2017-06-01

We evaluate different ridge-enhancement and segmentation methods to automatically extract the network architecture from time-series of Physarum plasmodia withdrawing from an arena via a single exit. Whilst all methods gave reasonable results, judged by precision-recall analysis against a ground-truth skeleton, the mean phase angle (Feature Type) from intensity-independent, phase-congruency edge enhancement and watershed segmentation was the most robust to variation in threshold parameters. The resultant single pixel-wide segmented skeleton was converted to a graph representation as a set of weighted adjacency matrices containing the physical dimensions of each vein, and the inter-vein regions. We encapsulate the complete image processing and network analysis pipeline in a downloadable software package, and provide an extensive set of metrics that characterise the network structure, including hierarchical loop decomposition to analyse the nested structure of the developing network. In addition, the change in volume for each vein and intervening plasmodial sheet was used to predict the net flow across the network. The scaling relationships between predicted current, speed and shear force with vein radius were consistent with predictions from Murray’s law. This work was presented at PhysNet 2015.

The Segmentation of Point Clouds with K-Means and ANN (artifical Neural Network)

NASA Astrophysics Data System (ADS)

Kuçak, R. A.; Özdemir, E.; Erol, S.

2017-05-01

Segmentation of point clouds is recently used in many Geomatics Engineering applications such as the building extraction in urban areas, Digital Terrain Model (DTM) generation and the road or urban furniture extraction. Segmentation is a process of dividing point clouds according to their special characteristic layers. The present paper discusses K-means and self-organizing map (SOM) which is a type of ANN (Artificial Neural Network) segmentation algorithm which treats the segmentation of point cloud. The point clouds which generate with photogrammetric method and Terrestrial Lidar System (TLS) were segmented according to surface normal, intensity and curvature. Thus, the results were evaluated. LIDAR (Light Detection and Ranging) and Photogrammetry are commonly used to obtain point clouds in many remote sensing and geodesy applications. By photogrammetric method or LIDAR method, it is possible to obtain point cloud from terrestrial or airborne systems. In this study, the measurements were made with a Leica C10 laser scanner in LIDAR method. In photogrammetric method, the point cloud was obtained from photographs taken from the ground with a 13 MP non-metric camera.

Seismic fragility formulations for segmented buried pipeline systems including the impact of differential ground subsidence

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pineda Porras, Omar Andrey; Ordaz, Mario

2009-01-01

Though Differential Ground Subsidence (DGS) impacts the seismic response of segmented buried pipelines augmenting their vulnerability, fragility formulations to estimate repair rates under such condition are not available in the literature. Physical models to estimate pipeline seismic damage considering other cases of permanent ground subsidence (e.g. faulting, tectonic uplift, liquefaction, and landslides) have been extensively reported, not being the case of DGS. The refinement of the study of two important phenomena in Mexico City - the 1985 Michoacan earthquake scenario and the sinking of the city due to ground subsidence - has contributed to the analysis of the interrelation ofmore » pipeline damage, ground motion intensity, and DGS; from the analysis of the 48-inch pipeline network of the Mexico City's Water System, fragility formulations for segmented buried pipeline systems for two DGS levels are proposed. The novel parameter PGV{sup 2}/PGA, being PGV peak ground velocity and PGA peak ground acceleration, has been used as seismic parameter in these formulations, since it has shown better correlation to pipeline damage than PGV alone according to previous studies. By comparing the proposed fragilities, it is concluded that a change in the DGS level (from Low-Medium to High) could increase the pipeline repair rates (number of repairs per kilometer) by factors ranging from 1.3 to 2.0; being the higher the seismic intensity the lower the factor.« less

Neural Networks for Segregation of Multiple Objects: Visual Figure-Ground Separation and Auditory Pitch Perception.

NASA Astrophysics Data System (ADS)

Wyse, Lonce

An important component of perceptual object recognition is the segmentation into coherent perceptual units of the "blooming buzzing confusion" that bombards the senses. The work presented herein develops neural network models of some key processes of pre-attentive vision and audition that serve this goal. A neural network model, called an FBF (Feature -Boundary-Feature) network, is proposed for automatic parallel separation of multiple figures from each other and their backgrounds in noisy images. Figure-ground separation is accomplished by iterating operations of a Boundary Contour System (BCS) that generates a boundary segmentation of a scene, and a Feature Contour System (FCS) that compensates for variable illumination and fills-in surface properties using boundary signals. A key new feature is the use of the FBF filling-in process for the figure-ground separation of connected regions, which are subsequently more easily recognized. The new CORT-X 2 model is a feed-forward version of the BCS that is designed to detect, regularize, and complete boundaries in up to 50 percent noise. It also exploits the complementary properties of on-cells and off -cells to generate boundary segmentations and to compensate for boundary gaps during filling-in. In the realm of audition, many sounds are dominated by energy at integer multiples, or "harmonics", of a fundamental frequency. For such sounds (e.g., vowels in speech), the individual frequency components fuse, so that they are perceived as one sound source with a pitch at the fundamental frequency. Pitch is integral to separating auditory sources, as well as to speaker identification and speech understanding. A neural network model of pitch perception called SPINET (SPatial PItch NETwork) is developed and used to simulate a broader range of perceptual data than previous spectral models. The model employs a bank of narrowband filters as a simple model of basilar membrane mechanics, spectral on-center off-surround competitive interactions, and a "harmonic sieve" mechanism whereby the strength of a pitch depends only on spectral regions near harmonics. The model is evaluated using data involving mistuned components, shifted harmonics, complex tones with varying phase relationships, and continuous spectra such as rippled noise and narrow noise bands.

A proposed ground-water quality monitoring network for Idaho

USGS Publications Warehouse

Whitehead, R.L.; Parliman, D.J.

1979-01-01

A ground water quality monitoring network is proposed for Idaho. The network comprises 565 sites, 8 of which will require construction of new wells. Frequencies of sampling at the different sites are assigned at quarterly, semiannual, annual, and 5 years. Selected characteristics of the water will be monitored by both laboratory- and field-analysis methods. The network is designed to: (1) Enable water managers to keep abreast of the general quality of the State 's ground water, and (2) serve as a warning system for undesirable changes in ground-water quality. Data were compiled for hydrogeologic conditions, ground-water quality, cultural elements, and pollution sources. A ' hydrologic unit priority index ' is used to rank 84 hydrologic units (river basins or segments of river basins) of the State for monitoring according to pollution potential. Emphasis for selection of monitoring sites is placed on the 15 highest ranked units. The potential for pollution is greatest in areas of privately owned agricultural land. Other areas of pollution potential are residential development, mining and related processes, and hazardous waste disposal. Data are given for laboratory and field analyses, number of site visits, manpower, subsistence, and mileage, from which costs for implementing the network can be estimated. Suggestions are made for data storage and retrieval and for reporting changes in water quality. (Kosco-USGS)

Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization.

PubMed

Kainz, Philipp; Pfeiffer, Michael; Urschler, Martin

2017-01-01

Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization

PubMed Central

Kainz, Philipp; Pfeiffer, Michael

2017-01-01

Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN) for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses. PMID:29018612

Rethinking Skin Lesion Segmentation in a Convolutional Classifier.

PubMed

Burdick, Jack; Marques, Oge; Weinthal, Janet; Furht, Borko

2017-10-18

Melanoma is a fatal form of skin cancer when left undiagnosed. Computer-aided diagnosis systems powered by convolutional neural networks (CNNs) can improve diagnostic accuracy and save lives. CNNs have been successfully used in both skin lesion segmentation and classification. For reasons heretofore unclear, previous works have found image segmentation to be, conflictingly, both detrimental and beneficial to skin lesion classification. We investigate the effect of expanding the segmentation border to include pixels surrounding the target lesion. Ostensibly, segmenting a target skin lesion will remove inessential information, non-lesion skin, and artifacts to aid in classification. Our results indicate that segmentation border enlargement produces, to a certain degree, better results across all metrics of interest when using a convolutional based classifier built using the transfer learning paradigm. Consequently, preprocessing methods which produce borders larger than the actual lesion can potentially improve classifier performance, more than both perfect segmentation, using dermatologist created ground truth masks, and no segmentation altogether.

Evaluation of grout behind the lining of shield tunnels using ground-penetrating radar in the Shanghai Metro Line, China

NASA Astrophysics Data System (ADS)

Xie, Xiongyao; Liu, Yujian; Huang, Hongwei; Du, Jun; Zhang, Fengshou; Liu, Lanbo

2007-09-01

For shield tunnelling construction in soft soil areas, the coverage uniformity and quality of consolidation of the injected grout mortar behind the prefabricated tunnel segment is the main concern for tunnel safety and ground settlement. In this paper, ground-penetrating radar (GPR) was applied to evaluate the grout behind the tunnel lining segments in Shanghai, China. The dielectric permittivity of the grout material in Shanghai Metro tunnelling construction was measured in the laboratory. Combining physical modelling results with finite different time domain numerical modelling results, we suggest that the antenna with frequency 200 MHz is well suited to penetrate the reinforced steel bar network of the tunnel lining segment and testing grout patterns behind the segment. The electromagnetic velocity of the grout behind the segment of the tunnel is 0.1 m ns-1 by the analysis of field common-middle point data. A wave-translated method was put forward to process the GPR images. Furthermore, combining the information acquired by GPR with experience data, a GPR non-destructive test standard for the grout mortar evaluation in Shanghai Metro tunnel construction was brought forward. The grout behind the tunnel lining segment is classified into three types: uncompensated grout mortar with a thickness less than 10 cm, normal grout mortar with a thickness between 10 cm and 30 cm and overcompensated grout mortar, which is more than 30 cm thick. The classified method is easily put into practice.

Automated segmentation of 3D anatomical structures on CT images by using a deep convolutional network based on end-to-end learning approach

NASA Astrophysics Data System (ADS)

Zhou, Xiangrong; Takayama, Ryosuke; Wang, Song; Zhou, Xinxin; Hara, Takeshi; Fujita, Hiroshi

2017-02-01

We have proposed an end-to-end learning approach that trained a deep convolutional neural network (CNN) for automatic CT image segmentation, which accomplished a voxel-wised multiple classification to directly map each voxel on 3D CT images to an anatomical label automatically. The novelties of our proposed method were (1) transforming the anatomical structures segmentation on 3D CT images into a majority voting of the results of 2D semantic image segmentation on a number of 2D-slices from different image orientations, and (2) using "convolution" and "deconvolution" networks to achieve the conventional "coarse recognition" and "fine extraction" functions which were integrated into a compact all-in-one deep CNN for CT image segmentation. The advantage comparing to previous works was its capability to accomplish real-time image segmentations on 2D slices of arbitrary CT-scan-range (e.g. body, chest, abdomen) and produced correspondingly-sized output. In this paper, we propose an improvement of our proposed approach by adding an organ localization module to limit CT image range for training and testing deep CNNs. A database consisting of 240 3D CT scans and a human annotated ground truth was used for training (228 cases) and testing (the remaining 12 cases). We applied the improved method to segment pancreas and left kidney regions, respectively. The preliminary results showed that the accuracies of the segmentation results were improved significantly (pancreas was 34% and kidney was 8% increased in Jaccard index from our previous results). The effectiveness and usefulness of proposed improvement for CT image segmentations were confirmed.

GSFC network operations with Tracking and Data Relay Satellites

NASA Astrophysics Data System (ADS)

Spearing, R.; Perreten, D. E.

The Tracking and Data Relay Satellite System (TDRSS) Network (TN) has been developed to provide services to all NASA User spacecraft in near-earth orbits. Three inter-relating entities will provide these services. The TN has been transformed from a network continuously changing to meet User specific requirements to a network which is flexible to meet future needs without significant changes in operational concepts. Attention is given to the evolution of the TN network, the TN capabilities-space segment, forward link services, tracking services, return link services, the three basic capabilities, single access services, multiple access services, simulation services, the White Sands Ground Terminal, the NASA communications network, and the network control center.

GSFC network operations with Tracking and Data Relay Satellites

NASA Technical Reports Server (NTRS)

Spearing, R.; Perreten, D. E.

1984-01-01

The Tracking and Data Relay Satellite System (TDRSS) Network (TN) has been developed to provide services to all NASA User spacecraft in near-earth orbits. Three inter-relating entities will provide these services. The TN has been transformed from a network continuously changing to meet User specific requirements to a network which is flexible to meet future needs without significant changes in operational concepts. Attention is given to the evolution of the TN network, the TN capabilities-space segment, forward link services, tracking services, return link services, the three basic capabilities, single access services, multiple access services, simulation services, the White Sands Ground Terminal, the NASA communications network, and the network control center.

A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI.

PubMed

Avendi, M R; Kheradvar, Arash; Jafarkhani, Hamid

2016-05-01

Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. Convolutional networks are employed to automatically detect the LV chamber in MRI dataset. Stacked autoencoders are used to infer the LV shape. The inferred shape is incorporated into deformable models to improve the accuracy and robustness of the segmentation. We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively. Copyright © 2016 Elsevier B.V. All rights reserved.

Destination-directed, packet-switched architecture for a geostationary communications satellite network

NASA Technical Reports Server (NTRS)

Ivancic, William D.; Shalkhauser, Mary JO; Bobinsky, Eric A.; Soni, Nitin J.; Quintana, Jorge A.; Kim, Heechul; Wager, Paul; Vanderaar, Mark

1993-01-01

A major goal of the Digital Systems Technology Branch at the NASA Lewis Research Center is to identify and develop critical digital components and technologies that either enable new commercial missions or significantly enhance the performance, cost efficiency, and/or reliability of existing and planned space communications systems. NASA envisions a need for low-data-rate, interactive, direct-to-the-user communications services for data, voice, facsimile, and video conferencing. The network would provide enhanced very-small-aperture terminal (VSAT) communications services and be capable of handling data rates of 64 kbps through 2.048 Mbps in 64-kbps increments. Efforts have concentrated heavily on the space segment; however, the ground segment has been considered concurrently to ensure cost efficiency and realistic operational constraints. The focus of current space segment developments is a flexible, high-throughput, fault-tolerant onboard information-switching processor (ISP) for a geostationary satellite communications network. The Digital Systems Technology Branch is investigating both circuit and packet architectures for the ISP. Destination-directed, packet-switched architectures for geostationary communications satellites are addressed.

MSAT signalling and network management architectures

NASA Technical Reports Server (NTRS)

Garland, Peter; Keelty, J. Malcolm

1989-01-01

Spar Aerospace has been active in the design and definition of Mobile Satellite Systems since the mid 1970's. In work sponsored by the Canadian Department of Communications, various payload configurations have evolved. In addressing the payload configuration, the requirements of the mobile user, the service provider and the satellite operator have always been the most important consideration. The current Spar 11 beam satellite design is reviewed, and its capabilities to provide flexibility and potential for network growth within the WARC87 allocations are explored. To enable the full capabilities of the payload to be realized, a large amount of ground based Switching and Network Management infrastructure will be required, when space segment becomes available. Early indications were that a single custom designed Demand Assignment Multiple Access (DAMA) switch should be implemented to provide efficient use of the space segment. As MSAT has evolved into a multiple service concept, supporting many service providers, this architecture should be reviewed. Some possible signalling and Network Management solutions are explored.

Mobile telephony through LEO satellites: To OBP or not

NASA Technical Reports Server (NTRS)

Monte, Paul A.; Louie, Ming; Wiedeman, R.

1991-01-01

GLOBALSTAR is a satellite-based mobile communications system that is interoperable with the current and future Public Land Mobile Network (PLMN) and Public Switched Telephone Network (PSTN). The selection of the transponder type, bent-pipe, or onboard processing (OBP), for GLOBALSTAR is based on many criteria, each of which is essential to the commercial and technological feasibility of GLOBALSTAR. The trade study that was done to determine the pros and cons of a bent-pipe transponder or an onboard processing transponder is described. The design of GLOBALSTAR's telecommunications system is a multi-variable cost optimization between the cost and complexity of individual satellites, the number of satellites required to provide coverage to the service areas, the cost of launching the satellites into their selected orbits, the ground segment cost, user equipment cost, satellite voice channel capacity, and other issues. Emphasis is on the cost and complexity of the individual satellites, specifically the transponder type and the impact of the transponder type on satellite and ground segment cost, satellite power and weight, and satellite voice channel capacity.

Mobile telephony through LEO satellites: To OBP or not

NASA Astrophysics Data System (ADS)

Monte, Paul A.; Louie, Ming; Wiedeman, R.

1991-11-01

GLOBALSTAR is a satellite-based mobile communications system that is interoperable with the current and future Public Land Mobile Network (PLMN) and Public Switched Telephone Network (PSTN). The selection of the transponder type, bent-pipe, or onboard processing (OBP), for GLOBALSTAR is based on many criteria, each of which is essential to the commercial and technological feasibility of GLOBALSTAR. The trade study that was done to determine the pros and cons of a bent-pipe transponder or an onboard processing transponder is described. The design of GLOBALSTAR's telecommunications system is a multi-variable cost optimization between the cost and complexity of individual satellites, the number of satellites required to provide coverage to the service areas, the cost of launching the satellites into their selected orbits, the ground segment cost, user equipment cost, satellite voice channel capacity, and other issues. Emphasis is on the cost and complexity of the individual satellites, specifically the transponder type and the impact of the transponder type on satellite and ground segment cost, satellite power and weight, and satellite voice channel capacity.

Transport time and care processes for patients transferred with ST-segment-elevation myocardial infarction: the reperfusion in acute myocardial infarction in Carolina emergency rooms experience.

PubMed

Muñoz, Daniel; Roettig, Mayme L; Monk, Lisa; Al-Khalidi, Hussein; Jollis, James G; Granger, Christopher B

2012-08-01

For patients with ST-segment elevation myocardial infarction transferred for primary percutaneous coronary intervention, guidelines have called for device activation within 90 minutes of initial presentation. Fewer than 20% of transferred patients are treated in such a timely fashion. We examine the association between transfer drive times and door-to-device (D2D) times in a network of North Carolina hospitals. We compare the feasibility of timely percutaneous coronary intervention using ground versus air transfer. We perform a retrospective analysis of the relationship between transfer drive times and D2D times in a 119-hospital ST-segment-elevation myocardial infarction statewide network. Between July 2008 and December 2009, 1537 ST-segment-elevation myocardial infarction patients underwent interhospital transfer for reperfusion via primary percutaneous coronary intervention. For ground transfers, median D2D time was 93 minutes for drive times ≤30 minutes, 117 minutes for drive times of 31 to 45 minutes, and 121 minutes for drive times >45 minutes. For air transfers, median D2D time was 125 minutes for drive times of 31 to 45 minutes and 138 minutes for drive times >45 minutes. Helicopter transport was associated with longer door-in door-out times and, ultimately, was associated with median D2D times that exceeded guideline recommendations, no matter the transfer drive time category. In a well-developed ST-segment-elevation myocardial infarction system, D2D times within 90 to 120 minutes appear most feasible for hospitals within 30-minute transfer drive time. Helicopter transport did not offer D2D time advantages for transferred STEMI patients. This finding appears to be attributable to comparably longer door-in door-out times for air transfers.

NASA's mobile satellite development program

NASA Technical Reports Server (NTRS)

Rafferty, William; Dessouky, Khaled; Sue, Miles

1988-01-01

A Mobile Satellite System (MSS) will provide data and voice communications over a vast geographical area to a large population of mobile users. A technical overview is given of the extensive research and development studies and development performed under NASA's mobile satellite program (MSAT-X) in support of the introduction of a U.S. MSS. The critical technologies necessary to enable such a system are emphasized: vehicle antennas, modulation and coding, speech coders, networking and propagation characterization. Also proposed is a first, and future generation MSS architecture based upon realized ground segment equipment and advanced space segment studies.

Technology Infusion of CodeSonar into the Space Network Ground Segment

NASA Technical Reports Server (NTRS)

Benson, Markland J.

2009-01-01

This slide presentation reviews the applicability of CodeSonar to the Space Network software. CodeSonar is a commercial off the shelf system that analyzes programs written in C, C++ or Ada for defects in the code. Software engineers use CodeSonar results as an input to the existing source code inspection process. The study is focused on large scale software developed using formal processes. The systems studied are mission critical in nature but some use commodity computer systems.

The Structure of the University Network: From the Soviet to Russian "Master Plan"

ERIC Educational Resources Information Center

Kuzminov, Ia. I.; Semenov, D. S.; Froumin, I. D.

2015-01-01

The authors discuss the underpinnings of structural analysis in the higher education system. The article justifies why it focuses on specific labor market segments and the nature of the university's basic product as grounds for proposing a typology and groups of institutions. A Soviet "master plan" is reconstructed on the basis of the…

TuMore: generation of synthetic brain tumor MRI data for deep learning based segmentation approaches

NASA Astrophysics Data System (ADS)

Lindner, Lydia; Pfarrkirchner, Birgit; Gsaxner, Christina; Schmalstieg, Dieter; Egger, Jan

2018-03-01

Accurate segmentation and measurement of brain tumors plays an important role in clinical practice and research, as it is critical for treatment planning and monitoring of tumor growth. However, brain tumor segmentation is one of the most challenging tasks in medical image analysis. Since manual segmentations are subjective, time consuming and neither accurate nor reliable, there exists a need for objective, robust and fast automated segmentation methods that provide competitive performance. Therefore, deep learning based approaches are gaining interest in the field of medical image segmentation. When the training data set is large enough, deep learning approaches can be extremely effective, but in domains like medicine, only limited data is available in the majority of cases. Due to this reason, we propose a method that allows to create a large dataset of brain MRI (Magnetic Resonance Imaging) images containing synthetic brain tumors - glioblastomas more specifically - and the corresponding ground truth, that can be subsequently used to train deep neural networks.

Volcano Monitoring: A Case Study in Pervasive Computing

NASA Astrophysics Data System (ADS)

Peterson, Nina; Anusuya-Rangappa, Lohith; Shirazi, Behrooz A.; Song, Wenzhan; Huang, Renjie; Tran, Daniel; Chien, Steve; Lahusen, Rick

Recent advances in wireless sensor network technology have provided robust and reliable solutions for sophisticated pervasive computing applications such as inhospitable terrain environmental monitoring. We present a case study for developing a real-time pervasive computing system, called OASIS for optimized autonomous space in situ sensor-web, which combines ground assets (a sensor network) and space assets (NASA’s earth observing (EO-1) satellite) to monitor volcanic activities at Mount St. Helens. OASIS’s primary goals are: to integrate complementary space and in situ ground sensors into an interactive and autonomous sensorweb, to optimize power and communication resource management of the sensorweb and to provide mechanisms for seamless and scalable fusion of future space and in situ components. The OASIS in situ ground sensor network development addresses issues related to power management, bandwidth management, quality of service management, topology and routing management, and test-bed design. The space segment development consists of EO-1 architectural enhancements, feedback of EO-1 data into the in situ component, command and control integration, data ingestion and dissemination and field demonstrations.

Feedback Enhances Feedforward Figure-Ground Segmentation by Changing Firing Mode

PubMed Central

Supèr, Hans; Romeo, August

2011-01-01

In the visual cortex, feedback projections are conjectured to be crucial in figure-ground segregation. However, the precise function of feedback herein is unclear. Here we tested a hypothetical model of reentrant feedback. We used a previous developed 2-layered feedforwardspiking network that is able to segregate figure from ground and included feedback connections. Our computer model data show that without feedback, neurons respond with regular low-frequency (∼9 Hz) bursting to a figure-ground stimulus. After including feedback the firing pattern changed into a regular (tonic) spiking pattern. In this state, we found an extra enhancement of figure responses and a further suppression of background responses resulting in a stronger figure-ground signal. Such push-pull effect was confirmed by comparing the figure-ground responses withthe responses to a homogenous texture. We propose that feedback controlsfigure-ground segregation by influencing the neural firing patterns of feedforward projecting neurons. PMID:21738747

Feedback enhances feedforward figure-ground segmentation by changing firing mode.

PubMed

Supèr, Hans; Romeo, August

2011-01-01

In the visual cortex, feedback projections are conjectured to be crucial in figure-ground segregation. However, the precise function of feedback herein is unclear. Here we tested a hypothetical model of reentrant feedback. We used a previous developed 2-layered feedforward spiking network that is able to segregate figure from ground and included feedback connections. Our computer model data show that without feedback, neurons respond with regular low-frequency (∼9 Hz) bursting to a figure-ground stimulus. After including feedback the firing pattern changed into a regular (tonic) spiking pattern. In this state, we found an extra enhancement of figure responses and a further suppression of background responses resulting in a stronger figure-ground signal. Such push-pull effect was confirmed by comparing the figure-ground responses with the responses to a homogenous texture. We propose that feedback controls figure-ground segregation by influencing the neural firing patterns of feedforward projecting neurons.

Global competition and local cooperation in a network of neural oscillators

NASA Astrophysics Data System (ADS)

Terman, David; Wang, DeLiang

An architecture of locally excitatory, globally inhibitory oscillator networks is proposed and investigated both analytically and by computer simulation. The model for each oscillator corresponds to a standard relaxation oscillator with two time scales. Oscillators are locally coupled by a scheme that resembles excitatory synaptic coupling, and each oscillator also inhibits other oscillators through a common inhibitor. Oscillators are driven to be oscillatory by external stimulation. The network exhibits a mechanism of selective gating, whereby an oscillator jumping up to its active phase rapidly recruits the oscillators stimulated by the same pattern, while preventing the other oscillators from jumping up. We show analytically that with the selective gating mechanism, the network rapidly achieves both synchronization within blocks of oscillators that are stimulated by connected regions and desynchronization between different blocks. Computer simulations demonstrate the model's promising ability for segmenting multiple input patterns in real time. This model lays a physical foundation for the oscillatory correlation theory of feature binding and may provide an effective computational framework for scene segmentation and figure/ ground segregation.

Taking the Evolutionary Road to Developing an In-House Cost Estimate

NASA Technical Reports Server (NTRS)

Jacintho, David; Esker, Lind; Herman, Frank; Lavaque, Rodolfo; Regardie, Myma

2011-01-01

This slide presentation reviews the process and some of the problems and challenges of developing an In-House Cost Estimate (IHCE). Using as an example the Space Network Ground Segment Sustainment (SGSS) project, the presentation reviews the phases for developing a Cost estimate within the project to estimate government and contractor project costs to support a budget request.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

An overview of the technical design of MSAT mobile satellite communications services

NASA Astrophysics Data System (ADS)

Davies, N. George

The Canadian MSAT mobile satellite communications system is being implemented in cooperation with the American Mobile Satellite Consortium (AMSC). Two satellites are to be jointly acquired and each satellite is expected to backup the other. This paper describes the technical concepts of the services to be offered and the baseline planning of the infrastructure for the ground segment. MSAT service requirements are analyzed for mobile radio, telephone, data, and aeronautical services. The MSAT system will use nine beams in a narrow range of L-band frequencies with frequency reuse. Beams may be added to cover flight information areas in the Atlantic and Pacific oceans. The elements of the network architecture are: a network control centre, data hub stations, gateway stations, base stations, mobile terminals, and a signalling system to interconnect the elements of the system. The network control center will manage the network and allocate space segment capacity; data hub stations will support a switched packet mobile data service; the gateway stations will provide interconnection to the public telephone system and data networks; and the base stations will support private circuit switched voice and data services. Several alternative designs for the signalling system are described.

Feed-forward segmentation of figure-ground and assignment of border-ownership.

PubMed

Supèr, Hans; Romeo, August; Keil, Matthias

2010-05-19

Figure-ground is the segmentation of visual information into objects and their surrounding backgrounds. Two main processes herein are boundary assignment and surface segregation, which rely on the integration of global scene information. Recurrent processing either by intrinsic horizontal connections that connect surrounding neurons or by feedback projections from higher visual areas provide such information, and are considered to be the neural substrate for figure-ground segmentation. On the contrary, a role of feedforward projections in figure-ground segmentation is unknown. To have a better understanding of a role of feedforward connections in figure-ground organization, we constructed a feedforward spiking model using a biologically plausible neuron model. By means of surround inhibition our simple 3-layered model performs figure-ground segmentation and one-sided border-ownership coding. We propose that the visual system uses feed forward suppression for figure-ground segmentation and border-ownership assignment.

Feed-Forward Segmentation of Figure-Ground and Assignment of Border-Ownership

PubMed Central

Supèr, Hans; Romeo, August; Keil, Matthias

2010-01-01

Figure-ground is the segmentation of visual information into objects and their surrounding backgrounds. Two main processes herein are boundary assignment and surface segregation, which rely on the integration of global scene information. Recurrent processing either by intrinsic horizontal connections that connect surrounding neurons or by feedback projections from higher visual areas provide such information, and are considered to be the neural substrate for figure-ground segmentation. On the contrary, a role of feedforward projections in figure-ground segmentation is unknown. To have a better understanding of a role of feedforward connections in figure-ground organization, we constructed a feedforward spiking model using a biologically plausible neuron model. By means of surround inhibition our simple 3-layered model performs figure-ground segmentation and one-sided border-ownership coding. We propose that the visual system uses feed forward suppression for figure-ground segmentation and border-ownership assignment. PMID:20502718

Automated detection of Schlemm's canal in spectral-domain optical coherence tomography

NASA Astrophysics Data System (ADS)

Tom, Manu; Ramakrishnan, Vignesh; van Oterendorp, Christian; Deserno, Thomas M.

2015-03-01

Recent advances in optical coherence tomography (OCT) technology allow in vivo imaging of the complex network of intra-scleral aqueous veins in the anterior segment of the eye. Pathological changes in this network, draining the aqueous humor from the eye, are considered to play a role in intraocular pressure elevation, which can lead to glaucoma, one of the major causes of blindness in the world. Through acquisition of OCT volume scans of the anterior eye segment, we aim at reconstructing the three dimensional network of aqueous veins in healthy and glaucomatous subjects. A novel algorithm for segmentation of the three-dimensional (3D) vessel system in human Schlemms canal is presented analyzing frames of spectral domain OCT (SD-OCT) of the eyes surface in either horizontal or vertical orientation. Distortions such as vertical stripes are caused by the superficial blood vessels in the conjunctiva and the episclera. They are removed in the discrete Fourier domain (DFT) masking particular frequencies. Feature-based rigid registration of these noise-filtered images is then performed using the scale invariant feature transform (SIFT). Segmentation of the vessels deep in the sclera originating at or in the vicinity of or having indirect connection to the Schlemm's canal is then performed with 3D region growing technique. The segmented vessels are visualized in 3D providing diagnostically relevant information to the physicians. A proof-of-concept study was performed on a healthy volunteer before and after a pharmaceutical narrowing of Schlemm's canal. A relative decreases 17% was measured based on manual ground truth and the image processing method.

Space Link Extension Protocol Emulation for High-Throughput, High-Latency Network Connections

NASA Technical Reports Server (NTRS)

Tchorowski, Nicole; Murawski, Robert

2014-01-01

New space missions require higher data rates and new protocols to meet these requirements. These high data rate space communication links push the limitations of not only the space communication links, but of the ground communication networks and protocols which forward user data to remote ground stations (GS) for transmission. The Consultative Committee for Space Data Systems, (CCSDS) Space Link Extension (SLE) standard protocol is one protocol that has been proposed for use by the NASA Space Network (SN) Ground Segment Sustainment (SGSS) program. New protocol implementations must be carefully tested to ensure that they provide the required functionality, especially because of the remote nature of spacecraft. The SLE protocol standard has been tested in the NASA Glenn Research Center's SCENIC Emulation Lab in order to observe its operation under realistic network delay conditions. More specifically, the delay between then NASA Integrated Services Network (NISN) and spacecraft has been emulated. The round trip time (RTT) delay for the continental NISN network has been shown to be up to 120ms; as such the SLE protocol was tested with network delays ranging from 0ms to 200ms. Both a base network condition and an SLE connection were tested with these RTT delays, and the reaction of both network tests to the delay conditions were recorded. Throughput for both of these links was set at 1.2Gbps. The results will show that, in the presence of realistic network delay, the SLE link throughput is significantly reduced while the base network throughput however remained at the 1.2Gbps specification. The decrease in SLE throughput has been attributed to the implementation's use of blocking calls. The decrease in throughput is not acceptable for high data rate links, as the link requires constant data a flow in order for spacecraft and ground radios to stay synchronized, unless significant data is queued a the ground station. In cases where queuing the data is not an option, such as during real time transmissions, the SLE implementation cannot support high data rate communication.

On measurement noise in the European TWSTFT network.

PubMed

Piester, Dirk; Bauch, Andreas; Becker, Jürgen; Staliuniene, Egle; Schlunegger, Christian

2008-09-01

Two-way satellite time and frequency transfer (TWSTFT) using geostationary telecommunication satellites is widely used in the timing community today and has also been chosen as the primary means to effect synchronization of elements of the ground segment of the European satellite navigation system Galileo. We investigated the link performance in a multistation network based on operational parameters such as the number of simultaneously transmitting stations, transmit and receive power, and chip rates of the pseudorandom noise modulation of the transmitted signals. Our work revealed that TWSTFT through a "quiet" transponder channel (2 stations transmitting only) leads to a measurement noise, expressed by the 1 pps jitter, reduced by a factor of 1.4 compared with a busy transponder carrying signals of 12 stations. The frequency transfer capability expressed by the Allan deviation is reduced at short averaging times by the same amount. At averaging times of >1 d, no such reduction could be observed, which points to the fact that other noise sources dominate at such averaging times. We also found that higher transmit power increases the carrier-to-noise density ratio at the receive station and thus entails lower jitter but causes interference with other station's signals. In addition, the use of lower chip rates, which could be accommodated by a reduced assigned bandwidth on the satellite transponder, is not recommended. The 1 pps jitter would go up by a factor of 2.5 when going from 2.5 MCh/s to 1 MCh/s. The 2 Galileo precise timing facilities (PTFs) can be included in the currently operated network of 12 stations in Europe and all requirements on the TWSTFT performance can be met, provided that suitable ground equipment will be installed in the Galileo ground segment.

Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets.

PubMed

Hu, Peijun; Wu, Fa; Peng, Jialin; Bao, Yuanyuan; Chen, Feng; Kong, Dexing

2017-03-01

Multi-organ segmentation from CT images is an essential step for computer-aided diagnosis and surgery planning. However, manual delineation of the organs by radiologists is tedious, time-consuming and poorly reproducible. Therefore, we propose a fully automatic method for the segmentation of multiple organs from three-dimensional abdominal CT images. The proposed method employs deep fully convolutional neural networks (CNNs) for organ detection and segmentation, which is further refined by a time-implicit multi-phase evolution method. Firstly, a 3D CNN is trained to automatically localize and delineate the organs of interest with a probability prediction map. The learned probability map provides both subject-specific spatial priors and initialization for subsequent fine segmentation. Then, for the refinement of the multi-organ segmentation, image intensity models, probability priors as well as a disjoint region constraint are incorporated into an unified energy functional. Finally, a novel time-implicit multi-phase level-set algorithm is utilized to efficiently optimize the proposed energy functional model. Our method has been evaluated on 140 abdominal CT scans for the segmentation of four organs (liver, spleen and both kidneys). With respect to the ground truth, average Dice overlap ratios for the liver, spleen and both kidneys are 96.0, 94.2 and 95.4%, respectively, and average symmetric surface distance is less than 1.3 mm for all the segmented organs. The computation time for a CT volume is 125 s in average. The achieved accuracy compares well to state-of-the-art methods with much higher efficiency. A fully automatic method for multi-organ segmentation from abdominal CT images was developed and evaluated. The results demonstrated its potential in clinical usage with high effectiveness, robustness and efficiency.

Automated construction of arterial and venous trees in retinal images.

PubMed

Hu, Qiao; Abràmoff, Michael D; Garvin, Mona K

2015-10-01

While many approaches exist to segment retinal vessels in fundus photographs, only a limited number focus on the construction and disambiguation of arterial and venous trees. Previous approaches are local and/or greedy in nature, making them susceptible to errors or limiting their applicability to large vessels. We propose a more global framework to generate arteriovenous trees in retinal images, given a vessel segmentation. In particular, our approach consists of three stages. The first stage is to generate an overconnected vessel network, named the vessel potential connectivity map (VPCM), consisting of vessel segments and the potential connectivity between them. The second stage is to disambiguate the VPCM into multiple anatomical trees, using a graph-based metaheuristic algorithm. The third stage is to classify these trees into arterial or venous (A/V) trees. We evaluated our approach with a ground truth built based on a public database, showing a pixel-wise classification accuracy of 88.15% using a manual vessel segmentation as input, and 86.11% using an automatic vessel segmentation as input.

Deficit in figure-ground segmentation following closed head injury.

PubMed

Baylis, G C; Baylis, L L

1997-08-01

Patient CB showed a severe impairment in figure-ground segmentation following a closed head injury. Unlike normal subjects, CB was unable to parse smaller and brighter parts of stimuli as figure. Moreover, she did not show the normal effect that symmetrical regions are seen as figure, although she was able to make overt judgments of symmetry. Since she was able to attend normally to isolated objects, CB demonstrates a dissociation between figure ground segmentation and subsequent processes of attention. Despite her severe impairment in figure-ground segmentation, CB showed normal 'parallel' single feature visual search. This suggests that figure-ground segmentation is dissociable from 'preattentive' processes such as visual search.

Tracking and data relay satellite system (TDRSS) capabilities

NASA Astrophysics Data System (ADS)

Spearing, R. E.

1985-10-01

The Tracking and Data Relay Satellite System (TDRSS) is the latest implementation to tracking and data acquisition network for near-earth orbiting satellite support designed to meet the requirements of the current and projected (to the year 2000) satellite user community. The TDRSS consists of a space segment (SS) and a ground segment (GS) that fit within NASA's Space Network (SN) complex controlled at the Goddard Space Flight Center. The SS currently employs a single satellite, TDRS-1, with two additional satellites to be deployed in January 1986 and July 1986. The GS contains the communications and equipment required to manage the three TDR satellites and to transmit and receive information to and from TDRSS user satellites. Diagrams and tables illustrating the TDRSS signal characteristics, the situation of TDRSS within the SN, the SN operations and element interrelationships, as well as future plans for new missions are included.

Tracking and data relay satellite system (TDRSS) capabilities

NASA Technical Reports Server (NTRS)

Spearing, R. E.

1985-01-01

The Tracking and Data Relay Satellite System (TDRSS) is the latest implementation to tracking and data acquisition network for near-earth orbiting satellite support designed to meet the requirements of the current and projected (to the year 2000) satellite user community. The TDRSS consists of a space segment (SS) and a ground segment (GS) that fit within NASA's Space Network (SN) complex controlled at the Goddard Space Flight Center. The SS currently employs a single satellite, TDRS-1, with two additional satellites to be deployed in January 1986 and July 1986. The GS contains the communications and equipment required to manage the three TDR satellites and to transmit and receive information to and from TDRSS user satellites. Diagrams and tables illustrating the TDRSS signal characteristics, the situation of TDRSS within the SN, the SN operations and element interrelationships, as well as future plans for new missions are included.

Customer premise service study for 30/20 GHz satellite system

NASA Technical Reports Server (NTRS)

Milton, R. T.; Ross, D. P.; Harcar, A. R.; Freedenberg, P.; Schoen, D.

1983-01-01

Satellite systems in which the space segment operates in the 30/20 GHz frequency band are defined and compared as to their potential for providing various types of communications services to customer premises and the economic and technical feasibility of doing so. Technical tasks performed include: market postulation, definition of the ground segment, definition of the space segment, definition of the integrated satellite system, service costs for satellite systems, sensitivity analysis, and critical technology. Based on an analysis of market data, a sufficiently large market for services is projected so as to make the system economically viable. A large market, and hence a high capacity satellite system, is found to be necessary to minimize service costs, i.e., economy of scale is found to hold. The wide bandwidth expected to be available in the 30/20 GHz band, along with frequency reuse which further increases the effective system bandwidth, makes possible the high capacity system. Extensive ground networking is required in most systems to both connect users into the system and to interconnect Earth stations to provide spatial diversity. Earth station spatial diversity is found to be a cost effective means of compensating the large fading encountered in the 30/20 GHz operating band.

Direct Data Distribution From Low-Earth Orbit

NASA Technical Reports Server (NTRS)

Budinger, James M.; Fujikawa, Gene; Kunath, Richard R.; Nguyen, Nam T.; Romanofsky, Robert R.; Spence, Rodney L.

1997-01-01

NASA Lewis Research Center (LeRC) is developing the space and ground segment technologies necessary to demonstrate a direct data distribution (1)3) system for use in space-to-ground communication links from spacecraft in low-Earth orbit (LEO) to strategically located tracking ground terminals. The key space segment technologies include a K-band (19 GHz) MMIC-based transmit phased array antenna, and a multichannel bandwidth- and power-efficient digital encoder/modulate with an aggregate data rate of 622 Mb/s. Along with small (1.8 meter), low-cost tracking terminals on the ground, the D3 system enables affordable distribution of data to the end user or archive facility through interoperability with commercial terrestrial telecommunications networks. The D3 system is applicable to both government and commercial science and communications spacecraft in LEO. The features and benefits of the D3 system concept are described. Starting with typical orbital characteristics, a set of baseline requirements for representative applications is developed, including requirements for onboard storage and tracking terminals, and sample link budgets are presented. Characteristics of the transmit array antenna and digital encoder/modulator are described. The architecture and components of the tracking terminal are described, including technologies for the next generation terminal. Candidate flights of opportunity for risk mitigation and space demonstration of the D3 features are identified.

Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: A clinical study.

PubMed

Dolz, Jose; Betrouni, Nacim; Quidet, Mathilde; Kharroubi, Dris; Leroy, Henri A; Reyns, Nicolas; Massoptier, Laurent; Vermandel, Maximilien

2016-09-01

Delineation of organs at risk (OARs) is a crucial step in surgical and treatment planning in brain cancer, where precise OARs volume delineation is required. However, this task is still often manually performed, which is time-consuming and prone to observer variability. To tackle these issues a deep learning approach based on stacking denoising auto-encoders has been proposed to segment the brainstem on magnetic resonance images in brain cancer context. Additionally to classical features used in machine learning to segment brain structures, two new features are suggested. Four experts participated in this study by segmenting the brainstem on 9 patients who underwent radiosurgery. Analysis of variance on shape and volume similarity metrics indicated that there were significant differences (p<0.05) between the groups of manual annotations and automatic segmentations. Experimental evaluation also showed an overlapping higher than 90% with respect to the ground truth. These results are comparable, and often higher, to those of the state of the art segmentation methods but with a considerably reduction of the segmentation time. Copyright © 2016 Elsevier Ltd. All rights reserved.

A superpixel-based framework for automatic tumor segmentation on breast DCE-MRI

NASA Astrophysics Data System (ADS)

Yu, Ning; Wu, Jia; Weinstein, Susan P.; Gaonkar, Bilwaj; Keller, Brad M.; Ashraf, Ahmed B.; Jiang, YunQing; Davatzikos, Christos; Conant, Emily F.; Kontos, Despina

2015-03-01

Accurate and efficient automated tumor segmentation in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is highly desirable for computer-aided tumor diagnosis. We propose a novel automatic segmentation framework which incorporates mean-shift smoothing, superpixel-wise classification, pixel-wise graph-cuts partitioning, and morphological refinement. A set of 15 breast DCE-MR images, obtained from the American College of Radiology Imaging Network (ACRIN) 6657 I-SPY trial, were manually segmented to generate tumor masks (as ground truth) and breast masks (as regions of interest). Four state-of-the-art segmentation approaches based on diverse models were also utilized for comparison. Based on five standard evaluation metrics for segmentation, the proposed framework consistently outperformed all other approaches. The performance of the proposed framework was: 1) 0.83 for Dice similarity coefficient, 2) 0.96 for pixel-wise accuracy, 3) 0.72 for VOC score, 4) 0.79 mm for mean absolute difference, and 5) 11.71 mm for maximum Hausdorff distance, which surpassed the second best method (i.e., adaptive geodesic transformation), a semi-automatic algorithm depending on precise initialization. Our results suggest promising potential applications of our segmentation framework in assisting analysis of breast carcinomas.

Quantitative analysis of vascular parameters for micro-CT imaging of vascular networks with multi-resolution.

PubMed

Zhao, Fengjun; Liang, Jimin; Chen, Xueli; Liu, Junting; Chen, Dongmei; Yang, Xiang; Tian, Jie

2016-03-01

Previous studies showed that all the vascular parameters from both the morphological and topological parameters were affected with the altering of imaging resolutions. However, neither the sensitivity analysis of the vascular parameters at multiple resolutions nor the distinguishability estimation of vascular parameters from different data groups has been discussed. In this paper, we proposed a quantitative analysis method of vascular parameters for vascular networks of multi-resolution, by analyzing the sensitivity of vascular parameters at multiple resolutions and estimating the distinguishability of vascular parameters from different data groups. Combining the sensitivity and distinguishability, we designed a hybrid formulation to estimate the integrated performance of vascular parameters in a multi-resolution framework. Among the vascular parameters, degree of anisotropy and junction degree were two insensitive parameters that were nearly irrelevant with resolution degradation; vascular area, connectivity density, vascular length, vascular junction and segment number were five parameters that could better distinguish the vascular networks from different groups and abide by the ground truth. Vascular area, connectivity density, vascular length and segment number not only were insensitive to multi-resolution but could also better distinguish vascular networks from different groups, which provided guidance for the quantification of the vascular networks in multi-resolution frameworks.

Semantic Segmentation and Difference Extraction via Time Series Aerial Video Camera and its Application

NASA Astrophysics Data System (ADS)

Amit, S. N. K.; Saito, S.; Sasaki, S.; Kiyoki, Y.; Aoki, Y.

2015-04-01

Google earth with high-resolution imagery basically takes months to process new images before online updates. It is a time consuming and slow process especially for post-disaster application. The objective of this research is to develop a fast and effective method of updating maps by detecting local differences occurred over different time series; where only region with differences will be updated. In our system, aerial images from Massachusetts's road and building open datasets, Saitama district datasets are used as input images. Semantic segmentation is then applied to input images. Semantic segmentation is a pixel-wise classification of images by implementing deep neural network technique. Deep neural network technique is implemented due to being not only efficient in learning highly discriminative image features such as road, buildings etc., but also partially robust to incomplete and poorly registered target maps. Then, aerial images which contain semantic information are stored as database in 5D world map is set as ground truth images. This system is developed to visualise multimedia data in 5 dimensions; 3 dimensions as spatial dimensions, 1 dimension as temporal dimension, and 1 dimension as degenerated dimensions of semantic and colour combination dimension. Next, ground truth images chosen from database in 5D world map and a new aerial image with same spatial information but different time series are compared via difference extraction method. The map will only update where local changes had occurred. Hence, map updating will be cheaper, faster and more effective especially post-disaster application, by leaving unchanged region and only update changed region.

Autonomy in military aircraft

NASA Astrophysics Data System (ADS)

Henderson, D. W.

Military users are becoming increasingly dependent on satellites for vital services related to communication, surveillance information, navigation, and meteorological data. The current military spacecraft, however, need the services of a ground support network which is vulnerable in connection with a variety of threats. It has, therefore, been proposed to decrease the dependence of the satellites on the ground segment by improving satellite autonomy, and the Satellite Autonomy Program at the recently created Air Force Space Technology Center is developing the Autonomous Redundancy and Maintenance Management Subsystem (ARMMS) for a near term generic autonomy solution. Attention is given to the implementation of autonomy and technological requirements for ensuring autonomy.

Automated construction of arterial and venous trees in retinal images

PubMed Central

Hu, Qiao; Abràmoff, Michael D.; Garvin, Mona K.

2015-01-01

Abstract. While many approaches exist to segment retinal vessels in fundus photographs, only a limited number focus on the construction and disambiguation of arterial and venous trees. Previous approaches are local and/or greedy in nature, making them susceptible to errors or limiting their applicability to large vessels. We propose a more global framework to generate arteriovenous trees in retinal images, given a vessel segmentation. In particular, our approach consists of three stages. The first stage is to generate an overconnected vessel network, named the vessel potential connectivity map (VPCM), consisting of vessel segments and the potential connectivity between them. The second stage is to disambiguate the VPCM into multiple anatomical trees, using a graph-based metaheuristic algorithm. The third stage is to classify these trees into arterial or venous (A/V) trees. We evaluated our approach with a ground truth built based on a public database, showing a pixel-wise classification accuracy of 88.15% using a manual vessel segmentation as input, and 86.11% using an automatic vessel segmentation as input. PMID:26636114

Pneumothorax detection in chest radiographs using convolutional neural networks

NASA Astrophysics Data System (ADS)

Blumenfeld, Aviel; Konen, Eli; Greenspan, Hayit

2018-02-01

This study presents a computer assisted diagnosis system for the detection of pneumothorax (PTX) in chest radiographs based on a convolutional neural network (CNN) for pixel classification. Using a pixel classification approach allows utilization of the texture information in the local environment of each pixel while training a CNN model on millions of training patches extracted from a relatively small dataset. The proposed system uses a pre-processing step of lung field segmentation to overcome the large variability in the input images coming from a variety of imaging sources and protocols. Using a CNN classification, suspected pixel candidates are extracted within each lung segment. A postprocessing step follows to remove non-physiological suspected regions and noisy connected components. The overall percentage of suspected PTX area was used as a robust global decision for the presence of PTX in each lung. The system was trained on a set of 117 chest x-ray images with ground truth segmentations of the PTX regions. The system was tested on a set of 86 images and reached diagnosis accuracy of AUC=0.95. Overall preliminary results are promising and indicate the growing ability of CAD based systems to detect findings in medical imaging on a clinical level accuracy.

Ulysses operations at Jupiter - Planning for the unknown

NASA Technical Reports Server (NTRS)

Angold, N.; Beech, P.; Garcia-Perez, R.; Mcgarry, A.; Standley, S.

1992-01-01

The operational preparations for the Ulysses encounter with Jupiter are described with particular attention given to requirements for survival in the Jovian environment, ground-segment planning, a deep-space network, and encounter activities. It is concluded that the successful operation of the Ulysses spacecraft at Jupiter was the culmination of many years of activity, from spacecraft design and mission planning to the coordination of the encounter activities and production of the detailed timeline.

Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data.

PubMed

Karnowski, Thomas P; Govindasamy, V; Tobin, Kenneth W; Chaum, Edward; Abramoff, M D

2008-01-01

In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90% of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.

Ground truth crop proportion summaries for US segments, 1976-1979

NASA Technical Reports Server (NTRS)

Horvath, R. (Principal Investigator); Rice, D.; Wessling, T.

1981-01-01

The original ground truth data was collected, digitized, and registered to LANDSAT data for use in the LACIE and AgRISTARS projects. The numerous ground truth categories were consolidated into fewer classes of crops or crop conditions and counted occurrences of these classes for each segment. Tables are presented in which the individual entries are the percentage of total segment area assigned to a given class. The ground truth summaries were prepared from a 20% sample of the scene. An analysis indicates that this size of sample provides sufficient accuracy for use of the data in initial segment screening.

An improved wavelet neural network medical image segmentation algorithm with combined maximum entropy

NASA Astrophysics Data System (ADS)

Hu, Xiaoqian; Tao, Jinxu; Ye, Zhongfu; Qiu, Bensheng; Xu, Jinzhang

2018-05-01

In order to solve the problem of medical image segmentation, a wavelet neural network medical image segmentation algorithm based on combined maximum entropy criterion is proposed. Firstly, we use bee colony algorithm to optimize the network parameters of wavelet neural network, get the parameters of network structure, initial weights and threshold values, and so on, we can quickly converge to higher precision when training, and avoid to falling into relative extremum; then the optimal number of iterations is obtained by calculating the maximum entropy of the segmented image, so as to achieve the automatic and accurate segmentation effect. Medical image segmentation experiments show that the proposed algorithm can reduce sample training time effectively and improve convergence precision, and segmentation effect is more accurate and effective than traditional BP neural network (back propagation neural network : a multilayer feed forward neural network which trained according to the error backward propagation algorithm.

Segmentation of corneal endothelium images using a U-Net-based convolutional neural network.

PubMed

Fabijańska, Anna

2018-04-18

Diagnostic information regarding the health status of the corneal endothelium may be obtained by analyzing the size and the shape of the endothelial cells in specular microscopy images. Prior to the analysis, the endothelial cells need to be extracted from the image. Up to today, this has been performed manually or semi-automatically. Several approaches to automatic segmentation of endothelial cells exist; however, none of them is perfect. Therefore this paper proposes to perform cell segmentation using a U-Net-based convolutional neural network. Particularly, the network is trained to discriminate pixels located at the borders between cells. The edge probability map outputted by the network is next binarized and skeletonized in order to obtain one-pixel wide edges. The proposed solution was tested on a dataset consisting of 30 corneal endothelial images presenting cells of different sizes, achieving an AUROC level of 0.92. The resulting DICE is on average equal to 0.86, which is a good result, regarding the thickness of the compared edges. The corresponding mean absolute percentage error of cell number is at the level of 4.5% which confirms the high accuracy of the proposed approach. The resulting cell edges are well aligned to the ground truths and require a limited number of manual corrections. This also results in accurate values of the cell morphometric parameters. The corresponding errors range from 5.2% for endothelial cell density, through 6.2% for cell hexagonality to 11.93% for the coefficient of variation of the cell size. Copyright © 2018 Elsevier B.V. All rights reserved.

Consistent interactive segmentation of pulmonary ground glass nodules identified in CT studies

NASA Astrophysics Data System (ADS)

Zhang, Li; Fang, Ming; Naidich, David P.; Novak, Carol L.

2004-05-01

Ground glass nodules (GGNs) have proved especially problematic in lung cancer diagnosis, as despite frequently being malignant they characteristically have extremely slow rates of growth. This problem is further magnified by the small size of many of these lesions now being routinely detected following the introduction of multislice CT scanners capable of acquiring contiguous high resolution 1 to 1.25 mm sections throughout the thorax in a single breathhold period. Although segmentation of solid nodules can be used clinically to determine volume doubling times quantitatively, reliable methods for segmentation of pure ground glass nodules have yet to be introduced. Our purpose is to evaluate a newly developed computer-based segmentation method for rapid and reproducible measurements of pure ground glass nodules. 23 pure or mixed ground glass nodules were identified in a total of 8 patients by a radiologist and subsequently segmented by our computer-based method using Markov random field and shape analysis. The computer-based segmentation was initialized by a click point. Methodological consistency was assessed using the overlap ratio between 3 segmentations initialized by 3 different click points for each nodule. The 95% confidence interval on the mean of the overlap ratios proved to be [0.984, 0.998]. The computer-based method failed on two nodules that were difficult to segment even manually either due to especially low contrast or markedly irregular margins. While achieving consistent manual segmentation of ground glass nodules has proven problematic most often due to indistinct boundaries and interobserver variability, our proposed method introduces a powerful new tool for obtaining reproducible quantitative measurements of these lesions. It is our intention to further document the value of this approach with a still larger set of ground glass nodules.

Figure-ground segmentation can occur without attention.

PubMed

Kimchi, Ruth; Peterson, Mary A

2008-07-01

The question of whether or not figure-ground segmentation can occur without attention is unresolved. Early theorists assumed it can, but the evidence is scant and open to alternative interpretations. Recent research indicating that attention can influence figure-ground segmentation raises the question anew. We examined this issue by asking participants to perform a demanding change-detection task on a small matrix presented on a task-irrelevant scene of alternating regions organized into figures and grounds by convexity. Independently of any change in the matrix, the figure-ground organization of the scene changed or remained the same. Changes in scene organization produced congruency effects on target-change judgments, even though, when probed with surprise questions, participants could report neither the figure-ground status of the region on which the matrix appeared nor any change in that status. When attending to the scene, participants reported figure-ground status and changes to it highly accurately. These results clearly demonstrate that figure-ground segmentation can occur without focal attention.

Implementation of the MSAT network in Canada

NASA Astrophysics Data System (ADS)

Roscoe, Orest S.

1991-10-01

MSAT will be launched into geostationary orbit at 106.5 degrees west longitude. It will have an aggregate EIRP in excess of 57 dBw, making it the highest powered mobile satellite launched or planned to date. The MSAT ground segment will comprise hundreds of thousands of mobile terminals, as well as numerous feederlink earth stations. This requires a large scale network control system which is unprecedented in a satellite environment. The network control system must support circuit-switched voice and data services and packet-switched data services. In addition to assignment of capacity on demand, the control system must be able to support a variety of service features required by customers, as well as record information for billing. It must operate in a multi-beam, multi-satellite environment as the system grows.

The July 12, 1993, Hokkaido-Nansei-Oki, Japan, earthquake: Coseismic slip pattern from strong-motion and teleseismic recordings

USGS Publications Warehouse

Mendoza, C.; Fukuyama, E.

1996-01-01

We employ a finite fault inversion scheme to infer the distribution of coseismic slip for the July 12, 1993, Hokkaido-Nansei-Oki earthquake using strong ground motions recorded by the Japan Meteorological Agency within 400 km of the epicenter and vertical P waveforms recorded by the Global Digital Seismograph Network at teleseismic distances. The assumed fault geometry is based on the location of the aftershock zone and comprises two fault segments with different orientations: a northern segment striking at N20??E with a 30?? dip to the west and a southern segment with a N20??W strike. For the southern segment we use both westerly and easterly dip directions to test thrust orientations previously proposed for this portion of the fault. The variance reduction is greater using a shallow west dipping segment, suggesting that the direction of dip did not change as the rupture propagated south from the hypocenter. This indicates that the earthquake resulted from the shallow underthrusting of Hokkaido beneath the Sea of Japan. Static vertical movements predicted by the corresponding distribution of fault slip are consistent with the general pattern of surface deformation observed following the earthquake. Fault rupture in the northern segment accounts for about 60% of the total P wave seismic moment of 3.4 ?? 1020 N m and includes a large circular slip zone (4-m peak) near the earthquake hypocenter at depths between 10 and 25 km. Slip in the southern segment is also predominantly shallower than 25 km, but the maximum coseismic displacements (2.0-2.5 m) are observed at a depth of about 5 km. This significant shallow slip in the southern portion of the rupture zone may have been responsible for the large tsunami that devastated the small offshore island of Okushiri. Localized shallow faulting near the island, however, may require a steep westerly dip to reconcile the measured values of ground subsidence.

Automated Detection of Selective Logging in Amazon Forests Using Airborne Lidar Data and Pattern Recognition Algorithms

NASA Astrophysics Data System (ADS)

Keller, M. M.; d'Oliveira, M. N.; Takemura, C. M.; Vitoria, D.; Araujo, L. S.; Morton, D. C.

2012-12-01

Selective logging, the removal of several valuable timber trees per hectare, is an important land use in the Brazilian Amazon and may degrade forests through long term changes in structure, loss of forest carbon and species diversity. Similar to deforestation, the annual area affected by selected logging has declined significantly in the past decade. Nonetheless, this land use affects several thousand km2 per year in Brazil. We studied a 1000 ha area of the Antimary State Forest (FEA) in the State of Acre, Brazil (9.304 ○S, 68.281 ○W) that has a basal area of 22.5 m2 ha-1 and an above-ground biomass of 231 Mg ha-1. Logging intensity was low, approximately 10 to 15 m3 ha-1. We collected small-footprint airborne lidar data using an Optech ALTM 3100EA over the study area once each in 2010 and 2011. The study area contained both recent and older logging that used both conventional and technologically advanced logging techniques. Lidar return density averaged over 20 m-2 for both collection periods with estimated horizontal and vertical precision of 0.30 and 0.15 m. A relative density model comparing returns from 0 to 1 m elevation to returns in 1-5 m elevation range revealed the pattern of roads and skid trails. These patterns were confirmed by ground-based GPS survey. A GIS model of the road and skid network was built using lidar and ground data. We tested and compared two pattern recognition approaches used to automate logging detection. Both segmentation using commercial eCognition segmentation and a Frangi filter algorithm identified the road and skid trail network compared to the GIS model. We report on the effectiveness of these two techniques.

File-Based Operations and CFDP On-Board Implementation

NASA Astrophysics Data System (ADS)

Herrera Alzu, Ignacio; Peran Mazon, Francisco; Gonzalo Palomo, Alfonso

2014-08-01

Since several years ago, there is an increasing interest among the space agencies, ESA in particular, in deploying File-based Operations (FbO) for Space missions. This aims at simplifying, from the Ground Segment's perspective, the access to the Space Segment and ultimately the overall operations. This is particularly important for deep Space missions, where the Ground-Space interaction can become too complex to handle just with traditional packet-based services. The use of a robust protocol for transferring files between Ground and Space is a key for the FbO approach, and the CCSDS File Delivery Protocol (CFDP) is nowadays the main candidate for doing this job. Both Ground and Space Segments need to be adapted for FbO, being the Ground Segment naturally closer to this concept. This paper focusses on the Space Segment. The main implications related to FbO/CFDP, the possible on-board implementations and the foreseen operations are described. The case of Euclid, the first ESA mission to be file-based operated with CFDP, is also analysed.

Universal partitioning of the hierarchical fold network of 50-residue segments in proteins

PubMed Central

Ito, Jun-ichi; Sonobe, Yuki; Ikeda, Kazuyoshi; Tomii, Kentaro; Higo, Junichi

2009-01-01

Background Several studies have demonstrated that protein fold space is structured hierarchically and that power-law statistics are satisfied in relation between the numbers of protein families and protein folds (or superfamilies). We examined the internal structure and statistics in the fold space of 50 amino-acid residue segments taken from various protein folds. We used inter-residue contact patterns to measure the tertiary structural similarity among segments. Using this similarity measure, the segments were classified into a number (Kc) of clusters. We examined various Kc values for the clustering. The special resolution to differentiate the segment tertiary structures increases with increasing Kc. Furthermore, we constructed networks by linking structurally similar clusters. Results The network was partitioned persistently into four regions for Kc ≥ 1000. This main partitioning is consistent with results of earlier studies, where similar partitioning was reported in classifying protein domain structures. Furthermore, the network was partitioned naturally into several dozens of sub-networks (i.e., communities). Therefore, intra-sub-network clusters were mutually connected with numerous links, although inter-sub-network ones were rarely done with few links. For Kc ≥ 1000, the major sub-networks were about 40; the contents of the major sub-networks were conserved. This sub-partitioning is a novel finding, suggesting that the network is structured hierarchically: Segments construct a cluster, clusters form a sub-network, and sub-networks constitute a region. Additionally, the network was characterized by non-power-law statistics, which is also a novel finding. Conclusion Main findings are: (1) The universe of 50 residue segments found here was characterized by non-power-law statistics. Therefore, the universe differs from those ever reported for the protein domains. (2) The 50-residue segments were partitioned persistently and universally into some dozens (ca. 40) of major sub-networks, irrespective of the number of clusters. (3) These major sub-networks encompassed 90% of all segments. Consequently, the protein tertiary structure is constructed using the dozens of elements (sub-networks). PMID:19454039

Low-Grade Glioma Segmentation Based on CNN with Fully Connected CRF

PubMed Central

Li, Zeju; Shi, Zhifeng; Guo, Yi; Chen, Liang; Mao, Ying

2017-01-01

This work proposed a novel automatic three-dimensional (3D) magnetic resonance imaging (MRI) segmentation method which would be widely used in the clinical diagnosis of the most common and aggressive brain tumor, namely, glioma. The method combined a multipathway convolutional neural network (CNN) and fully connected conditional random field (CRF). Firstly, 3D information was introduced into the CNN which makes more accurate recognition of glioma with low contrast. Then, fully connected CRF was added as a postprocessing step which purposed more delicate delineation of glioma boundary. The method was applied to T2flair MRI images of 160 low-grade glioma patients. With 59 cases of data training and manual segmentation as the ground truth, the Dice similarity coefficient (DSC) of our method was 0.85 for the test set of 101 MRI images. The results of our method were better than those of another state-of-the-art CNN method, which gained the DSC of 0.76 for the same dataset. It proved that our method could produce better results for the segmentation of low-grade gliomas. PMID:29065666

Low-Grade Glioma Segmentation Based on CNN with Fully Connected CRF.

PubMed

Li, Zeju; Wang, Yuanyuan; Yu, Jinhua; Shi, Zhifeng; Guo, Yi; Chen, Liang; Mao, Ying

2017-01-01

This work proposed a novel automatic three-dimensional (3D) magnetic resonance imaging (MRI) segmentation method which would be widely used in the clinical diagnosis of the most common and aggressive brain tumor, namely, glioma. The method combined a multipathway convolutional neural network (CNN) and fully connected conditional random field (CRF). Firstly, 3D information was introduced into the CNN which makes more accurate recognition of glioma with low contrast. Then, fully connected CRF was added as a postprocessing step which purposed more delicate delineation of glioma boundary. The method was applied to T2flair MRI images of 160 low-grade glioma patients. With 59 cases of data training and manual segmentation as the ground truth, the Dice similarity coefficient (DSC) of our method was 0.85 for the test set of 101 MRI images. The results of our method were better than those of another state-of-the-art CNN method, which gained the DSC of 0.76 for the same dataset. It proved that our method could produce better results for the segmentation of low-grade gliomas.

Automatic segmentation of fluorescence lifetime microscopy images of cells using multiresolution community detection--a first study.

PubMed

Hu, D; Sarder, P; Ronhovde, P; Orthaus, S; Achilefu, S; Nussinov, Z

2014-01-01

Inspired by a multiresolution community detection based network segmentation method, we suggest an automatic method for segmenting fluorescence lifetime (FLT) imaging microscopy (FLIM) images of cells in a first pilot investigation on two selected images. The image processing problem is framed as identifying segments with respective average FLTs against the background in FLIM images. The proposed method segments a FLIM image for a given resolution of the network defined using image pixels as the nodes and similarity between the FLTs of the pixels as the edges. In the resulting segmentation, low network resolution leads to larger segments, and high network resolution leads to smaller segments. Furthermore, using the proposed method, the mean-square error in estimating the FLT segments in a FLIM image was found to consistently decrease with increasing resolution of the corresponding network. The multiresolution community detection method appeared to perform better than a popular spectral clustering-based method in performing FLIM image segmentation. At high resolution, the spectral segmentation method introduced noisy segments in its output, and it was unable to achieve a consistent decrease in mean-square error with increasing resolution. © 2013 The Authors Journal of Microscopy © 2013 Royal Microscopical Society.

Automatic Segmentation of Fluorescence Lifetime Microscopy Images of Cells Using Multi-Resolution Community Detection -A First Study

PubMed Central

Hu, Dandan; Sarder, Pinaki; Ronhovde, Peter; Orthaus, Sandra; Achilefu, Samuel; Nussinov, Zohar

2014-01-01

Inspired by a multi-resolution community detection (MCD) based network segmentation method, we suggest an automatic method for segmenting fluorescence lifetime (FLT) imaging microscopy (FLIM) images of cells in a first pilot investigation on two selected images. The image processing problem is framed as identifying segments with respective average FLTs against the background in FLIM images. The proposed method segments a FLIM image for a given resolution of the network defined using image pixels as the nodes and similarity between the FLTs of the pixels as the edges. In the resulting segmentation, low network resolution leads to larger segments, and high network resolution leads to smaller segments. Further, using the proposed method, the mean-square error (MSE) in estimating the FLT segments in a FLIM image was found to consistently decrease with increasing resolution of the corresponding network. The MCD method appeared to perform better than a popular spectral clustering based method in performing FLIM image segmentation. At high resolution, the spectral segmentation method introduced noisy segments in its output, and it was unable to achieve a consistent decrease in MSE with increasing resolution. PMID:24251410

Groundwater-surfacewater relationships in the Bonaparte Creek basin, Okanogan County, Washington, 1979-1980

USGS Publications Warehouse

Packard, F.A.; Sumioka, S.S.; Whiteman, K.J.

1983-01-01

Ground water-surface-water relationships were studied in five morphological segments in the Bonaparte Creek basin, Washington during 1979 and 1980. In one segment, kettle lakes were found to be closely associated with the ground-water system. In the other four segments, a close relationship was found between streamflow and ground water. It was concluded that additional ground-water development would adversely affect lake levels and streamflow, thereby reducing surface-water resources already closed to further appropriation. The ground-water divide between the Bonaparte and Sanpoil basins was 6 miles southeast of where it was estimated to be. (USGS)

Intelligent multi-spectral IR image segmentation

NASA Astrophysics Data System (ADS)

Lu, Thomas; Luong, Andrew; Heim, Stephen; Patel, Maharshi; Chen, Kang; Chao, Tien-Hsin; Chow, Edward; Torres, Gilbert

2017-05-01

This article presents a neural network based multi-spectral image segmentation method. A neural network is trained on the selected features of both the objects and background in the longwave (LW) Infrared (IR) images. Multiple iterations of training are performed until the accuracy of the segmentation reaches satisfactory level. The segmentation boundary of the LW image is used to segment the midwave (MW) and shortwave (SW) IR images. A second neural network detects the local discontinuities and refines the accuracy of the local boundaries. This article compares the neural network based segmentation method to the Wavelet-threshold and Grab-Cut methods. Test results have shown increased accuracy and robustness of this segmentation scheme for multi-spectral IR images.

Ground Water Atlas of the United States: Segment 1, California, Nevada

USGS Publications Warehouse

Planert, Michael; Williams, John S.

1995-01-01

California and Nevada compose Segment 1 of the Ground Water Atlas of the United States. Segment 1 is a region of pronounced physiographic and climatic contrasts. From the Cascade Mountains and the Sierra Nevada of northern California, where precipitation is abundant, to the Great Basin in Nevada and the deserts of southern California, which have the most arid environments in the United States, few regions exhibit such a diversity of topography or environment. Since the discovery of gold in the mid-1800's, California has experienced a population, industrial, and agricultural boom unrivaled by that of any other State. Water needs in California are very large, and the State leads the United States in agricultural and municipal water use. The demand for water exceeds the natural water supply in many agricultural and nearly all urban areas. As a result, water is impounded by reservoirs in areas of surplus and transported to areas of scarcity by an extensive network of aqueducts. Unlike California, which has a relative abundance of water, development in Nevada has been limited by a scarcity of recoverable freshwater. The Truckee, the Carson, the Walker, the Humboldt, and the Colorado Rivers are the only perennial streams of significance in the State. The individual basin-fill aquifers, which together compose the largest known ground-water reserves, receive little annual recharge and are easily depleted. Nevada is sparsely populated, except for the Las Vegas, the Reno-Sparks, and the Carson City areas, which rely heavily on imported water for public supplies. Although important to the economy of Nevada, agriculture has not been developed to the same degree as in California due, in large part, to a scarcity of water. Some additional ground-water development might be possible in Nevada through prudent management of the basin-fill aquifers and increased utilization of ground water in the little-developed carbonate-rock aquifers that underlie the eastern one-half of the State. The potential problem of withdrawals in excess of natural recharge, however, will require careful management of ground-water withdrawals.

Comparison of the Data Products from Different Instrument Types with Application to Induced Seismic Monitoring Framework

NASA Astrophysics Data System (ADS)

Yenier, E.; Baturan, D.; Karimi, S.; Moores, A. O.; Spriggs, N.

2016-12-01

Earthquakes may be induced by man-made activity in the vicinity of critically-stressed fault segments. A number of earthquakes characterized as induced with magnitudes M>3 were recorded in British Columbia, Alberta, Oklahoma and Ohio, since 2013. In response to growing induced seismicity in North America, many jurisdictions have mandated near real-time seismic monitoring around operation sites. The data products from monitoring networks are used as drivers of operational traffic light systems designed to mitigate risks associated with induced seismicity. Most traffic light protocols developed to date use staged thresholds of earthquake magnitudes. Additionally, ground motions, which are used to estimate the impact of earthquakes and specify seismic hazard, have been proposed as an enhancement to the existing protocols. There are several challenges and options to consider at the time of planning and designing a monitoring network, the most important of which is the choice of ground motion sensing technology. In order to accurately estimate event source parameters and ground motions, monitoring instruments have to record and image the low-frequency plateau and the corner frequency of the anticipated event spectrum. A flat response over a wide frequency range with a wide dynamic range is desired for a maximum benefit from ground motion products. This study evaluates the performance of three types of instruments in terms of their suitability for induced seismic monitoring (ISM): broadband seismometers, accelerometers and geophones. Each instrument type is assessed in terms of self-noise, frequency response and clip level using instrument specifications and real-world ISM application data. The impact of each sensing technology on key ISM network performance criteria, event magnitude estimations and ground motion measurements are examined.

Adaptive attenuation of aliased ground roll using the shearlet transform

NASA Astrophysics Data System (ADS)

Hosseini, Seyed Abolfazl; Javaherian, Abdolrahim; Hassani, Hossien; Torabi, Siyavash; Sadri, Maryam

2015-01-01

Attenuation of ground roll is an essential step in seismic data processing. Spatial aliasing of the ground roll may cause the overlap of the ground roll with reflections in the f-k domain. The shearlet transform is a directional and multidimensional transform that separates the events with different dips and generates subimages in different scales and directions. In this study, the shearlet transform was used adaptively to attenuate aliased and non-aliased ground roll. After defining a filtering zone, an input shot record is divided into segments. Each segment overlaps adjacent segments. To apply the shearlet transform on each segment, the subimages containing aliased and non-aliased ground roll, the locations of these events on each subimage are selected adaptively. Based on these locations, mute is applied on the selected subimages. The filtered segments are merged together, using the Hanning function, after applying the inverse shearlet transform. This adaptive process of ground roll attenuation was tested on synthetic data, and field shot records from west of Iran. Analysis of the results using the f-k spectra revealed that the non-aliased and most of the aliased ground roll were attenuated using the proposed adaptive attenuation procedure. Also, we applied this method on shot records of a 2D land survey, and the data sets before and after ground roll attenuation were stacked and compared. The stacked section after ground roll attenuation contained less linear ground roll noise and more continuous reflections in comparison with the stacked section before the ground roll attenuation. The proposed method has some drawbacks such as more run time in comparison with traditional methods such as f-k filtering and reduced performance when the dip and frequency content of aliased ground roll are the same as those of the reflections.

Automated mammographic breast density estimation using a fully convolutional network.

PubMed

Lee, Juhun; Nishikawa, Robert M

2018-03-01

The purpose of this study was to develop a fully automated algorithm for mammographic breast density estimation using deep learning. Our algorithm used a fully convolutional network, which is a deep learning framework for image segmentation, to segment both the breast and the dense fibroglandular areas on mammographic images. Using the segmented breast and dense areas, our algorithm computed the breast percent density (PD), which is the faction of dense area in a breast. Our dataset included full-field digital screening mammograms of 604 women, which included 1208 mediolateral oblique (MLO) and 1208 craniocaudal (CC) views. We allocated 455, 58, and 91 of 604 women and their exams into training, testing, and validation datasets, respectively. We established ground truth for the breast and the dense fibroglandular areas via manual segmentation and segmentation using a simple thresholding based on BI-RADS density assessments by radiologists, respectively. Using the mammograms and ground truth, we fine-tuned a pretrained deep learning network to train the network to segment both the breast and the fibroglandular areas. Using the validation dataset, we evaluated the performance of the proposed algorithm against radiologists' BI-RADS density assessments. Specifically, we conducted a correlation analysis between a BI-RADS density assessment of a given breast and its corresponding PD estimate by the proposed algorithm. In addition, we evaluated our algorithm in terms of its ability to classify the BI-RADS density using PD estimates, and its ability to provide consistent PD estimates for the left and the right breast and the MLO and CC views of the same women. To show the effectiveness of our algorithm, we compared the performance of our algorithm against a state of the art algorithm, laboratory for individualized breast radiodensity assessment (LIBRA). The PD estimated by our algorithm correlated well with BI-RADS density ratings by radiologists. Pearson's rho values of our algorithm for CC view, MLO view, and CC-MLO-averaged were 0.81, 0.79, and 0.85, respectively, while those of LIBRA were 0.58, 0.71, and 0.69, respectively. For CC view and CC-MLO averaged cases, the difference in rho values between the proposed algorithm and LIBRA showed statistical significance (P < 0.006). In addition, our algorithm provided reliable PD estimates for the left and the right breast (Pearson's ρ > 0.87) and for the MLO and CC views (Pearson's ρ = 0.76). However, LIBRA showed a lower Pearson's rho value (0.66) for both the left and right breasts for the CC view. In addition, our algorithm showed an excellent ability to separate each sub BI-RADS breast density class (statistically significant, p-values = 0.0001 or less); only one comparison pair, density 1 and density 2 in the CC view, was not statistically significant (P = 0.54). However, LIBRA failed to separate breasts in density 1 and 2 for both the CC and MLO views (P > 0.64). We have developed a new deep learning based algorithm for breast density segmentation and estimation. We showed that the proposed algorithm correlated well with BI-RADS density assessments by radiologists and outperformed an existing state of the art algorithm. © 2018 American Association of Physicists in Medicine.

Numerical Simulations for Distribution Characteristics of Internal Forces on Segments of Tunnel Linings

NASA Astrophysics Data System (ADS)

Li, Shouju; Shangguan, Zichang; Cao, Lijuan

A procedure based on FEM is proposed to simulate interaction between concrete segments of tunnel linings and soils. The beam element named as Beam 3 in ANSYS software was used to simulate segments. The ground loss induced from shield tunneling and segment installing processes is simulated in finite element analysis. The distributions of bending moment, axial force and shear force on segments were computed by FEM. The commutated internal forces on segments will be used to design reinforced bars on shield linings. Numerically simulated ground settlements agree with observed values.

Automatic extraction of road features in urban environments using dense ALS data

NASA Astrophysics Data System (ADS)

Soilán, Mario; Truong-Hong, Linh; Riveiro, Belén; Laefer, Debra

2018-02-01

This paper describes a methodology that automatically extracts semantic information from urban ALS data for urban parameterization and road network definition. First, building façades are segmented from the ground surface by combining knowledge-based information with both voxel and raster data. Next, heuristic rules and unsupervised learning are applied to the ground surface data to distinguish sidewalk and pavement points as a means for curb detection. Then radiometric information was employed for road marking extraction. Using high-density ALS data from Dublin, Ireland, this fully automatic workflow was able to generate a F-score close to 95% for pavement and sidewalk identification with a resolution of 20 cm and better than 80% for road marking detection.

Shearlet transform in aliased ground roll attenuation and its comparison with f-k filtering and curvelet transform

NASA Astrophysics Data System (ADS)

Abolfazl Hosseini, Seyed; Javaherian, Abdolrahim; Hassani, Hossien; Torabi, Siyavash; Sadri, Maryam

2015-06-01

Ground roll, which is a Rayleigh surface wave that exists in land seismic data, may mask reflections. Sometimes ground roll is spatially aliased. Attenuation of aliased ground roll is of importance in seismic data processing. Different methods have been developed to attenuate ground roll. The shearlet transform is a directional and multidimensional transform that generates subimages of an input image in different directions and scales. Events with different dips are separated in these subimages. In this study, the shearlet transform is used to attenuate the aliased ground roll. To do this, a shot record is divided into several segments, and the appropriate mute zone is defined for all segments. The shearlet transform is applied to each segment. The subimages related to the non-aliased and aliased ground roll are identified by plotting the energy distributions of subimages with visual checking. Then, muting filters are used on selected subimages. The inverse shearlet transform is applied to the filtered segment. This procedure is repeated for all segments. Finally, all filtered segments are merged using the Hanning window. This method of aliased ground roll attenuation was tested on a synthetic dataset and a field shot record from the west of Iran. The synthetic shot record included strong aliased ground roll, whereas the field shot record did not. To produce the strong aliased ground roll on the field shot record, the data were resampled in the offset direction from 30 to 60 m. To show the performance of the shearlet transform in attenuating the aliased ground roll, we compared the shearlet transform with the f-k filtering and curvelet transform. We showed that the performance of the shearlet transform in the aliased ground roll attenuation is better than that of the f-k filtering and curvelet transform in both the synthetic and field shot records. However, when the dip and frequency content of the aliased ground roll are the same as the reflections, ability of the shearlet transform is limited in attenuating the aliased ground roll.

A NDVI assisted remote sensing image adaptive scale segmentation method

NASA Astrophysics Data System (ADS)

Zhang, Hong; Shen, Jinxiang; Ma, Yanmei

2018-03-01

Multiscale segmentation of images can effectively form boundaries of different objects with different scales. However, for the remote sensing image which widely coverage with complicated ground objects, the number of suitable segmentation scales, and each of the scale size is still difficult to be accurately determined, which severely restricts the rapid information extraction of the remote sensing image. A great deal of experiments showed that the normalized difference vegetation index (NDVI) can effectively express the spectral characteristics of a variety of ground objects in remote sensing images. This paper presents a method using NDVI assisted adaptive segmentation of remote sensing images, which segment the local area by using NDVI similarity threshold to iteratively select segmentation scales. According to the different regions which consist of different targets, different segmentation scale boundaries could be created. The experimental results showed that the adaptive segmentation method based on NDVI can effectively create the objects boundaries for different ground objects of remote sensing images.

Pulse Coupled Neural Networks for the Segmentation of Magnetic Resonance Brain Images.

DTIC Science & Technology

1996-12-01

PULSE COUPLED NEURAL NETWORKS FOR THE SEGMENTATION OF MAGNETIC RESONANCE BRAIN IMAGES THESIS Shane Lee Abrahamson First Lieutenant, USAF AFIT/GCS/ENG...COUPLED NEURAL NETWORKS FOR THE SEGMENTATION OF MAGNETIC RESONANCE BRAIN IMAGES THESIS Shane Lee Abrahamson First Lieutenant, USAF AFIT/GCS/ENG/96D-01...research develops an automated method for segmenting Magnetic Resonance (MR) brain images based on Pulse Coupled Neural Networks (PCNN). MR brain image

Synchronization and desynchronization in a network of locally coupled Wilson-Cowan oscillators.

PubMed

Campbell, S; Wang, D

1996-01-01

A network of Wilson-Cowan (WC) oscillators is constructed, and its emergent properties of synchronization and desynchronization are investigated by both computer simulation and formal analysis. The network is a 2D matrix, where each oscillator is coupled only to its neighbors. We show analytically that a chain of locally coupled oscillators (the piecewise linear approximation to the WC oscillator) synchronizes, and we present a technique to rapidly entrain finite numbers of oscillators. The coupling strengths change on a fast time scale based on a Hebbian rule. A global separator is introduced which receives input from and sends feedback to each oscillator in the matrix. The global separator is used to desynchronize different oscillator groups. Unlike many other models, the properties of this network emerge from local connections that preserve spatial relationships among components and are critical for encoding Gestalt principles of feature grouping. The ability to synchronize and desynchronize oscillator groups within this network offers a promising approach for pattern segmentation and figure/ground segregation based on oscillatory correlation.

An Algorithm for Obtaining the Distribution of 1-Meter Lightning Channel Segment Altitudes for Application in Lightning NOx Production Estimation

NASA Technical Reports Server (NTRS)

Peterson, Harold; Koshak, William J.

2009-01-01

An algorithm has been developed to estimate the altitude distribution of one-meter lightning channel segments. The algorithm is required as part of a broader objective that involves improving the lightning NOx emission inventories of both regional air quality and global chemistry/climate models. The algorithm was tested and applied to VHF signals detected by the North Alabama Lightning Mapping Array (NALMA). The accuracy of the algorithm was characterized by comparing algorithm output to the plots of individual discharges whose lengths were computed by hand; VHF source amplitude thresholding and smoothing were applied to optimize results. Several thousands of lightning flashes within 120 km of the NALMA network centroid were gathered from all four seasons, and were analyzed by the algorithm. The mean, standard deviation, and median statistics were obtained for all the flashes, the ground flashes, and the cloud flashes. One-meter channel segment altitude distributions were also obtained for the different seasons.

Progress on ten-meter optical receiver telescope

NASA Technical Reports Server (NTRS)

Shaik, Kamran

1992-01-01

A ten-meter hexagonally segmented Cassegrain optical telescope is being considered at the Jet Propulsion Laboratory for use as a research and development facility for optical communications technology. The goal of the study is to demonstrate technology which can eventually be used to develop a network of such telescopes to continuously track and communicate with the spacecraft. Hence, the technology has to be economical enough to allow replication for a ground or space based network. As we need to collect signal photons only, the telescope cost can be substantially reduced by accepting lower image quality. An important design consideration for the telescope is its ability to look very close to the sun. The telescope for optical communications must function during the daytime. Indeed, for some planetary missions it may be necessary that the system be capable of looking within a few degrees of the sun. To enable this, a unique sunshade consisting of hexagonal tubes in precise alignment with the mirror segments has been proposed which will also serve as the support for the secondary. Recent progress on the design and analysis of such an optical reception station is discussed here.

Pixel-Level Deep Segmentation: Artificial Intelligence Quantifies Muscle on Computed Tomography for Body Morphometric Analysis.

PubMed

Lee, Hyunkwang; Troschel, Fabian M; Tajmir, Shahein; Fuchs, Georg; Mario, Julia; Fintelmann, Florian J; Do, Synho

2017-08-01

Pretreatment risk stratification is key for personalized medicine. While many physicians rely on an "eyeball test" to assess whether patients will tolerate major surgery or chemotherapy, "eyeballing" is inherently subjective and difficult to quantify. The concept of morphometric age derived from cross-sectional imaging has been found to correlate well with outcomes such as length of stay, morbidity, and mortality. However, the determination of the morphometric age is time intensive and requires highly trained experts. In this study, we propose a fully automated deep learning system for the segmentation of skeletal muscle cross-sectional area (CSA) on an axial computed tomography image taken at the third lumbar vertebra. We utilized a fully automated deep segmentation model derived from an extended implementation of a fully convolutional network with weight initialization of an ImageNet pre-trained model, followed by post processing to eliminate intramuscular fat for a more accurate analysis. This experiment was conducted by varying window level (WL), window width (WW), and bit resolutions in order to better understand the effects of the parameters on the model performance. Our best model, fine-tuned on 250 training images and ground truth labels, achieves 0.93 ± 0.02 Dice similarity coefficient (DSC) and 3.68 ± 2.29% difference between predicted and ground truth muscle CSA on 150 held-out test cases. Ultimately, the fully automated segmentation system can be embedded into the clinical environment to accelerate the quantification of muscle and expanded to volume analysis of 3D datasets.

Spring contributions to water quality and nitrate loads in the Suwannee River during base flow in July 1995

USGS Publications Warehouse

Pittman, J.R.; Hatzell, H.H.; Oaksford, E.T.

1997-01-01

The Suwannee River flows through an area of north-central Florida where ground water has elevated nitrate concentrations. A study was conducted to determine how springs and other ground-water inflow affect the quantity and quality of water in the Suwannee River. The study was done on a 33-mile (mi) reach of the lower Suwannee River from just downstream of Dowling Park, Fla., to Branford, Fla. Water samples for nitrate concentrations (dissolved nitrite plus nitrate as nitrogen) and discharge data were collected at 11 springs and 3 river sites during the 3-day period in July 1995 during base flow in the river. In the study reach, all inflow to the river is derived from ground water. Measured springs and other ground-water inflow, such as unmeasured springs and upward diffuse leakage through the riverbed, increased the river discharge 47 percent over the 33-mi reach. The 11 measured springs contributed 41 percent of the increased discharge and other ground-water inflow contributed the remaining 59 percent. River nitrate loads increased downstream from 2,300 to 6,000 kilograms per day (kg/d), an increase of 160 percent in the 33-mi study reach. Measured springs contributed 46 percent of this increase and other ground-water inflow contributed the remaining 54 percent. The study reach was divided at Luraville, Fla., into an 11-mi upper segment and a 22-mi lower segment to determine whether the ground-water inflows and nitrate concentrations were uniform throughout the entire study reach (fig. 1). The two segments were dissimilar. The amount of water added to the river by measured springs more than tripled from the upper to the lower segment. Even though the median nitrate concentration for the three springs in the upper segment (1.7 milligrams per liter (mg/L)) was similar to the median for the eight springs in the lower segment (1.8 mg/L), nitrate concentrations in the river almost doubled from 0.46 to 0.83 mg/L in the lower segment. Only 11 percent of the increase in nitrate load for the study reach occurred in the upper segment; the remaining 89 percent occurred in the lower segment. Measured springs were the major source of nitrate load in the upper reach and other ground-water inflow was the major source in the lower segment. Differences in nitrate loads between the upper and lower river segments are probably controlled by such factors as differences in the magnitude of the spring discharges, the size and location of spring basins, and the hydrologic characteristics of ground water in the study area.

Performance evaluation of automated segmentation software on optical coherence tomography volume data

PubMed Central

Tian, Jing; Varga, Boglarka; Tatrai, Erika; Fanni, Palya; Somfai, Gabor Mark; Smiddy, William E.

2016-01-01

Over the past two decades a significant number of OCT segmentation approaches have been proposed in the literature. Each methodology has been conceived for and/or evaluated using specific datasets that do not reflect the complexities of the majority of widely available retinal features observed in clinical settings. In addition, there does not exist an appropriate OCT dataset with ground truth that reflects the realities of everyday retinal features observed in clinical settings. While the need for unbiased performance evaluation of automated segmentation algorithms is obvious, the validation process of segmentation algorithms have been usually performed by comparing with manual labelings from each study and there has been a lack of common ground truth. Therefore, a performance comparison of different algorithms using the same ground truth has never been performed. This paper reviews research-oriented tools for automated segmentation of the retinal tissue on OCT images. It also evaluates and compares the performance of these software tools with a common ground truth. PMID:27159849

Oscillatory network with self-organized dynamical connections for synchronization-based image segmentation.

PubMed

Kuzmina, Margarita; Manykin, Eduard; Surina, Irina

2004-01-01

An oscillatory network of columnar architecture located in 3D spatial lattice was recently designed by the authors as oscillatory model of the brain visual cortex. Single network oscillator is a relaxational neural oscillator with internal dynamics tunable by visual image characteristics - local brightness and elementary bar orientation. It is able to demonstrate either activity state (stable undamped oscillations) or "silence" (quickly damped oscillations). Self-organized nonlocal dynamical connections of oscillators depend on oscillator activity levels and orientations of cortical receptive fields. Network performance consists in transfer into a state of clusterized synchronization. At current stage grey-level image segmentation tasks are carried out by 2D oscillatory network, obtained as a limit version of the source model. Due to supplemented network coupling strength control the 2D reduced network provides synchronization-based image segmentation. New results on segmentation of brightness and texture images presented in the paper demonstrate accurate network performance and informative visualization of segmentation results, inherent in the model.

Telesat Canada's mobile satellite system

NASA Astrophysics Data System (ADS)

Bertenyi, E.; Wachira, M.

1987-10-01

Telesat Canada plans to begin instituting mobile satellite ('Msat') services in the early 1990s, in order to permit voice and data communications between land vehicles, aircraft, and ships throughout the remote northern regions and the 200-mile offshore regions of Canada and any other point on Canadian territory. An account is presently given of Msat's overall configuration and projected capacity, together with the design features and performance capabilities of the constituent ground, space, and network control segments. Key technology items are the spacecraft high power RF amplifier and its large deployable antenna.

Corpus callosum segmentation using deep neural networks with prior information from multi-atlas images

NASA Astrophysics Data System (ADS)

Park, Gilsoon; Hong, Jinwoo; Lee, Jong-Min

2018-03-01

In human brain, Corpus Callosum (CC) is the largest white matter structure, connecting between right and left hemispheres. Structural features such as shape and size of CC in midsagittal plane are of great significance for analyzing various neurological diseases, for example Alzheimer's disease, autism and epilepsy. For quantitative and qualitative studies of CC in brain MR images, robust segmentation of CC is important. In this paper, we present a novel method for CC segmentation. Our approach is based on deep neural networks and the prior information generated from multi-atlas images. Deep neural networks have recently shown good performance in various image processing field. Convolutional neural networks (CNN) have shown outstanding performance for classification and segmentation in medical image fields. We used convolutional neural networks for CC segmentation. Multi-atlas based segmentation model have been widely used in medical image segmentation because atlas has powerful information about the target structure we want to segment, consisting of MR images and corresponding manual segmentation of the target structure. We combined the prior information, such as location and intensity distribution of target structure (i.e. CC), made from multi-atlas images in CNN training process for more improving training. The CNN with prior information showed better segmentation performance than without.

Efficient Power Network Analysis with Modeling of Inductive Effects

NASA Astrophysics Data System (ADS)

Zeng, Shan; Yu, Wenjian; Hong, Xianlong; Cheng, Chung-Kuan

In this paper, an efficient method is proposed to accurately analyze large-scale power/ground (P/G) networks, where inductive parasitics are modeled with the partial reluctance. The method is based on frequency-domain circuit analysis and the technique of vector fitting [14], and obtains the time-domain voltage response at given P/G nodes. The frequency-domain circuit equation including partial reluctances is derived, and then solved with the GMRES algorithm with rescaling, preconditioning and recycling techniques. With the merit of sparsified reluctance matrix and iterative solving techniques for the frequency-domain circuit equations, the proposed method is able to handle large-scale P/G networks with complete inductive modeling. Numerical results show that the proposed method is orders of magnitude faster than HSPICE, several times faster than INDUCTWISE [4], and capable of handling the inductive P/G structures with more than 100, 000 wire segments.

Analysis of NASA communications (Nascom) II network protocols and performance

NASA Technical Reports Server (NTRS)

Omidyar, Guy C.; Butler, Thomas E.

1991-01-01

The NASA Communications (Nascom) Division of the Mission Operations and Data Systems Directorate is to undertake a major initiative to develop the Nascom II (NII) network to achieve its long-range service objectives for operational data transport to support the Space Station Freedom Program, the Earth Observing System, and other projects. NII is the Nascom ground communications network being developed to accommodate the operational traffic of the mid-1990s and beyond. The authors describe various baseline protocol architectures based on current and evolving technologies. They address the internetworking issues suggested for reliable transfer of data over heterogeneous segments. They also describe the NII architecture, topology, system components, and services. A comparative evaluation of the current and evolving technologies was made, and suggestions for further study are described. It is shown that the direction of the NII configuration and the subsystem component design will clearly depend on the advances made in the area of broadband integrated services.

The European project Merlin on multi-gigabit, energy-efficient, ruggedized lightwave engines for advanced on-board digital processors

NASA Astrophysics Data System (ADS)

Stampoulidis, L.; Kehayas, E.; Karppinen, M.; Tanskanen, A.; Heikkinen, V.; Westbergh, P.; Gustavsson, J.; Larsson, A.; Grüner-Nielsen, L.; Sotom, M.; Venet, N.; Ko, M.; Micusik, D.; Kissinger, D.; Ulusoy, A. C.; King, R.; Safaisini, R.

2017-11-01

Modern broadband communication networks rely on satellites to complement the terrestrial telecommunication infrastructure. Satellites accommodate global reach and enable world-wide direct broadcasting by facilitating wide access to the backbone network from remote sites or areas where the installation of ground segment infrastructure is not economically viable. At the same time the new broadband applications increase the bandwidth demands in every part of the network - and satellites are no exception. Modern telecom satellites incorporate On-Board Processors (OBP) having analogue-to-digital (ADC) and digital-to-analogue converters (DAC) at their inputs/outputs and making use of digital processing to handle hundreds of signals; as the amount of information exchanged increases, so do the physical size, mass and power consumption of the interconnects required to transfer massive amounts of data through bulk electric wires.

Image feature based GPS trace filtering for road network generation and road segmentation

DOE PAGES

Yuan, Jiangye; Cheriyadat, Anil M.

2015-10-19

We propose a new method to infer road networks from GPS trace data and accurately segment road regions in high-resolution aerial images. Unlike previous efforts that rely on GPS traces alone, we exploit image features to infer road networks from noisy trace data. The inferred road network is used to guide road segmentation. We show that the number of image segments spanned by the traces and the trace orientation validated with image features are important attributes for identifying GPS traces on road regions. Based on filtered traces , we construct road networks and integrate them with image features to segmentmore » road regions. Lastly, our experiments show that the proposed method produces more accurate road networks than the leading method that uses GPS traces alone, and also achieves high accuracy in segmenting road regions even with very noisy GPS data.« less

Image feature based GPS trace filtering for road network generation and road segmentation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yuan, Jiangye; Cheriyadat, Anil M.

We propose a new method to infer road networks from GPS trace data and accurately segment road regions in high-resolution aerial images. Unlike previous efforts that rely on GPS traces alone, we exploit image features to infer road networks from noisy trace data. The inferred road network is used to guide road segmentation. We show that the number of image segments spanned by the traces and the trace orientation validated with image features are important attributes for identifying GPS traces on road regions. Based on filtered traces , we construct road networks and integrate them with image features to segmentmore » road regions. Lastly, our experiments show that the proposed method produces more accurate road networks than the leading method that uses GPS traces alone, and also achieves high accuracy in segmenting road regions even with very noisy GPS data.« less

Software performance in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas.

PubMed

Cohen, Julien G; Goo, Jin Mo; Yoo, Roh-Eul; Park, Chang Min; Lee, Chang Hyun; van Ginneken, Bram; Chung, Doo Hyun; Kim, Young Tae

2016-12-01

To evaluate the performance of software in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas. Seventy-three pulmonary adenocarcinomas manifesting as subsolid nodules were included. Two radiologists measured the maximal axial diameter of the ground-glass components on lung windows and that of the solid components on lung and mediastinal windows. Nodules were segmented using software by applying five (-850 HU to -650 HU) and nine (-130 HU to -500 HU) attenuation thresholds. We compared the manual and software measurements of ground-glass and solid components with pathology measurements of tumour and invasive components. Segmentation of ground-glass components at a threshold of -750 HU yielded mean differences of +0.06 mm (p = 0.83, 95 % limits of agreement, 4.51 to 4.67) and -2.32 mm (p < 0.001, -8.27 to 3.63) when compared with pathology and manual measurements, respectively. For solid components, mean differences between the software (at -350 HU) and pathology measurements and between the manual (lung and mediastinal windows) and pathology measurements were -0.12 mm (p = 0.74, -5.73 to 5.55]), 0.15 mm (p = 0.73, -6.92 to 7.22), and -1.14 mm (p < 0.001, -7.93 to 5.64), respectively. Software segmentation of ground-glass and solid components in subsolid nodules showed no significant difference with pathology. • Software can effectively segment ground-glass and solid components in subsolid nodules. • Software measurements show no significant difference with pathology measurements. • Manual measurements are more accurate on lung windows than on mediastinal windows.

A proposed framework for consensus-based lung tumour volume auto-segmentation in 4D computed tomography imaging

NASA Astrophysics Data System (ADS)

Martin, Spencer; Brophy, Mark; Palma, David; Louie, Alexander V.; Yu, Edward; Yaremko, Brian; Ahmad, Belal; Barron, John L.; Beauchemin, Steven S.; Rodrigues, George; Gaede, Stewart

2015-02-01

This work aims to propose and validate a framework for tumour volume auto-segmentation based on ground-truth estimates derived from multi-physician input contours to expedite 4D-CT based lung tumour volume delineation. 4D-CT datasets of ten non-small cell lung cancer (NSCLC) patients were manually segmented by 6 physicians. Multi-expert ground truth (GT) estimates were constructed using the STAPLE algorithm for the gross tumour volume (GTV) on all respiratory phases. Next, using a deformable model-based method, multi-expert GT on each individual phase of the 4D-CT dataset was propagated to all other phases providing auto-segmented GTVs and motion encompassing internal gross target volumes (IGTVs) based on GT estimates (STAPLE) from each respiratory phase of the 4D-CT dataset. Accuracy assessment of auto-segmentation employed graph cuts for 3D-shape reconstruction and point-set registration-based analysis yielding volumetric and distance-based measures. STAPLE-based auto-segmented GTV accuracy ranged from (81.51  ±  1.92) to (97.27  ±  0.28)% volumetric overlap of the estimated ground truth. IGTV auto-segmentation showed significantly improved accuracies with reduced variance for all patients ranging from 90.87 to 98.57% volumetric overlap of the ground truth volume. Additional metrics supported these observations with statistical significance. Accuracy of auto-segmentation was shown to be largely independent of selection of the initial propagation phase. IGTV construction based on auto-segmented GTVs within the 4D-CT dataset provided accurate and reliable target volumes compared to manual segmentation-based GT estimates. While inter-/intra-observer effects were largely mitigated, the proposed segmentation workflow is more complex than that of current clinical practice and requires further development.

A proposed framework for consensus-based lung tumour volume auto-segmentation in 4D computed tomography imaging.

PubMed

Martin, Spencer; Brophy, Mark; Palma, David; Louie, Alexander V; Yu, Edward; Yaremko, Brian; Ahmad, Belal; Barron, John L; Beauchemin, Steven S; Rodrigues, George; Gaede, Stewart

2015-02-21

This work aims to propose and validate a framework for tumour volume auto-segmentation based on ground-truth estimates derived from multi-physician input contours to expedite 4D-CT based lung tumour volume delineation. 4D-CT datasets of ten non-small cell lung cancer (NSCLC) patients were manually segmented by 6 physicians. Multi-expert ground truth (GT) estimates were constructed using the STAPLE algorithm for the gross tumour volume (GTV) on all respiratory phases. Next, using a deformable model-based method, multi-expert GT on each individual phase of the 4D-CT dataset was propagated to all other phases providing auto-segmented GTVs and motion encompassing internal gross target volumes (IGTVs) based on GT estimates (STAPLE) from each respiratory phase of the 4D-CT dataset. Accuracy assessment of auto-segmentation employed graph cuts for 3D-shape reconstruction and point-set registration-based analysis yielding volumetric and distance-based measures. STAPLE-based auto-segmented GTV accuracy ranged from (81.51  ±  1.92) to (97.27  ±  0.28)% volumetric overlap of the estimated ground truth. IGTV auto-segmentation showed significantly improved accuracies with reduced variance for all patients ranging from 90.87 to 98.57% volumetric overlap of the ground truth volume. Additional metrics supported these observations with statistical significance. Accuracy of auto-segmentation was shown to be largely independent of selection of the initial propagation phase. IGTV construction based on auto-segmented GTVs within the 4D-CT dataset provided accurate and reliable target volumes compared to manual segmentation-based GT estimates. While inter-/intra-observer effects were largely mitigated, the proposed segmentation workflow is more complex than that of current clinical practice and requires further development.

Large aperture segmented optics for space-to-ground communications.

PubMed

Lucy, R F

1968-08-01

A large aperture, moderate quality segmented optical array for use in noncoherent space-to-ground laser communications is determined as a function of resolution, diameter, focal length, and number of segments in the array. Secondary optics and construction tolerances are also discussed. Performance predictions show a typical receiver to be capable of megahertz communications at Mars distances during daylight operation.

SCOUT: simultaneous time segmentation and community detection in dynamic networks

PubMed Central

Hulovatyy, Yuriy; Milenković, Tijana

2016-01-01

Many evolving complex real-world systems can be modeled via dynamic networks. An important problem in dynamic network research is community detection, which finds groups of topologically related nodes. Typically, this problem is approached by assuming either that each time point has a distinct community organization or that all time points share a single community organization. The reality likely lies between these two extremes. To find the compromise, we consider community detection in the context of the problem of segment detection, which identifies contiguous time periods with consistent network structure. Consequently, we formulate a combined problem of segment community detection (SCD), which simultaneously partitions the network into contiguous time segments with consistent community organization and finds this community organization for each segment. To solve SCD, we introduce SCOUT, an optimization framework that explicitly considers both segmentation quality and partition quality. SCOUT addresses limitations of existing methods that can be adapted to solve SCD, which consider only one of segmentation quality or partition quality. In a thorough evaluation, SCOUT outperforms the existing methods in terms of both accuracy and computational complexity. We apply SCOUT to biological network data to study human aging. PMID:27881879

Joint experiments using ETS-5

NASA Astrophysics Data System (ADS)

Nakata, Mutsumi

1993-03-01

An overview of the PARTNERS (Pan-Pacific Regional Telecommunications Network Research Satellite) project, which is the post-mission utilization of the ETS-5 (Engineering Test Satellite-5) is presented. The project was registered at SAFISY (Space Agency Forum for International Space Year) and includes the following experiments: (1) research on radio propagation characteristics in satellite links in Pan-Pacific region; (2) joint study on development of rural satellite network using simple mobile station; (3) experiments on telecommunication using personal computers for academic network; (4) experiments on remote education and training through satellite networks; (5) experiments on remote medicine; (6) experiments on the operation of medical information data base; (7) experiments on transmission of the earth observation data; and (8) demonstration of real time transmission of Asia-Pacific ISY (International Space Year) Conference. The experiment systems consisting of space segment (ETS-5) and simple and low cost ground system composed of 1.2 m aperture parabolic antenna, TV (Television) conference system, and terminal equipment are outlined.

Running the figure to the ground: figure-ground segmentation during visual search.

PubMed

Ralph, Brandon C W; Seli, Paul; Cheng, Vivian O Y; Solman, Grayden J F; Smilek, Daniel

2014-04-01

We examined how figure-ground segmentation occurs across multiple regions of a visual array during a visual search task. Stimuli consisted of arrays of black-and-white figure-ground images in which roughly half of each image depicted a meaningful object, whereas the other half constituted a less meaningful shape. The colours of the meaningful regions of the targets and distractors were either the same (congruent) or different (incongruent). We found that incongruent targets took longer to locate than congruent targets (Experiments 1, 2, and 3) and that this segmentation-congruency effect decreased when the number of search items was reduced (Experiment 2). Furthermore, an analysis of eye movements revealed that participants spent more time scrutinising the target before confirming its identity on incongruent trials than on congruent trials (Experiment 3). These findings suggest that the distractor context influences target segmentation and detection during visual search. Copyright © 2014 Elsevier B.V. All rights reserved.

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

NASA Astrophysics Data System (ADS)

Ha, Jin Gwan; Moon, Hyeonjoon; Kwak, Jin Tae; Hassan, Syed Ibrahim; Dang, Minh; Lee, O. New; Park, Han Yong

2017-10-01

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

Vulnerability Analysis and Passenger Source Prediction in Urban Rail Transit Networks

PubMed Central

Wang, Junjie; Li, Yishuai; Liu, Jingyu; He, Kun; Wang, Pu

2013-01-01

Based on large-scale human mobility data collected in San Francisco and Boston, the morning peak urban rail transit (URT) ODs (origin-destination matrix) were estimated and the most vulnerable URT segments, those capable of causing the largest service interruptions, were identified. In both URT networks, a few highly vulnerable segments were observed. For this small group of vital segments, the impact of failure must be carefully evaluated. A bipartite URT usage network was developed and used to determine the inherent connections between urban rail transits and their passengers' travel demands. Although passengers' origins and destinations were easy to locate for a large number of URT segments, a few show very complicated spatial distributions. Based on the bipartite URT usage network, a new layer of the understanding of a URT segment's vulnerability can be achieved by taking the difficulty of addressing the failure of a given segment into account. Two proof-of-concept cases are described here: Possible transfer of passenger flow to the road network is here predicted in the cases of failures of two representative URT segments in San Francisco. PMID:24260355

Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN).

PubMed

Iqbal, Sajid; Ghani, M Usman; Saba, Tanzila; Rehman, Amjad

2018-04-01

A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research. © 2018 Wiley Periodicals, Inc.

Superpixel Cut for Figure-Ground Image Segmentation

NASA Astrophysics Data System (ADS)

Yang, Michael Ying; Rosenhahn, Bodo

2016-06-01

Figure-ground image segmentation has been a challenging problem in computer vision. Apart from the difficulties in establishing an effective framework to divide the image pixels into meaningful groups, the notions of figure and ground often need to be properly defined by providing either user inputs or object models. In this paper, we propose a novel graph-based segmentation framework, called superpixel cut. The key idea is to formulate foreground segmentation as finding a subset of superpixels that partitions a graph over superpixels. The problem is formulated as Min-Cut. Therefore, we propose a novel cost function that simultaneously minimizes the inter-class similarity while maximizing the intra-class similarity. This cost function is optimized using parametric programming. After a small learning step, our approach is fully automatic and fully bottom-up, which requires no high-level knowledge such as shape priors and scene content. It recovers coherent components of images, providing a set of multiscale hypotheses for high-level reasoning. We evaluate our proposed framework by comparing it to other generic figure-ground segmentation approaches. Our method achieves improved performance on state-of-the-art benchmark databases.

Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer images.

PubMed

Fu, Min; Wu, Wenming; Hong, Xiafei; Liu, Qiuhua; Jiang, Jialin; Ou, Yaobin; Zhao, Yupei; Gong, Xinqi

2018-04-24

Efficient computational recognition and segmentation of target organ from medical images are foundational in diagnosis and treatment, especially about pancreas cancer. In practice, the diversity in appearance of pancreas and organs in abdomen, makes detailed texture information of objects important in segmentation algorithm. According to our observations, however, the structures of previous networks, such as the Richer Feature Convolutional Network (RCF), are too coarse to segment the object (pancreas) accurately, especially the edge. In this paper, we extend the RCF, proposed to the field of edge detection, for the challenging pancreas segmentation, and put forward a novel pancreas segmentation network. By employing multi-layer up-sampling structure replacing the simple up-sampling operation in all stages, the proposed network fully considers the multi-scale detailed contexture information of object (pancreas) to perform per-pixel segmentation. Additionally, using the CT scans, we supply and train our network, thus get an effective pipeline. Working with our pipeline with multi-layer up-sampling model, we achieve better performance than RCF in the task of single object (pancreas) segmentation. Besides, combining with multi scale input, we achieve the 76.36% DSC (Dice Similarity Coefficient) value in testing data. The results of our experiments show that our advanced model works better than previous networks in our dataset. On the other words, it has better ability in catching detailed contexture information. Therefore, our new single object segmentation model has practical meaning in computational automatic diagnosis.

Noise destroys feedback enhanced figure-ground segmentation but not feedforward figure-ground segmentation.

PubMed

Romeo, August; Arall, Marina; Supèr, Hans

2012-01-01

Figure-ground (FG) segmentation is the separation of visual information into background and foreground objects. In the visual cortex, FG responses are observed in the late stimulus response period, when neurons fire in tonic mode, and are accompanied by a switch in cortical state. When such a switch does not occur, FG segmentation fails. Currently, it is not known what happens in the brain on such occasions. A biologically plausible feedforward spiking neuron model was previously devised that performed FG segmentation successfully. After incorporating feedback the FG signal was enhanced, which was accompanied by a change in spiking regime. In a feedforward model neurons respond in a bursting mode whereas in the feedback model neurons fired in tonic mode. It is known that bursts can overcome noise, while tonic firing appears to be much more sensitive to noise. In the present study, we try to elucidate how the presence of noise can impair FG segmentation, and to what extent the feedforward and feedback pathways can overcome noise. We show that noise specifically destroys the feedback enhanced FG segmentation and leaves the feedforward FG segmentation largely intact. Our results predict that noise produces failure in FG perception.

Noise destroys feedback enhanced figure-ground segmentation but not feedforward figure-ground segmentation

PubMed Central

Romeo, August; Arall, Marina; Supèr, Hans

2012-01-01

Figure-ground (FG) segmentation is the separation of visual information into background and foreground objects. In the visual cortex, FG responses are observed in the late stimulus response period, when neurons fire in tonic mode, and are accompanied by a switch in cortical state. When such a switch does not occur, FG segmentation fails. Currently, it is not known what happens in the brain on such occasions. A biologically plausible feedforward spiking neuron model was previously devised that performed FG segmentation successfully. After incorporating feedback the FG signal was enhanced, which was accompanied by a change in spiking regime. In a feedforward model neurons respond in a bursting mode whereas in the feedback model neurons fired in tonic mode. It is known that bursts can overcome noise, while tonic firing appears to be much more sensitive to noise. In the present study, we try to elucidate how the presence of noise can impair FG segmentation, and to what extent the feedforward and feedback pathways can overcome noise. We show that noise specifically destroys the feedback enhanced FG segmentation and leaves the feedforward FG segmentation largely intact. Our results predict that noise produces failure in FG perception. PMID:22934028

Biased figure-ground assignment affects conscious object recognition in spatial neglect.

PubMed

Eramudugolla, Ranmalee; Driver, Jon; Mattingley, Jason B

2010-09-01

Unilateral spatial neglect is a disorder of attention and spatial representation, in which early visual processes such as figure-ground segmentation have been assumed to be largely intact. There is evidence, however, that the spatial attention bias underlying neglect can bias the segmentation of a figural region from its background. Relatively few studies have explicitly examined the effect of spatial neglect on processing the figures that result from such scene segmentation. Here, we show that a neglect patient's bias in figure-ground segmentation directly influences his conscious recognition of these figures. By varying the relative salience of figural and background regions in static, two-dimensional displays, we show that competition between elements in such displays can modulate a neglect patient's ability to recognise parsed figures in a scene. The findings provide insight into the interaction between scene segmentation, explicit object recognition, and attention.

CONEDEP: COnvolutional Neural network based Earthquake DEtection and Phase Picking

NASA Astrophysics Data System (ADS)

Zhou, Y.; Huang, Y.; Yue, H.; Zhou, S.; An, S.; Yun, N.

2017-12-01

We developed an automatic local earthquake detection and phase picking algorithm based on Fully Convolutional Neural network (FCN). The FCN algorithm detects and segments certain features (phases) in 3 component seismograms to realize efficient picking. We use STA/LTA algorithm and template matching algorithm to construct the training set from seismograms recorded 1 month before and after the Wenchuan earthquake. Precise P and S phases are identified and labeled to construct the training set. Noise data are produced by combining back-ground noise and artificial synthetic noise to form the equivalent scale of noise set as the signal set. Training is performed on GPUs to achieve efficient convergence. Our algorithm has significantly improved performance in terms of the detection rate and precision in comparison with STA/LTA and template matching algorithms.

SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation.

PubMed

Xue, Yuan; Xu, Tao; Zhang, Han; Long, L Rodney; Huang, Xiaolei

2018-05-03

Inspired by classic Generative Adversarial Networks (GANs), we propose a novel end-to-end adversarial neural network, called SegAN, for the task of medical image segmentation. Since image segmentation requires dense, pixel-level labeling, the single scalar real/fake output of a classic GAN's discriminator may be ineffective in producing stable and sufficient gradient feedback to the networks. Instead, we use a fully convolutional neural network as the segmentor to generate segmentation label maps, and propose a novel adversarial critic network with a multi-scale L 1 loss function to force the critic and segmentor to learn both global and local features that capture long- and short-range spatial relationships between pixels. In our SegAN framework, the segmentor and critic networks are trained in an alternating fashion in a min-max game: The critic is trained by maximizing a multi-scale loss function, while the segmentor is trained with only gradients passed along by the critic, with the aim to minimize the multi-scale loss function. We show that such a SegAN framework is more effective and stable for the segmentation task, and it leads to better performance than the state-of-the-art U-net segmentation method. We tested our SegAN method using datasets from the MICCAI BRATS brain tumor segmentation challenge. Extensive experimental results demonstrate the effectiveness of the proposed SegAN with multi-scale loss: on BRATS 2013 SegAN gives performance comparable to the state-of-the-art for whole tumor and tumor core segmentation while achieves better precision and sensitivity for Gd-enhance tumor core segmentation; on BRATS 2015 SegAN achieves better performance than the state-of-the-art in both dice score and precision.

Security aspects of space operations data

NASA Technical Reports Server (NTRS)

Schmitz, Stefan

1993-01-01

This paper deals with data security. It identifies security threats to European Space Agency's (ESA) In Orbit Infrastructure Ground Segment (IOI GS) and proposes a method of dealing with its complex data structures from the security point of view. It is part of the 'Analysis of Failure Modes, Effects Hazards and Risks of the IOI GS for Operations, including Backup Facilities and Functions' carried out on behalf of the European Space Operations Center (ESOC). The security part of this analysis has been prepared with the following aspects in mind: ESA's large decentralized ground facilities for operations, the multiple organizations/users involved in the operations and the developments of ground data systems, and the large heterogeneous network structure enabling access to (sensitive) data which does involve crossing organizational boundaries. An IOI GS data objects classification is introduced to determine the extent of the necessary protection mechanisms. The proposal of security countermeasures is oriented towards the European 'Information Technology Security Evaluation Criteria (ITSEC)' whose hierarchically organized requirements can be directly mapped to the security sensitivity classification.

A fully convolutional networks (FCN) based image segmentation algorithm in binocular imaging system

NASA Astrophysics Data System (ADS)

Long, Zourong; Wei, Biao; Feng, Peng; Yu, Pengwei; Liu, Yuanyuan

2018-01-01

This paper proposes an image segmentation algorithm with fully convolutional networks (FCN) in binocular imaging system under various circumstance. Image segmentation is perfectly solved by semantic segmentation. FCN classifies the pixels, so as to achieve the level of image semantic segmentation. Different from the classical convolutional neural networks (CNN), FCN uses convolution layers instead of the fully connected layers. So it can accept image of arbitrary size. In this paper, we combine the convolutional neural network and scale invariant feature matching to solve the problem of visual positioning under different scenarios. All high-resolution images are captured with our calibrated binocular imaging system and several groups of test data are collected to verify this method. The experimental results show that the binocular images are effectively segmented without over-segmentation. With these segmented images, feature matching via SURF method is implemented to obtain regional information for further image processing. The final positioning procedure shows that the results are acceptable in the range of 1.4 1.6 m, the distance error is less than 10mm.

A Composite Model of Wound Segmentation Based on Traditional Methods and Deep Neural Networks

PubMed Central

Wang, Changjian; Liu, Xiaohui; Jin, Shiyao

2018-01-01

Wound segmentation plays an important supporting role in the wound observation and wound healing. Current methods of image segmentation include those based on traditional process of image and those based on deep neural networks. The traditional methods use the artificial image features to complete the task without large amounts of labeled data. Meanwhile, the methods based on deep neural networks can extract the image features effectively without the artificial design, but lots of training data are required. Combined with the advantages of them, this paper presents a composite model of wound segmentation. The model uses the skin with wound detection algorithm we designed in the paper to highlight image features. Then, the preprocessed images are segmented by deep neural networks. And semantic corrections are applied to the segmentation results at last. The model shows a good performance in our experiment. PMID:29955227

Evaluating segmentation error without ground truth.

PubMed

Kohlberger, Timo; Singh, Vivek; Alvino, Chris; Bahlmann, Claus; Grady, Leo

2012-01-01

The automatic delineation of the boundaries of organs and other anatomical structures is a key component of many medical image processing systems. In this paper we present a generic learning approach based on a novel space of segmentation features, which can be trained to predict the overlap error and Dice coefficient of an arbitrary organ segmentation without knowing the ground truth delineation. We show the regressor to be much stronger a predictor of these error metrics than the responses of probabilistic boosting classifiers trained on the segmentation boundary. The presented approach not only allows us to build reliable confidence measures and fidelity checks, but also to rank several segmentation hypotheses against each other during online usage of the segmentation algorithm in clinical practice.

Figure-ground segmentation based on class-independent shape priors

NASA Astrophysics Data System (ADS)

Li, Yang; Liu, Yang; Liu, Guojun; Guo, Maozu

2018-01-01

We propose a method to generate figure-ground segmentation by incorporating shape priors into the graph-cuts algorithm. Given an image, we first obtain a linear representation of an image and then apply directional chamfer matching to generate class-independent, nonparametric shape priors, which provide shape clues for the graph-cuts algorithm. We then enforce shape priors in a graph-cuts energy function to produce object segmentation. In contrast to previous segmentation methods, the proposed method shares shape knowledge for different semantic classes and does not require class-specific model training. Therefore, the approach obtains high-quality segmentation for objects. We experimentally validate that the proposed method outperforms previous approaches using the challenging PASCAL VOC 2010/2012 and Berkeley (BSD300) segmentation datasets.

Robust hepatic vessel segmentation using multi deep convolution network

NASA Astrophysics Data System (ADS)

Kitrungrotsakul, Titinunt; Han, Xian-Hua; Iwamoto, Yutaro; Foruzan, Amir Hossein; Lin, Lanfen; Chen, Yen-Wei

2017-03-01

Extraction of blood vessels of the organ is a challenging task in the area of medical image processing. It is really difficult to get accurate vessel segmentation results even with manually labeling by human being. The difficulty of vessels segmentation is the complicated structure of blood vessels and its large variations that make them hard to recognize. In this paper, we present deep artificial neural network architecture to automatically segment the hepatic vessels from computed tomography (CT) image. We proposed novel deep neural network (DNN) architecture for vessel segmentation from a medical CT volume, which consists of three deep convolution neural networks to extract features from difference planes of CT data. The three networks have share features at the first convolution layer but will separately learn their own features in the second layer. All three networks will join again at the top layer. To validate effectiveness and efficiency of our proposed method, we conduct experiments on 12 CT volumes which training data are randomly generate from 5 CT volumes and 7 using for test. Our network can yield an average dice coefficient 0.830, while 3D deep convolution neural network can yield around 0.7 and multi-scale can yield only 0.6.

Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks

PubMed Central

Huo, Yuankai; Xu, Zhoubing; Bao, Shunxing; Bermudez, Camilo; Plassard, Andrew J.; Liu, Jiaqi; Yao, Yuang; Assad, Albert; Abramson, Richard G.; Landman, Bennett A.

2018-01-01

Spleen volume estimation using automated image segmentation technique may be used to detect splenomegaly (abnormally enlarged spleen) on Magnetic Resonance Imaging (MRI) scans. In recent years, Deep Convolutional Neural Networks (DCNN) segmentation methods have demonstrated advantages for abdominal organ segmentation. However, variations in both size and shape of the spleen on MRI images may result in large false positive and false negative labeling when deploying DCNN based methods. In this paper, we propose the Splenomegaly Segmentation Network (SSNet) to address spatial variations when segmenting extraordinarily large spleens. SSNet was designed based on the framework of image-to-image conditional generative adversarial networks (cGAN). Specifically, the Global Convolutional Network (GCN) was used as the generator to reduce false negatives, while the Markovian discriminator (PatchGAN) was used to alleviate false positives. A cohort of clinically acquired 3D MRI scans (both T1 weighted and T2 weighted) from patients with splenomegaly were used to train and test the networks. The experimental results demonstrated that a mean Dice coefficient of 0.9260 and a median Dice coefficient of 0.9262 using SSNet on independently tested MRI volumes of patients with splenomegaly.

Segmented-memory recurrent neural networks.

PubMed

Chen, Jinmiao; Chaudhari, Narendra S

2009-08-01

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.

Generating Ground Reference Data for a Global Impervious Surface Survey

NASA Technical Reports Server (NTRS)

Tilton, James C.; De Colstoun, Eric Brown; Wolfe, Robert E.; Tan, Bin; Huang, Chengquan

2012-01-01

We are developing an approach for generating ground reference data in support of a project to produce a 30m impervious cover data set of the entire Earth for the years 2000 and 2010 based on the Landsat Global Land Survey (GLS) data set. Since sufficient ground reference data for training and validation is not available from ground surveys, we are developing an interactive tool, called HSegLearn, to facilitate the photo-interpretation of 1 to 2 m spatial resolution imagery data, which we will use to generate the needed ground reference data at 30m. Through the submission of selected region objects and positive or negative examples of impervious surfaces, HSegLearn enables an analyst to automatically select groups of spectrally similar objects from a hierarchical set of image segmentations produced by the HSeg image segmentation program at an appropriate level of segmentation detail, and label these region objects as either impervious or nonimpervious.

Is STAPLE algorithm confident to assess segmentation methods in PET imaging?

NASA Astrophysics Data System (ADS)

Dewalle-Vignion, Anne-Sophie; Betrouni, Nacim; Baillet, Clio; Vermandel, Maximilien

2015-12-01

Accurate tumor segmentation in [18F]-fluorodeoxyglucose positron emission tomography is crucial for tumor response assessment and target volume definition in radiation therapy. Evaluation of segmentation methods from clinical data without ground truth is usually based on physicians’ manual delineations. In this context, the simultaneous truth and performance level estimation (STAPLE) algorithm could be useful to manage the multi-observers variability. In this paper, we evaluated how this algorithm could accurately estimate the ground truth in PET imaging. Complete evaluation study using different criteria was performed on simulated data. The STAPLE algorithm was applied to manual and automatic segmentation results. A specific configuration of the implementation provided by the Computational Radiology Laboratory was used. Consensus obtained by the STAPLE algorithm from manual delineations appeared to be more accurate than manual delineations themselves (80% of overlap). An improvement of the accuracy was also observed when applying the STAPLE algorithm to automatic segmentations results. The STAPLE algorithm, with the configuration used in this paper, is more appropriate than manual delineations alone or automatic segmentations results alone to estimate the ground truth in PET imaging. Therefore, it might be preferred to assess the accuracy of tumor segmentation methods in PET imaging.

Is STAPLE algorithm confident to assess segmentation methods in PET imaging?

PubMed

Dewalle-Vignion, Anne-Sophie; Betrouni, Nacim; Baillet, Clio; Vermandel, Maximilien

2015-12-21

Accurate tumor segmentation in [18F]-fluorodeoxyglucose positron emission tomography is crucial for tumor response assessment and target volume definition in radiation therapy. Evaluation of segmentation methods from clinical data without ground truth is usually based on physicians' manual delineations. In this context, the simultaneous truth and performance level estimation (STAPLE) algorithm could be useful to manage the multi-observers variability. In this paper, we evaluated how this algorithm could accurately estimate the ground truth in PET imaging. Complete evaluation study using different criteria was performed on simulated data. The STAPLE algorithm was applied to manual and automatic segmentation results. A specific configuration of the implementation provided by the Computational Radiology Laboratory was used. Consensus obtained by the STAPLE algorithm from manual delineations appeared to be more accurate than manual delineations themselves (80% of overlap). An improvement of the accuracy was also observed when applying the STAPLE algorithm to automatic segmentations results. The STAPLE algorithm, with the configuration used in this paper, is more appropriate than manual delineations alone or automatic segmentations results alone to estimate the ground truth in PET imaging. Therefore, it might be preferred to assess the accuracy of tumor segmentation methods in PET imaging.

Fully convolutional network with cluster for semantic segmentation

NASA Astrophysics Data System (ADS)

Ma, Xiao; Chen, Zhongbi; Zhang, Jianlin

2018-04-01

At present, image semantic segmentation technology has been an active research topic for scientists in the field of computer vision and artificial intelligence. Especially, the extensive research of deep neural network in image recognition greatly promotes the development of semantic segmentation. This paper puts forward a method based on fully convolutional network, by cluster algorithm k-means. The cluster algorithm using the image's low-level features and initializing the cluster centers by the super-pixel segmentation is proposed to correct the set of points with low reliability, which are mistakenly classified in great probability, by the set of points with high reliability in each clustering regions. This method refines the segmentation of the target contour and improves the accuracy of the image segmentation.

As-built design specification for segment map (Sgmap) program

NASA Technical Reports Server (NTRS)

Tompkins, M. A. (Principal Investigator)

1981-01-01

The segment map program (SGMAP), which is part of the CLASFYT package, is described in detail. This program is designed to output symbolic maps or numerical dumps from LANDSAT cluster/classification files or aircraft ground truth/processed ground truth files which are in 'universal' format.

What limits the achievable areal densities of large aperture space telescopes?

NASA Astrophysics Data System (ADS)

Peterson, Lee D.; Hinkle, Jason D.

2005-08-01

This paper examines requirements trades involving areal density for large space telescope mirrors. A segmented mirror architecture is used to define a quantitative example that leads to relevant insight about the trades. In this architecture, the mirror consists of segments of non-structural optical elements held in place by a structural truss that rests behind the segments. An analysis is presented of the driving design requirements for typical on-orbit loads and ground-test loads. It is shown that the driving on-orbit load would be the resonance of the lowest mode of the mirror by a reaction wheel static unbalance. The driving ground-test load would be dynamics due to ground-induced random vibration. Two general conclusions are derived from these results. First, the areal density that can be allocated to the segments depends on the depth allocated to the structure. More depth in the structure allows the allocation of more mass to the segments. This, however, leads to large structural depth that might be a significant development challenge. Second, the requirement for ground-test-ability results in an order of magnitude or more depth in the structure than is required by the on-orbit loads. This leads to the proposition that avoiding ground test as a driving requirement should be a fundamental technology on par with the provision of deployable depth. Both are important structural challenges for these future systems.

End-to-end simulation and verification of GNC and robotic systems considering both space segment and ground segment

NASA Astrophysics Data System (ADS)

Benninghoff, Heike; Rems, Florian; Risse, Eicke; Brunner, Bernhard; Stelzer, Martin; Krenn, Rainer; Reiner, Matthias; Stangl, Christian; Gnat, Marcin

2018-01-01

In the framework of a project called on-orbit servicing end-to-end simulation, the final approach and capture of a tumbling client satellite in an on-orbit servicing mission are simulated. The necessary components are developed and the entire end-to-end chain is tested and verified. This involves both on-board and on-ground systems. The space segment comprises a passive client satellite, and an active service satellite with its rendezvous and berthing payload. The space segment is simulated using a software satellite simulator and two robotic, hardware-in-the-loop test beds, the European Proximity Operations Simulator (EPOS) 2.0 and the OOS-Sim. The ground segment is established as for a real servicing mission, such that realistic operations can be performed from the different consoles in the control room. During the simulation of the telerobotic operation, it is important to provide a realistic communication environment with different parameters like they occur in the real world (realistic delay and jitter, for example).

Dynamic segment shared protection for multicast traffic in meshed wavelength-division-multiplexing optical networks

NASA Astrophysics Data System (ADS)

Liao, Luhua; Li, Lemin; Wang, Sheng

2006-12-01

We investigate the protection approach for dynamic multicast traffic under shared risk link group (SRLG) constraints in meshed wavelength-division-multiplexing optical networks. We present a shared protection algorithm called dynamic segment shared protection for multicast traffic (DSSPM), which can dynamically adjust the link cost according to the current network state and can establish a primary light-tree as well as corresponding SRLG-disjoint backup segments for a dependable multicast connection. A backup segment can efficiently share the wavelength capacity of its working tree and the common resources of other backup segments based on SRLG-disjoint constraints. The simulation results show that DSSPM not only can protect the multicast sessions against a single-SRLG breakdown, but can make better use of the wavelength resources and also lower the network blocking probability.

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Key Features of the Deployed NPP/NPOESS Ground System

NASA Astrophysics Data System (ADS)

Heckmann, G.; Grant, K. D.; Mulligan, J. E.

2010-12-01

The National Oceanic & Atmospheric Administration (NOAA), Department of Defense (DoD), and National Aeronautics & Space Administration (NASA) are jointly acquiring the next-generation weather/environmental satellite system; the National Polar-orbiting Operational Environmental Satellite System (NPOESS). NPOESS replaces the current NOAA Polar-orbiting Operational Environmental Satellites (POES) and DoD Defense Meteorological Satellite Program (DMSP). NPOESS satellites carry sensors to collect meteorological, oceanographic, climatological, and solar-geophysical data of the earth, atmosphere, and space. The ground data processing segment is the Interface Data Processing Segment (IDPS), developed by Raytheon Intelligence & Information Systems (IIS). The IDPS processes NPOESS Preparatory Project (NPP)/NPOESS satellite data to provide environmental data products/records (EDRs) to NOAA and DoD processing centers operated by the US government. The IDPS will process EDRs beginning with NPP and continuing through the lifetime of the NPOESS system. The command & telemetry segment is the Command, Control & Communications Segment (C3S), also developed by Raytheon IIS. C3S is responsible for managing the overall NPP/NPOESS missions from control & status of the space and ground assets to ensuring delivery of timely, high quality data from the Space Segment to IDPS for processing. In addition, the C3S provides the globally-distributed ground assets needed to collect and transport mission, telemetry, and command data between the satellites and processing locations. The C3S provides all functions required for day-to-day satellite commanding & state-of-health monitoring, and delivery of Stored Mission Data to each Central IDP for data products development and transfer to system subscribers. The C3S also monitors and reports system-wide health & status and data communications with external systems and between the segments. The C3S & IDPS segments were delivered & transitioned to operations for NPP. C3S transitioned to operations at the NOAA Satellite Operations Facility (NSOF) in Suitland Maryland in August 2007 and IDPS transitioned in July 2009. Both segments were involved with several compatibility tests with the NPP Satellite at the Ball Aerospace Technology Corporation (BATC) factory. The compatibility tests involved the spacecraft bus, the four sensors (VIIRS, ATMS, CrIS and OMPS), and both ground segments flowing data between the NSOF and BATC factory and flowing data from the polar ground station (Svalbard) over high-speed links back to the NSOF and the two IDP locations (NESDIS & AFWA). This presentation will describe the NPP/NPOESS ground architecture features & enhancements for the NPOESS era. These will include C3S-provided space-to-ground connectivity, reliable and secure data delivery and insight & oversight of the total operation. For NPOESS the ground architecture is extended to provide additional ground receptor sites to reduce data product delivery times to users and delivery of additional sensor data products from sensors similar to NPP and more NPOESS sensors. This architecture is also extended from two Centrals (NESDIS & AFWA) to two additional Centrals (FNMOC & NAVO). IDPS acts as a buffer minimizing changes in how users request and receive data products.

LANDSAT-D ground segment operations plan, revision A

NASA Technical Reports Server (NTRS)

Evans, B.

1982-01-01

The basic concept for the utilization of LANDSAT ground processing resources is described. Only the steady state activities that support normal ground processing are addressed. This ground segment operations plan covers all processing of the multispectral scanner and the processing of thematic mapper through data acquisition and payload correction data generation for the LANDSAT 4 mission. The capabilities embedded in the hardware and software elements are presented from an operations viewpoint. The personnel assignments associated with each functional process and the mechanisms available for controlling the overall data flow are identified.

Evolution of semilocal string networks. II. Velocity estimators

NASA Astrophysics Data System (ADS)

Lopez-Eiguren, A.; Urrestilla, J.; Achúcarro, A.; Avgoustidis, A.; Martins, C. J. A. P.

2017-07-01

We continue a comprehensive numerical study of semilocal string networks and their cosmological evolution. These can be thought of as hybrid networks comprised of (nontopological) string segments, whose core structure is similar to that of Abelian Higgs vortices, and whose ends have long-range interactions and behavior similar to that of global monopoles. Our study provides further evidence of a linear scaling regime, already reported in previous studies, for the typical length scale and velocity of the network. We introduce a new algorithm to identify the position of the segment cores. This allows us to determine the length and velocity of each individual segment and follow their evolution in time. We study the statistical distribution of segment lengths and velocities for radiation- and matter-dominated evolution in the regime where the strings are stable. Our segment detection algorithm gives higher length values than previous studies based on indirect detection methods. The statistical distribution shows no evidence of (anti)correlation between the speed and the length of the segments.

Student beats the teacher: deep neural networks for lateral ventricles segmentation in brain MR

NASA Astrophysics Data System (ADS)

Ghafoorian, Mohsen; Teuwen, Jonas; Manniesing, Rashindra; Leeuw, Frank-Erik d.; van Ginneken, Bram; Karssemeijer, Nico; Platel, Bram

2018-03-01

Ventricular volume and its progression are known to be linked to several brain diseases such as dementia and schizophrenia. Therefore accurate measurement of ventricle volume is vital for longitudinal studies on these disorders, making automated ventricle segmentation algorithms desirable. In the past few years, deep neural networks have shown to outperform the classical models in many imaging domains. However, the success of deep networks is dependent on manually labeled data sets, which are expensive to acquire especially for higher dimensional data in the medical domain. In this work, we show that deep neural networks can be trained on muchcheaper-to-acquire pseudo-labels (e.g., generated by other automated less accurate methods) and still produce more accurate segmentations compared to the quality of the labels. To show this, we use noisy segmentation labels generated by a conventional region growing algorithm to train a deep network for lateral ventricle segmentation. Then on a large manually annotated test set, we show that the network significantly outperforms the conventional region growing algorithm which was used to produce the training labels for the network. Our experiments report a Dice Similarity Coefficient (DSC) of 0.874 for the trained network compared to 0.754 for the conventional region growing algorithm (p < 0.001).

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

NASA Astrophysics Data System (ADS)

Moran, Steven; Gaonkar, Bilwaj; Whitehead, William; Wolk, Aidan; Macyszyn, Luke; Iyer, Subramanian S.

2018-03-01

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the 1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

Blood vessels segmentation of hatching eggs based on fully convolutional networks

NASA Astrophysics Data System (ADS)

Geng, Lei; Qiu, Ling; Wu, Jun; Xiao, Zhitao

2018-04-01

FCN, trained end-to-end, pixels-to-pixels, predict result of each pixel. It has been widely used for semantic segmentation. In order to realize the blood vessels segmentation of hatching eggs, a method based on FCN is proposed in this paper. The training datasets are composed of patches extracted from very few images to augment data. The network combines with lower layer and deconvolution to enables precise segmentation. The proposed method frees from the problem that training deep networks need large scale samples. Experimental results on hatching eggs demonstrate that this method can yield more accurate segmentation outputs than previous researches. It provides a convenient reference for fertility detection subsequently.

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images.

PubMed

Chen, Hao; Dou, Qi; Yu, Lequan; Qin, Jing; Heng, Pheng-Ann

2018-04-15

Segmentation of key brain tissues from 3D medical images is of great significance for brain disease diagnosis, progression assessment and monitoring of neurologic conditions. While manual segmentation is time-consuming, laborious, and subjective, automated segmentation is quite challenging due to the complicated anatomical environment of brain and the large variations of brain tissues. We propose a novel voxelwise residual network (VoxResNet) with a set of effective training schemes to cope with this challenging problem. The main merit of residual learning is that it can alleviate the degradation problem when training a deep network so that the performance gains achieved by increasing the network depth can be fully leveraged. With this technique, our VoxResNet is built with 25 layers, and hence can generate more representative features to deal with the large variations of brain tissues than its rivals using hand-crafted features or shallower networks. In order to effectively train such a deep network with limited training data for brain segmentation, we seamlessly integrate multi-modality and multi-level contextual information into our network, so that the complementary information of different modalities can be harnessed and features of different scales can be exploited. Furthermore, an auto-context version of the VoxResNet is proposed by combining the low-level image appearance features, implicit shape information, and high-level context together for further improving the segmentation performance. Extensive experiments on the well-known benchmark (i.e., MRBrainS) of brain segmentation from 3D magnetic resonance (MR) images corroborated the efficacy of the proposed VoxResNet. Our method achieved the first place in the challenge out of 37 competitors including several state-of-the-art brain segmentation methods. Our method is inherently general and can be readily applied as a powerful tool to many brain-related studies, where accurate segmentation of brain structures is critical. Copyright © 2017 Elsevier Inc. All rights reserved.

Accurate segmentation of lung fields on chest radiographs using deep convolutional networks

NASA Astrophysics Data System (ADS)

Arbabshirani, Mohammad R.; Dallal, Ahmed H.; Agarwal, Chirag; Patel, Aalpan; Moore, Gregory

2017-02-01

Accurate segmentation of lung fields on chest radiographs is the primary step for computer-aided detection of various conditions such as lung cancer and tuberculosis. The size, shape and texture of lung fields are key parameters for chest X-ray (CXR) based lung disease diagnosis in which the lung field segmentation is a significant primary step. Although many methods have been proposed for this problem, lung field segmentation remains as a challenge. In recent years, deep learning has shown state of the art performance in many visual tasks such as object detection, image classification and semantic image segmentation. In this study, we propose a deep convolutional neural network (CNN) framework for segmentation of lung fields. The algorithm was developed and tested on 167 clinical posterior-anterior (PA) CXR images collected retrospectively from picture archiving and communication system (PACS) of Geisinger Health System. The proposed multi-scale network is composed of five convolutional and two fully connected layers. The framework achieved IOU (intersection over union) of 0.96 on the testing dataset as compared to manual segmentation. The suggested framework outperforms state of the art registration-based segmentation by a significant margin. To our knowledge, this is the first deep learning based study of lung field segmentation on CXR images developed on a heterogeneous clinical dataset. The results suggest that convolutional neural networks could be employed reliably for lung field segmentation.

Atomic Force Microscopy Nanomechanical Mapping Visualizes Interfacial Broadening between Networks Due to Chemical Exchange Reactions.

PubMed

He, Changfei; Shi, Shaowei; Wu, Xuefei; Russell, Thomas P; Wang, Dong

2018-06-06

The interfacial broadening between two different epoxy networks having different moduli was nanomechanically mapped. The interfacial broadening of the two networks produced an interfacial zone having a gradient in the concentration and, hence, properties of the original two networks. This interfacial broadening of the networks leads to the generation of a new network with a segmental composition corresponding to a mixture of the original two network segments. The intermixing of the two, by nature of the exchange reactions, was on the segmental level. By mapping the time dependence of the variation in the modulus at different temperatures, the kinetics of the exchange reaction was measured and, by varying the temperature, the activation energy of the exchange reaction was determined.

System services and architecture of the TMI satellite mobile data system

NASA Technical Reports Server (NTRS)

Gokhale, D.; Agarwal, A.; Guibord, A.

1993-01-01

The North American Mobile Satellite Service (MSS) system being developed by AMSC/TMI and scheduled to go into service in early 1995 will include the provision for real time packet switched services (mobile data service - MDS) and circuit switched services (mobile telephony service - MTS). These services will utilize geostationary satellites which provide access to mobile terminals (MT's) through L-band beams. The MDS system utilizes a star topology with a centralized data hub (DH) and will support a large number of mobile terminals. The DH, which accesses the satellite via a single Ku band beam, is responsible for satellite resource management, for providing mobile users with access to public and private data networks, and for comprehensive network management of the system. This paper describes the various MDS services available for the users, the ground segment elements involved in the provisioning of these services, and a summary description of the channel types, protocol architecture, and network management capabilities provided within the system.

Analytic method for calculating properties of random walks on networks

NASA Technical Reports Server (NTRS)

Goldhirsch, I.; Gefen, Y.

1986-01-01

A method for calculating the properties of discrete random walks on networks is presented. The method divides complex networks into simpler units whose contribution to the mean first-passage time is calculated. The simplified network is then further iterated. The method is demonstrated by calculating mean first-passage times on a segment, a segment with a single dangling bond, a segment with many dangling bonds, and a looplike structure. The results are analyzed and related to the applicability of the Einstein relation between conductance and diffusion.

Gaia Launch Imminent: A Review of Practices (Good and Bad) in Building the Gaia Ground Segment

NASA Astrophysics Data System (ADS)

O'Mullane, W.

2014-05-01

As we approach launch the Gaia ground segment is ready to process a steady stream of complex data coming from Gaia at L2. This talk will focus on the software engineering aspects of the ground segment. Of course in a short paper it is difficult to cover everything but an attempt will be made to highlight some good things, like the Dictionary Tool and some things to be careful with like computer aided software engineering tools. The usefulness of some standards like ECSS will be touched upon. Testing is also certainly part of this story as are Challenges or Rehearsals so they will not go without mention.

Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study.

PubMed

Blanc-Durand, Paul; Van Der Gucht, Axel; Schaefer, Niklaus; Itti, Emmanuel; Prior, John O

2018-01-01

Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Convolutional Neural Network (CNN). All dynamic 18F-FET PET brain image volumes were temporally realigned to the first dynamic acquisition, coregistered and spatially normalized onto the Montreal Neurological Institute template. Ground truth segmentations were obtained using manual delineation and thresholding (1.3 x background). The volumetric CNN was implemented based on a modified Keras implementation of a U-Net library with 3 layers for the encoding and decoding paths. Dice similarity coefficient (DSC) was used as an accuracy measure of segmentation. Thirty-seven patients were included (26 [70%] in the training set and 11 [30%] in the validation set). All 11 lesions were accurately detected with no false positive, resulting in a sensitivity and a specificity for the detection at the tumor level of 100%. After 150 epochs, DSC reached 0.7924 in the training set and 0.7911 in the validation set. After morphological dilatation and fixed thresholding of the predicted U-Net mask a substantial improvement of the DSC to 0.8231 (+ 4.1%) was noted. At the voxel level, this segmentation led to a 0.88 sensitivity [95% CI, 87.1 to, 88.2%] a 0.99 specificity [99.9 to 99.9%], a 0.78 positive predictive value: [76.9 to 78.3%], and a 0.99 negative predictive value [99.9 to 99.9%]. With relatively high performance, it was proposed the first full 3D automated procedure for segmentation of 18F-FET PET brain images of patients with different gliomas using a U-Net CNN architecture.

Automatic detection and segmentation of brain metastases on multimodal MR images with a deep convolutional neural network.

PubMed

Charron, Odelin; Lallement, Alex; Jarnet, Delphine; Noblet, Vincent; Clavier, Jean-Baptiste; Meyer, Philippe

2018-04-01

Stereotactic treatments are today the reference techniques for the irradiation of brain metastases in radiotherapy. The dose per fraction is very high, and delivered in small volumes (diameter <1 cm). As part of these treatments, effective detection and precise segmentation of lesions are imperative. Many methods based on deep-learning approaches have been developed for the automatic segmentation of gliomas, but very little for that of brain metastases. We adapted an existing 3D convolutional neural network (DeepMedic) to detect and segment brain metastases on MRI. At first, we sought to adapt the network parameters to brain metastases. We then explored the single or combined use of different MRI modalities, by evaluating network performance in terms of detection and segmentation. We also studied the interest of increasing the database with virtual patients or of using an additional database in which the active parts of the metastases are separated from the necrotic parts. Our results indicated that a deep network approach is promising for the detection and the segmentation of brain metastases on multimodal MRI. Copyright © 2018 Elsevier Ltd. All rights reserved.

The ASAC Flight Segment and Network Cost Models

NASA Technical Reports Server (NTRS)

Kaplan, Bruce J.; Lee, David A.; Retina, Nusrat; Wingrove, Earl R., III; Malone, Brett; Hall, Stephen G.; Houser, Scott A.

1997-01-01

To assist NASA in identifying research art, with the greatest potential for improving the air transportation system, two models were developed as part of its Aviation System Analysis Capability (ASAC). The ASAC Flight Segment Cost Model (FSCM) is used to predict aircraft trajectories, resource consumption, and variable operating costs for one or more flight segments. The Network Cost Model can either summarize the costs for a network of flight segments processed by the FSCM or can be used to independently estimate the variable operating costs of flying a fleet of equipment given the number of departures and average flight stage lengths.

Intuitive Terrain Reconstruction Using Height Observation-Based Ground Segmentation and 3D Object Boundary Estimation

PubMed Central

Song, Wei; Cho, Kyungeun; Um, Kyhyun; Won, Chee Sun; Sim, Sungdae

2012-01-01

Mobile robot operators must make rapid decisions based on information about the robot’s surrounding environment. This means that terrain modeling and photorealistic visualization are required for the remote operation of mobile robots. We have produced a voxel map and textured mesh from the 2D and 3D datasets collected by a robot’s array of sensors, but some upper parts of objects are beyond the sensors’ measurements and these parts are missing in the terrain reconstruction result. This result is an incomplete terrain model. To solve this problem, we present a new ground segmentation method to detect non-ground data in the reconstructed voxel map. Our method uses height histograms to estimate the ground height range, and a Gibbs-Markov random field model to refine the segmentation results. To reconstruct a complete terrain model of the 3D environment, we develop a 3D boundary estimation method for non-ground objects. We apply a boundary detection technique to the 2D image, before estimating and refining the actual height values of the non-ground vertices in the reconstructed textured mesh. Our proposed methods were tested in an outdoor environment in which trees and buildings were not completely sensed. Our results show that the time required for ground segmentation is faster than that for data sensing, which is necessary for a real-time approach. In addition, those parts of objects that were not sensed are accurately recovered to retrieve their real-world appearances. PMID:23235454

Intuitive terrain reconstruction using height observation-based ground segmentation and 3D object boundary estimation.

PubMed

Song, Wei; Cho, Kyungeun; Um, Kyhyun; Won, Chee Sun; Sim, Sungdae

2012-12-12

Mobile robot operators must make rapid decisions based on information about the robot's surrounding environment. This means that terrain modeling and photorealistic visualization are required for the remote operation of mobile robots. We have produced a voxel map and textured mesh from the 2D and 3D datasets collected by a robot's array of sensors, but some upper parts of objects are beyond the sensors' measurements and these parts are missing in the terrain reconstruction result. This result is an incomplete terrain model. To solve this problem, we present a new ground segmentation method to detect non-ground data in the reconstructed voxel map. Our method uses height histograms to estimate the ground height range, and a Gibbs-Markov random field model to refine the segmentation results. To reconstruct a complete terrain model of the 3D environment, we develop a 3D boundary estimation method for non-ground objects. We apply a boundary detection technique to the 2D image, before estimating and refining the actual height values of the non-ground vertices in the reconstructed textured mesh. Our proposed methods were tested in an outdoor environment in which trees and buildings were not completely sensed. Our results show that the time required for ground segmentation is faster than that for data sensing, which is necessary for a real-time approach. In addition, those parts of objects that were not sensed are accurately recovered to retrieve their real-world appearances.

Seismic Design of a Single Bored Tunnel: Longitudinal Deformations and Seismic Joints

NASA Astrophysics Data System (ADS)

Oh, J.; Moon, T.

2018-03-01

The large diameter bored tunnel passing through rock and alluvial deposits subjected to seismic loading is analyzed for estimating longitudinal deformations and member forces on the segmental tunnel liners. The project site has challenges including high hydrostatic pressure, variable ground profile and high seismic loading. To ensure the safety of segmental tunnel liner from the seismic demands, the performance-based two-level design earthquake approach, Functional Evaluation Earthquake and Safety Evaluation Earthquake, has been adopted. The longitudinal tunnel and ground response seismic analyses are performed using a three-dimensional quasi-static linear elastic and nonlinear elastic discrete beam-spring elements to represent segmental liner and ground spring, respectively. Three components (longitudinal, transverse and vertical) of free-field ground displacement-time histories evaluated from site response analyses considering wave passage effects have been applied at the end support of the strain-compatible ground springs. The result of the longitudinal seismic analyses suggests that seismic joint for the mitigation measure requiring the design deflection capacity of 5-7.5 cm is to be furnished at the transition zone between hard and soft ground condition where the maximum member forces on the segmental liner (i.e., axial, shear forces and bending moments) are induced. The paper illustrates how detailed numerical analyses can be practically applied to evaluate the axial and curvature deformations along the tunnel alignment under difficult ground conditions and to provide the seismic joints at proper locations to effectively reduce the seismic demands below the allowable levels.

Fast Surface Reconstruction and Segmentation with Ground-Based and Airborne LIDAR Range Data

DTIC Science & Technology

2009-01-14

to perform a union find on the ground mesh vertices to calculate the sizes of ground mesh segments, 462 seconds to read the airborne data in to a...NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) University of...California at Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720 8. PERFORMING ORGANIZATION REPORT NUMBER 9

Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images

PubMed Central

Ji, Zexuan; Chen, Qiang; Niu, Sijie; Leng, Theodore; Rubin, Daniel L.

2018-01-01

Purpose To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation. Methods An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models. Results Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets. Conclusions Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. Translational Relevance Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD. PMID:29302382

Beyond Retinal Layers: A Deep Voting Model for Automated Geographic Atrophy Segmentation in SD-OCT Images.

PubMed

Ji, Zexuan; Chen, Qiang; Niu, Sijie; Leng, Theodore; Rubin, Daniel L

2018-01-01

To automatically and accurately segment geographic atrophy (GA) in spectral-domain optical coherence tomography (SD-OCT) images by constructing a voting system with deep neural networks without the use of retinal layer segmentation. An automatic GA segmentation method for SD-OCT images based on the deep network was constructed. The structure of the deep network was composed of five layers, including one input layer, three hidden layers, and one output layer. During the training phase, the labeled A-scans with 1024 features were directly fed into the network as the input layer to obtain the deep representations. Then a soft-max classifier was trained to determine the label of each individual pixel. Finally, a voting decision strategy was used to refine the segmentation results among 10 trained models. Two image data sets with GA were used to evaluate the model. For the first dataset, our algorithm obtained a mean overlap ratio (OR) 86.94% ± 8.75%, absolute area difference (AAD) 11.49% ± 11.50%, and correlation coefficients (CC) 0.9857; for the second dataset, the mean OR, AAD, and CC of the proposed method were 81.66% ± 10.93%, 8.30% ± 9.09%, and 0.9952, respectively. The proposed algorithm was capable of improving over 5% and 10% segmentation accuracy, respectively, when compared with several state-of-the-art algorithms on two data sets. Without retinal layer segmentation, the proposed algorithm could produce higher segmentation accuracy and was more stable when compared with state-of-the-art methods that relied on retinal layer segmentation results. Our model may provide reliable GA segmentations from SD-OCT images and be useful in the clinical diagnosis of advanced nonexudative AMD. Based on the deep neural networks, this study presents an accurate GA segmentation method for SD-OCT images without using any retinal layer segmentation results, and may contribute to improved understanding of advanced nonexudative AMD.

Shape-specific perceptual learning in a figure-ground segregation task.

PubMed

Yi, Do-Joon; Olson, Ingrid R; Chun, Marvin M

2006-03-01

What does perceptual experience contribute to figure-ground segregation? To study this question, we trained observers to search for symmetric dot patterns embedded in random dot backgrounds. Training improved shape segmentation, but learning did not completely transfer either to untrained locations or to untrained shapes. Such partial specificity persisted for a month after training. Interestingly, training on shapes in empty backgrounds did not help segmentation of the trained shapes in noisy backgrounds. Our results suggest that perceptual training increases the involvement of early sensory neurons in the segmentation of trained shapes, and that successful segmentation requires perceptual skills beyond shape recognition alone.

Estimation procedure of the efficiency of the heat network segment

NASA Astrophysics Data System (ADS)

Polivoda, F. A.; Sokolovskii, R. I.; Vladimirov, M. A.; Shcherbakov, V. P.; Shatrov, L. A.

2017-07-01

An extensive city heat network contains many segments, and each segment operates with different efficiency of heat energy transfer. This work proposes an original technical approach; it involves the evaluation of the energy efficiency function of the heat network segment and interpreting of two hyperbolic functions in the form of the transcendental equation. In point of fact, the problem of the efficiency change of the heat network depending on the ambient temperature was studied. Criteria dependences used for evaluation of the set segment efficiency of the heat network and finding of the parameters for the most optimal control of the heat supply process of the remote users were inferred with the help of the functional analysis methods. Generally, the efficiency function of the heat network segment is interpreted by the multidimensional surface, which allows illustrating it graphically. It was shown that the solution of the inverse problem is possible as well. Required consumption of the heating agent and its temperature may be found by the set segment efficient and ambient temperature; requirements to heat insulation and pipe diameters may be formulated as well. Calculation results were received in a strict analytical form, which allows investigating the found functional dependences for availability of the extremums (maximums) under the set external parameters. A conclusion was made that it is expedient to apply this calculation procedure in two practically important cases: for the already made (built) network, when the change of the heat agent consumption and temperatures in the pipe is only possible, and for the projecting (under construction) network, when introduction of changes into the material parameters of the network is possible. This procedure allows clarifying diameter and length of the pipes, types of insulation, etc. Length of the pipes may be considered as the independent parameter for calculations; optimization of this parameter is made in accordance with other, economical, criteria for the specific project.

Iterative deep convolutional encoder-decoder network for medical image segmentation.

PubMed

Jung Uk Kim; Hak Gu Kim; Yong Man Ro

2017-07-01

In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely localize the regions of interest (ROIs) including complex shapes or detailed textures of medical images in an iterative manner. The proposed iterative deep convolutional encoder-decoder network consists of two main paths: convolutional encoder path and convolutional decoder path with iterative learning. Experimental results show that the proposed iterative deep learning framework is able to yield excellent medical image segmentation performances for various medical images. The effectiveness of the proposed method has been proved by comparing with other state-of-the-art medical image segmentation methods.

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network.

PubMed

Cui, Shaoguo; Mao, Lei; Jiang, Jingfeng; Liu, Chang; Xiong, Shuyu

2018-01-01

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.

Spectral Skyline Separation: Extended Landmark Databases and Panoramic Imaging

PubMed Central

Differt, Dario; Möller, Ralf

2016-01-01

Evidence from behavioral experiments suggests that insects use the skyline as a cue for visual navigation. However, changes of lighting conditions, over hours, days or possibly seasons, significantly affect the appearance of the sky and ground objects. One possible solution to this problem is to extract the “skyline” by an illumination-invariant classification of the environment into two classes, ground objects and sky. In a previous study (Insect models of illumination-invariant skyline extraction from UV (ultraviolet) and green channels), we examined the idea of using two different color channels available for many insects (UV and green) to perform this segmentation. We found out that for suburban scenes in temperate zones, where the skyline is dominated by trees and artificial objects like houses, a “local” UV segmentation with adaptive thresholds applied to individual images leads to the most reliable classification. Furthermore, a “global” segmentation with fixed thresholds (trained on an image dataset recorded over several days) using UV-only information is only slightly worse compared to using both the UV and green channel. In this study, we address three issues: First, to enhance the limited range of environments covered by the dataset collected in the previous study, we gathered additional data samples of skylines consisting of minerals (stones, sand, earth) as ground objects. We could show that also for mineral-rich environments, UV-only segmentation achieves a quality comparable to multi-spectral (UV and green) segmentation. Second, we collected a wide variety of ground objects to examine their spectral characteristics under different lighting conditions. On the one hand, we found that the special case of diffusely-illuminated minerals increases the difficulty to reliably separate ground objects from the sky. On the other hand, the spectral characteristics of this collection of ground objects covers well with the data collected in the skyline databases, increasing, due to the increased variety of ground objects, the validity of our findings for novel environments. Third, we collected omnidirectional images, as often used for visual navigation tasks, of skylines using an UV-reflective hyperbolic mirror. We could show that “local” separation techniques can be adapted to the use of panoramic images by splitting the image into segments and finding individual thresholds for each segment. Contrarily, this is not possible for ‘global’ separation techniques. PMID:27690053

The network and transmission of based on the principle of laser multipoint communication

NASA Astrophysics Data System (ADS)

Fu, Qiang; Liu, Xianzhu; Jiang, Huilin; Hu, Yuan; Jiang, Lun

2014-11-01

Space laser communication is the perfectly choose to the earth integrated information backbone network in the future. This paper introduces the structure of the earth integrated information network that is a large capacity integrated high-speed broadband information network, a variety of communications platforms were densely interconnected together, such as the land, sea, air and deep air users or aircraft, the technologies of the intelligent high-speed processing, switching and routing were adopt. According to the principle of maximum effective comprehensive utilization of information resources, get accurately information, fast processing and efficient transmission through inter-satellite, satellite earth, sky and ground station and other links. Namely it will be a space-based, air-based and ground-based integrated information network. It will be started from the trends of laser communication. The current situation of laser multi-point communications were expounded, the transmission scheme of the dynamic multi-point between wireless laser communication n network has been carefully studied, a variety of laser communication network transmission schemes the corresponding characteristics and scope described in detail , described the optical multiplexer machine that based on the multiport form of communication is applied to relay backbone link; the optical multiplexer-based on the form of the segmentation receiver field of view is applied to small angle link, the optical multiplexer-based form of three concentric spheres structure is applied to short distances, motorized occasions, and the multi-point stitching structure based on the rotation paraboloid is applied to inter-satellite communications in detail. The multi-point laser communication terminal apparatus consist of the transmitting and receiving antenna, a relay optical system, the spectroscopic system, communication system and communication receiver transmitter system. The communication forms of optical multiplexer more than four goals or more, the ratio of received power and volume weight will be Obvious advantages, and can track multiple moving targets in flexible.It would to provide reference for the construction of earth integrated information networks.

Unsupervised segmentation with dynamical units.

PubMed

Rao, A Ravishankar; Cecchi, Guillermo A; Peck, Charles C; Kozloski, James R

2008-01-01

In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the components of each input object that most contribute to its classification. The network consists of amplitude-phase units that can synchronize their dynamics, so that separation is determined by the amplitude of units in an output layer, and segmentation by phase similarity between input and output layer units. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. Moreover, efficient segmentation can be achieved even when there is considerable superposition of the inputs. The network dynamics are derived from an objective function that rewards sparse coding in the generalized amplitude-phase variables. We argue that this objective function can provide a possible formal interpretation of the binding problem and that the implementation of the network architecture and dynamics is biologically plausible.

Detection of pseudosinusoidal epileptic seizure segments in the neonatal EEG by cascading a rule-based algorithm with a neural network.

PubMed

Karayiannis, Nicolaos B; Mukherjee, Amit; Glover, John R; Ktonas, Periklis Y; Frost, James D; Hrachovy, Richard A; Mizrahi, Eli M

2006-04-01

This paper presents an approach to detect epileptic seizure segments in the neonatal electroencephalogram (EEG) by characterizing the spectral features of the EEG waveform using a rule-based algorithm cascaded with a neural network. A rule-based algorithm screens out short segments of pseudosinusoidal EEG patterns as epileptic based on features in the power spectrum. The output of the rule-based algorithm is used to train and compare the performance of conventional feedforward neural networks and quantum neural networks. The results indicate that the trained neural networks, cascaded with the rule-based algorithm, improved the performance of the rule-based algorithm acting by itself. The evaluation of the proposed cascaded scheme for the detection of pseudosinusoidal seizure segments reveals its potential as a building block of the automated seizure detection system under development.

Strong motion seismology in Mexico

NASA Astrophysics Data System (ADS)

Singh, S. K.; Ordaz, M.

1993-02-01

Since 1985, digital accelerographs have been installed along a 500 km segment above the Mexican subduction zone, at some inland sites which form an attenuation line between the Guerrero seismic gap and Mexico City, and in the Valley of Mexico. These networks have recorded a few large earthquakes and many moderate and small earthquakes. Analysis of the data has permitted a significant advance in the understanding of source characteristics, wave propagation and attenuation, and site effects. This, in turn, has permitted reliable estimations of ground motions from future earthquakes. This paper presents a brief summary of some important results which are having a direct bearing on current earthquake engineering practice in Mexico.

Figure/Ground Segmentation via a Haptic Glance: Attributing Initial Finger Contacts to Objects or Their Supporting Surfaces.

PubMed

Pawluk, D; Kitada, R; Abramowicz, A; Hamilton, C; Lederman, S J

2011-01-01

The current study addresses the well-known "figure/ground" problem in human perception, a fundamental topic that has received surprisingly little attention from touch scientists to date. Our approach is grounded in, and directly guided by, current knowledge concerning the nature of haptic processing. Given inherent figure/ground ambiguity in natural scenes and limited sensory inputs from first contact (a "haptic glance"), we consider first whether people are even capable of differentiating figure from ground (Experiments 1 and 2). Participants were required to estimate the strength of their subjective impression that they were feeling an object (i.e., figure) as opposed to just the supporting structure (i.e., ground). Second, we propose a tripartite factor classification scheme to further assess the influence of kinetic, geometric (Experiments 1 and 2), and material (Experiment 2) factors on haptic figure/ground segmentation, complemented by more open-ended subjective responses obtained at the end of the experiment. Collectively, the results indicate that under certain conditions it is possible to segment figure from ground via a single haptic glance with a reasonable degree of certainty, and that all three factor classes influence the estimated likelihood that brief, spatially distributed fingertip contacts represent contact with an object and/or its background supporting structure.

Unsupervised sputum color image segmentation for lung cancer diagnosis based on a Hopfield neural network

NASA Astrophysics Data System (ADS)

Sammouda, Rachid; Niki, Noboru; Nishitani, Hiroshi; Nakamura, S.; Mori, Shinichiro

1997-04-01

The paper presents a method for automatic segmentation of sputum cells with color images, to develop an efficient algorithm for lung cancer diagnosis based on a Hopfield neural network. We formulate the segmentation problem as a minimization of an energy function constructed with two terms, the cost-term as a sum of squared errors, and the second term a temporary noise added to the network as an excitation to escape certain local minima with the result of being closer to the global minimum. To increase the accuracy in segmenting the regions of interest, a preclassification technique is used to extract the sputum cell regions within the color image and remove those of the debris cells. The former is then given with the raw image to the input of Hopfield neural network to make a crisp segmentation by assigning each pixel to label such as background, cytoplasm, and nucleus. The proposed technique has yielded correct segmentation of complex scene of sputum prepared by ordinary manual staining method in most of the tested images selected from our database containing thousands of sputum color images.

Non-Gimbaled Antenna Pointing: Summary of Results and Analysis

NASA Technical Reports Server (NTRS)

Horan, Stephen

1998-01-01

There is considerable interest at this time in developing small satellites for quick-turnaround missions to investigate near-earth phenomena from space. One problem to be solved in mission planning is the means of communication between the control infrastructure in the ground segment and the satellite in the space segment. A nominal small-satellite mission design often includes an omni-directional or similar wide-pattern antenna on the satellite and a dedicated ground station for telemetry, tracking, and command support. These terminals typically provide up to 15 minutes of coverage during an orbit that is within the visibility of the ground station; however, not all orbits will pass over the ground station so that coverage gaps will exist in the data flow. To overcome this general limitation on data transmission for low-earth orbiting satellites, the Space Network (SN), operated by the National Aeronautics and Space Administration, (NASA) has been designed to transmit data to and from user satellites through the Tracking and Data Relay Satellites (TDRS) in geostationary orbit and interfacing to the White Sands Complex (WSC) in New Mexico for the data's ground entry point. The advantage of the SN over a fixed ground station is that all low-earth-satellite orbits will be within the visibility area of at least one TDRS within the SN for a large part of the orbit and the potential exists to establish a communications link if the user satellite can point an antenna in the direction of any one of the relay satellites. Within NASA, there is considerable interest in seeing that small satellite developers are aware of the advantages to the SN and that designs to include the SN are part of the satellite design. Small satellite users have not often considered using the SN because of: (1) The 26-dB link penalty differential between direct broadcast to a ground station and transmission through a TDRS to the ground; (2) The class of satellite is too small to support high-gain antennas and associated attitude control and drive electronics; (3) The class of satellites is severely weight and power limited; (4) There are perceived problems in scheduling communications for this class of user on the SN. This report addresses the potential for SN access using non-gimbaled, i.e. fixed-pointed, antennas in the design of the small satellite using modest transmission power to achieve the necessary space-to-ground transmissions. The advantage of using the SN is in the reduction of mission costs arising from using the SN infrastructure instead of a dedicated, proprietary ground station using a similar type of communications package. From the simulations and analysis presented, we will show that a modest satellite configuration can be used with the space network to achieve the data transmission goals of a number of users and thereby rival the performance achieved with proprietary ground stations. In this study, we will concentrate on the return data link (from the user satellite through a TDRS to the ground data entry point). The forward command link (from the ground data entry point through a TDRS to the user satellite) will usually be a lower data rate service and the data volume will also be considerably lower than the return link's requirement. Therefore, we assume that if the return link requirements are satisfied, then the forward link requirements can also be satisfied.

Development of a Subject-Specific Foot-Ground Contact Model for Walking.

PubMed

Jackson, Jennifer N; Hass, Chris J; Fregly, Benjamin J

2016-09-01

Computational walking simulations could facilitate the development of improved treatments for clinical conditions affecting walking ability. Since an effective treatment is likely to change a patient's foot-ground contact pattern and timing, such simulations should ideally utilize deformable foot-ground contact models tailored to the patient's foot anatomy and footwear. However, no study has reported a deformable modeling approach that can reproduce all six ground reaction quantities (expressed as three reaction force components, two center of pressure (CoP) coordinates, and a free reaction moment) for an individual subject during walking. This study proposes such an approach for use in predictive optimizations of walking. To minimize complexity, we modeled each foot as two rigid segments-a hindfoot (HF) segment and a forefoot (FF) segment-connected by a pin joint representing the toes flexion-extension axis. Ground reaction forces (GRFs) and moments acting on each segment were generated by a grid of linear springs with nonlinear damping and Coulomb friction spread across the bottom of each segment. The stiffness and damping of each spring and common friction parameter values for all springs were calibrated for both feet simultaneously via a novel three-stage optimization process that used motion capture and ground reaction data collected from a single walking trial. The sequential three-stage process involved matching (1) the vertical force component, (2) all three force components, and finally (3) all six ground reaction quantities. The calibrated model was tested using four additional walking trials excluded from calibration. With only small changes in input kinematics, the calibrated model reproduced all six ground reaction quantities closely (root mean square (RMS) errors less than 13 N for all three forces, 25 mm for anterior-posterior (AP) CoP, 8 mm for medial-lateral (ML) CoP, and 2 N·m for the free moment) for both feet in all walking trials. The largest errors in AP CoP occurred at the beginning and end of stance phase when the vertical ground reaction force (vGRF) was small. Subject-specific deformable foot-ground contact models created using this approach should enable changes in foot-ground contact pattern to be predicted accurately by gait optimization studies, which may lead to improvements in personalized rehabilitation medicine.

Automated detection of videotaped neonatal seizures of epileptic origin.

PubMed

Karayiannis, Nicolaos B; Xiong, Yaohua; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-06-01

This study aimed at the development of a seizure-detection system by training neural networks with quantitative motion information extracted from short video segments of neonatal seizures of the myoclonic and focal clonic types and random infant movements. The motion of the infants' body parts was quantified by temporal motion-strength signals extracted from video segments by motion-segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The motion of the infants' body parts also was quantified by temporal motion-trajectory signals extracted from video recordings by robust motion trackers based on block-motion models. These motion trackers were developed to adjust autonomously to illumination and contrast changes that may occur during the video-frame sequence. Video segments were represented by quantitative features obtained by analyzing motion-strength and motion-trajectory signals in both the time and frequency domains. Seizure recognition was performed by conventional feed-forward neural networks, quantum neural networks, and cosine radial basis function neural networks, which were trained to detect neonatal seizures of the myoclonic and focal clonic types and to distinguish them from random infant movements. The computational tools and procedures developed for automated seizure detection were evaluated on a set of 240 video segments of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). Regardless of the decision scheme used for interpreting the responses of the trained neural networks, all the neural network models exhibited sensitivity and specificity>90%. For one of the decision schemes proposed for interpreting the responses of the trained neural networks, the majority of the trained neural-network models exhibited sensitivity>90% and specificity>95%. In particular, cosine radial basis function neural networks achieved the performance targets of this phase of the project (i.e., sensitivity>95% and specificity>95%). The best among the motion segmentation and tracking methods developed in this study produced quantitative features that constitute a reliable basis for detecting neonatal seizures. The performance targets of this phase of the project were achieved by combining the quantitative features obtained by analyzing motion-strength signals with those produced by analyzing motion-trajectory signals. The computational procedures and tools developed in this study to perform off-line analysis of short video segments will be used in the next phase of this project, which involves the integration of these procedures and tools into a system that can process and analyze long video recordings of infants monitored for seizures in real time.

The algorithm study for using the back propagation neural network in CT image segmentation

NASA Astrophysics Data System (ADS)

Zhang, Peng; Liu, Jie; Chen, Chen; Li, Ying Qi

2017-01-01

Back propagation neural network(BP neural network) is a type of multi-layer feed forward network which spread positively, while the error spread backwardly. Since BP network has advantages in learning and storing the mapping between a large number of input and output layers without complex mathematical equations to describe the mapping relationship, it is most widely used. BP can iteratively compute the weight coefficients and thresholds of the network based on the training and back propagation of samples, which can minimize the error sum of squares of the network. Since the boundary of the computed tomography (CT) heart images is usually discontinuous, and it exist large changes in the volume and boundary of heart images, The conventional segmentation such as region growing and watershed algorithm can't achieve satisfactory results. Meanwhile, there are large differences between the diastolic and systolic images. The conventional methods can't accurately classify the two cases. In this paper, we introduced BP to handle the segmentation of heart images. We segmented a large amount of CT images artificially to obtain the samples, and the BP network was trained based on these samples. To acquire the appropriate BP network for the segmentation of heart images, we normalized the heart images, and extract the gray-level information of the heart. Then the boundary of the images was input into the network to compare the differences between the theoretical output and the actual output, and we reinput the errors into the BP network to modify the weight coefficients of layers. Through a large amount of training, the BP network tend to be stable, and the weight coefficients of layers can be determined, which means the relationship between the CT images and the boundary of heart.

Image segmentation using fuzzy LVQ clustering networks

NASA Technical Reports Server (NTRS)

Tsao, Eric Chen-Kuo; Bezdek, James C.; Pal, Nikhil R.

1992-01-01

In this note we formulate image segmentation as a clustering problem. Feature vectors extracted from a raw image are clustered into subregions, thereby segmenting the image. A fuzzy generalization of a Kohonen learning vector quantization (LVQ) which integrates the Fuzzy c-Means (FCM) model with the learning rate and updating strategies of the LVQ is used for this task. This network, which segments images in an unsupervised manner, is thus related to the FCM optimization problem. Numerical examples on photographic and magnetic resonance images are given to illustrate this approach to image segmentation.

Research on trust calculation of wireless sensor networks based on time segmentation

NASA Astrophysics Data System (ADS)

Su, Yaoxin; Gao, Xiufeng; Qiao, Wenxin

2017-05-01

Because the wireless sensor network is different from the traditional network characteristics, it is easy to accept the intrusion from the compromise node. The trust mechanism is the most effective way to defend against internal attacks. Aiming at the shortcomings of the existing trust mechanism, a method of calculating the trust of wireless sensor networks based on time segmentation is proposed. It improves the security of the network and extends the life of the network

CT correlation with outcomes in 15 patients with acute Middle East respiratory syndrome coronavirus.

PubMed

Das, Karuna M; Lee, Edward Y; Enani, Mushira A; AlJawder, Suhaila E; Singh, Rajvir; Bashir, Salman; Al-Nakshbandi, Nizar; AlDossari, Khalid; Larsson, Sven G

2015-04-01

The purpose of this article is to retrospectively analyze chest CT findings for 15 patients with Middle East respiratory syndrome coronavirus and to identify features associated with survival. Patients were assigned to group 1 if they died (n=9) and to group 2 if they made a full recovery (n=6). Two reviewers scored chest radiographs and CT examinations for segmental involvement, ground-glass opacities, consolidation, and interstitial thickening. Eight patients had ground-glass opacity (53%), five had ground-glass and consolidation in combination (33%), five had pleural effusion (33%), and four patients had interlobular thickening (27%). Of 281 CT findings, 151 (54%) were peripheral, 68 (24%) were central, and 62 (22%) had a mixed location. The number of involved lung segments was higher in group 1. The lower lobe was more commonly involved (mean, 12.2 segments) than in the upper and middle lobes combined (mean, 6.3 segments). The mean number of lung segments involved was 12.3 segments in group 1 and 3.4 segments in group 2. The CT lung score (mean±SD, 15.78±7.9 vs 7.3±5.7, p=0.003), chest radiographic score (20.8±1.7 vs 5.6±5.4; p=0.001), and mechanical ventilation duration (13.11±8.3 vs 0.5±1.2 days; p=0.002) were higher in group 1. All nine group 1 patients and three of six group 2 patients had pleural effusion (p=0.52). CT of patients with Middle East respiratory syndrome coronavirus predominantly showed ground-glass opacities, with peripheral lower lobe preference. Pleural effusion and higher CT lung and chest radiographic scores correlate with poor prognosis and short-term mortality.

Modeling cytoskeletal traffic: an interplay between passive diffusion and active transport.

PubMed

Neri, Izaak; Kern, Norbert; Parmeggiani, Andrea

2013-03-01

We introduce the totally asymmetric simple exclusion process with Langmuir kinetics on a network as a microscopic model for active motor protein transport on the cytoskeleton, immersed in the diffusive cytoplasm. We discuss how the interplay between active transport along a network and infinite diffusion in a bulk reservoir leads to a heterogeneous matter distribution on various scales: we find three regimes for steady state transport, corresponding to the scale of the network, of individual segments, or local to sites. At low exchange rates strong density heterogeneities develop between different segments in the network. In this regime one has to consider the topological complexity of the whole network to describe transport. In contrast, at moderate exchange rates the transport through the network decouples, and the physics is determined by single segments and the local topology. At last, for very high exchange rates the homogeneous Langmuir process dominates the stationary state. We introduce effective rate diagrams for the network to identify these different regimes. Based on this method we develop an intuitive but generic picture of how the stationary state of excluded volume processes on complex networks can be understood in terms of the single-segment phase diagram.

A European mobile satellite system concept exploiting CDMA and OBP

NASA Technical Reports Server (NTRS)

Vernucci, A.; Craig, A. D.

1993-01-01

This paper describes a novel Land Mobile Satellite System (LMSS) concept applicable to networks allowing access to a large number of gateway stations ('Hubs'), utilizing low-cost Very Small Aperture Terminals (VSAT's). Efficient operation of the Forward-Link (FL) repeater can be achieved by adopting a synchronous Code Division Multiple Access (CDMA) technique, whereby inter-code interference (self-noise) is virtually eliminated by synchronizing orthogonal codes. However, with a transparent FL repeater, the requirements imposed by the highly decentralized ground segment can lead to significant efficiency losses. The adoption of a FL On-Board Processing (OBP) repeater is proposed as a means of largely recovering this efficiency impairment. The paper describes the network architecture, the system design and performance, the OBP functions and impact on implementation. The proposed concept, applicable to a future generation of the European LMSS, was developed in the context of a European Space Agency (ESA) study contract.

Evaluation metrics for bone segmentation in ultrasound

NASA Astrophysics Data System (ADS)

Lougheed, Matthew; Fichtinger, Gabor; Ungi, Tamas

2015-03-01

Tracked ultrasound is a safe alternative to X-ray for imaging bones. The interpretation of bony structures is challenging as ultrasound has no specific intensity characteristic of bones. Several image segmentation algorithms have been devised to identify bony structures. We propose an open-source framework that would aid in the development and comparison of such algorithms by quantitatively measuring segmentation performance in the ultrasound images. True-positive and false-negative metrics used in the framework quantify algorithm performance based on correctly segmented bone and correctly segmented boneless regions. Ground-truth for these metrics are defined manually and along with the corresponding automatically segmented image are used for the performance analysis. Manually created ground truth tests were generated to verify the accuracy of the analysis. Further evaluation metrics for determining average performance per slide and standard deviation are considered. The metrics provide a means of evaluating accuracy of frames along the length of a volume. This would aid in assessing the accuracy of the volume itself and the approach to image acquisition (positioning and frequency of frame). The framework was implemented as an open-source module of the 3D Slicer platform. The ground truth tests verified that the framework correctly calculates the implemented metrics. The developed framework provides a convenient way to evaluate bone segmentation algorithms. The implementation fits in a widely used application for segmentation algorithm prototyping. Future algorithm development will benefit by monitoring the effects of adjustments to an algorithm in a standard evaluation framework.

NASA's mobile satellite communications program; ground and space segment technologies

NASA Technical Reports Server (NTRS)

Naderi, F.; Weber, W. J.; Knouse, G. H.

1984-01-01

This paper describes the Mobile Satellite Communications Program of the United States National Aeronautics and Space Administration (NASA). The program's objectives are to facilitate the deployment of the first generation commercial mobile satellite by the private sector, and to technologically enable future generations by developing advanced and high risk ground and space segment technologies. These technologies are aimed at mitigating severe shortages of spectrum, orbital slot, and spacecraft EIRP which are expected to plague the high capacity mobile satellite systems of the future. After a brief introduction of the concept of mobile satellite systems and their expected evolution, this paper outlines the critical ground and space segment technologies. Next, the Mobile Satellite Experiment (MSAT-X) is described. MSAT-X is the framework through which NASA will develop advanced ground segment technologies. An approach is outlined for the development of conformal vehicle antennas, spectrum and power-efficient speech codecs, and modulation techniques for use in the non-linear faded channels and efficient multiple access schemes. Finally, the paper concludes with a description of the current and planned NASA activities aimed at developing complex large multibeam spacecraft antennas needed for future generation mobile satellite systems.

A sensitivity analysis method for the body segment inertial parameters based on ground reaction and joint moment regressor matrices.

PubMed

Futamure, Sumire; Bonnet, Vincent; Dumas, Raphael; Venture, Gentiane

2017-11-07

This paper presents a method allowing a simple and efficient sensitivity analysis of dynamics parameters of complex whole-body human model. The proposed method is based on the ground reaction and joint moment regressor matrices, developed initially in robotics system identification theory, and involved in the equations of motion of the human body. The regressor matrices are linear relatively to the segment inertial parameters allowing us to use simple sensitivity analysis methods. The sensitivity analysis method was applied over gait dynamics and kinematics data of nine subjects and with a 15 segments 3D model of the locomotor apparatus. According to the proposed sensitivity indices, 76 segments inertial parameters out the 150 of the mechanical model were considered as not influent for gait. The main findings were that the segment masses were influent and that, at the exception of the trunk, moment of inertia were not influent for the computation of the ground reaction forces and moments and the joint moments. The same method also shows numerically that at least 90% of the lower-limb joint moments during the stance phase can be estimated only from a force-plate and kinematics data without knowing any of the segment inertial parameters. Copyright © 2017 Elsevier Ltd. All rights reserved.

Figure-Ground Segmentation Using Factor Graphs

PubMed Central

Shen, Huiying; Coughlan, James; Ivanchenko, Volodymyr

2009-01-01

Foreground-background segmentation has recently been applied [26,12] to the detection and segmentation of specific objects or structures of interest from the background as an efficient alternative to techniques such as deformable templates [27]. We introduce a graphical model (i.e. Markov random field)-based formulation of structure-specific figure-ground segmentation based on simple geometric features extracted from an image, such as local configurations of linear features, that are characteristic of the desired figure structure. Our formulation is novel in that it is based on factor graphs, which are graphical models that encode interactions among arbitrary numbers of random variables. The ability of factor graphs to express interactions higher than pairwise order (the highest order encountered in most graphical models used in computer vision) is useful for modeling a variety of pattern recognition problems. In particular, we show how this property makes factor graphs a natural framework for performing grouping and segmentation, and demonstrate that the factor graph framework emerges naturally from a simple maximum entropy model of figure-ground segmentation. We cast our approach in a learning framework, in which the contributions of multiple grouping cues are learned from training data, and apply our framework to the problem of finding printed text in natural scenes. Experimental results are described, including a performance analysis that demonstrates the feasibility of the approach. PMID:20160994

Using simulated fluorescence cell micrographs for the evaluation of cell image segmentation algorithms.

PubMed

Wiesmann, Veit; Bergler, Matthias; Palmisano, Ralf; Prinzen, Martin; Franz, Daniela; Wittenberg, Thomas

2017-03-18

Manual assessment and evaluation of fluorescent micrograph cell experiments is time-consuming and tedious. Automated segmentation pipelines can ensure efficient and reproducible evaluation and analysis with constant high quality for all images of an experiment. Such cell segmentation approaches are usually validated and rated in comparison to manually annotated micrographs. Nevertheless, manual annotations are prone to errors and display inter- and intra-observer variability which influence the validation results of automated cell segmentation pipelines. We present a new approach to simulate fluorescent cell micrographs that provides an objective ground truth for the validation of cell segmentation methods. The cell simulation was evaluated twofold: (1) An expert observer study shows that the proposed approach generates realistic fluorescent cell micrograph simulations. (2) An automated segmentation pipeline on the simulated fluorescent cell micrographs reproduces segmentation performances of that pipeline on real fluorescent cell micrographs. The proposed simulation approach produces realistic fluorescent cell micrographs with corresponding ground truth. The simulated data is suited to evaluate image segmentation pipelines more efficiently and reproducibly than it is possible on manually annotated real micrographs.

A region-based segmentation of tumour from brain CT images using nonlinear support vector machine classifier.

PubMed

Nanthagopal, A Padma; Rajamony, R Sukanesh

2012-07-01

The proposed system provides new textural information for segmenting tumours, efficiently and accurately and with less computational time, from benign and malignant tumour images, especially in smaller dimensions of tumour regions of computed tomography (CT) images. Region-based segmentation of tumour from brain CT image data is an important but time-consuming task performed manually by medical experts. The objective of this work is to segment brain tumour from CT images using combined grey and texture features with new edge features and nonlinear support vector machine (SVM) classifier. The selected optimal features are used to model and train the nonlinear SVM classifier to segment the tumour from computed tomography images and the segmentation accuracies are evaluated for each slice of the tumour image. The method is applied on real data of 80 benign, malignant tumour images. The results are compared with the radiologist labelled ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and the overlap similarity measure dice metric. From the analysis and performance measures such as segmentation accuracy and dice metric, it is inferred that better segmentation accuracy and higher dice metric are achieved with the normalized cut segmentation method than with the fuzzy c-means clustering method.

Structures associated with strike-slip faults that bound landslide elements

USGS Publications Warehouse

Fleming, R.W.; Johnson, A.M.

1989-01-01

Large landslides are bounded on their flanks and on elements within the landslides by structures analogous to strike-slip faults. We observed the formation of thwse strike-slip faults and associated structures at two large landslides in central Utah during 1983-1985. The strike-slip faults in landslides are nearly vertical but locally may dip a few degrees toward or away from the moving ground. Fault surfaces are slickensided, and striations are subparallel to the ground surface. Displacement along strike-slip faults commonly produces scarps; scarps occur where local relief of the failure surface or ground surface is displaced and becomes adjacent to higher or lower ground, or where the landslide is thickening or thinning as a result of internal deformation. Several types of structures are formed at the ground surface as a strike-slip fault, which is fully developed at some depth below the ground surface, propagates upward in response to displacement. The simplest structure is a tension crack oriented at 45?? clockwise or counterclockwise from the trend of an underlying right- or left-lateral strike-slip fault, respectively. The tension cracks are typically arranged en echelon with the row of cracks parallel to the trace of the underlying strike-slip fault. Another common structure that forms above a developing strike-slip fault is a fault segment. Fault segments are discontinuous strike-slip faults that contain the same sense of slip but are turned clockwise or counterclockwise from a few to perhaps 20?? from the underlying strike-slip fault. The fault segments are slickensided and striated a few centimeters below the ground surface; continued displacement of the landslide causes the fault segments to open and a short tension crack propagates out of one or both ends of the fault segments. These structures, open fault segments containing a short tension crack, are termed compound cracks; and the short tension crack that propagates from the tip of the fault segment is typically oriented 45?? to the trend of the underlying fault. Fault segments are also typically arranged en echelon above the upward-propagating strike-slip fault. Continued displacement of the landslide causes the ground to buckle between the tension crack portions of the compound cracks. Still more displacement produces a thrust fault on one or both limbs of the buckle fold. These compressional structures form at right angles to the short tension cracks at the tips of the fault segments. Thus, the compressional structures are bounded on their ends by one face of a tension crack and detached from underlying material by thrusting or buckling. The tension cracks, fault segments, compound cracks, folds, and thrusts are ephemeral; they are created and destroyed with continuing displacement of the landslide. Ultimately, the structures are replaced by a throughgoing strike-slip fault. At one landslide, we observed the creation and destruction of the ephemeral structures as the landslide enlarged. Displacement of a few centimeters to about a decimeter was sufficient to produce scattered tension cracks and fault segments. Sets of compound cracks with associated folds and thrusts were produced by displacements of up to 1 m, and 1 to 2 m of displacement was required to produce a throughgoing strike-slip fault. The type of first-formed structure above an upward-propagating strike-slip fault is apparently controlled by the rheology of the material. Brittle material such as dry topsoil or the compact surface of a gravel road produces echelon tension cracks and sets of tension cracks and compressional structures, wherein the cracks and compressional structures are normal to each other and 45?? to the strike-slip fault at depth. First-formed structures in more ductile material such as moist cohesive soil are fault segments. In very ductile material such as soft clay and very wet soil in swampy areas, the first-formed structure is a throughgoing strike-slip fault. There are othe

Brain tumor classification and segmentation using sparse coding and dictionary learning.

PubMed

Salman Al-Shaikhli, Saif Dawood; Yang, Michael Ying; Rosenhahn, Bodo

2016-08-01

This paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

Influence of the segmentation on the characterization of cerebral networks of structural damage for patients with disorders of consciousness

NASA Astrophysics Data System (ADS)

Martínez, Darwin; Mahalingam, Jamuna J.; Soddu, Andrea; Franco, Hugo; Lepore, Natasha; Laureys, Steven; Gómez, Francisco

2015-01-01

Disorders of consciousness (DOC) are a consequence of a variety of severe brain injuries. DOC commonly results in anatomical brain modifications, which can affect cortical and sub-cortical brain structures. Postmortem studies suggest that severity of brain damage correlates with level of impairment in DOC. In-vivo studies in neuroimaging mainly focus in alterations on single structures. Recent evidence suggests that rather than one, multiple brain regions can be simultaneously affected by this condition. In other words, DOC may be linked to an underlying cerebral network of structural damage. Recently, geometrical spatial relationships among key sub-cortical brain regions, such as left and right thalamus and brain stem, have been used for the characterization of this network. This approach is strongly supported on automatic segmentation processes, which aim to extract regions of interests without human intervention. Nevertheless, patients with DOC usually present massive structural brain changes. Therefore, segmentation methods may highly influence the characterization of the underlying cerebral network structure. In this work, we evaluate the level of characterization obtained by using the spatial relationships as descriptor of a sub-cortical cerebral network (left and right thalamus) in patients with DOC, when different segmentation approaches are used (FSL, Free-surfer and manual segmentation). Our results suggest that segmentation process may play a critical role for the construction of robust and reliable structural characterization of DOC conditions.

Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

PubMed Central

Mao, Lei; Liu, Chang; Xiong, Shuyu

2018-01-01

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice. PMID:29755716

Determination of Exterior Orientation Parameters Through Direct Geo-Referencing in a Real-Time Aerial Monitoring System

NASA Astrophysics Data System (ADS)

Kim, H.; Lee, J.; Choi, K.; Lee, I.

2012-07-01

Rapid responses for emergency situations such as natural disasters or accidents often require geo-spatial information describing the on-going status of the affected area. Such geo-spatial information can be promptly acquired by a manned or unmanned aerial vehicle based multi-sensor system that can monitor the emergent situations in near real-time from the air using several kinds of sensors. Thus, we are in progress of developing such a real-time aerial monitoring system (RAMS) consisting of both aerial and ground segments. The aerial segment acquires the sensory data about the target areas by a low-altitude helicopter system equipped with sensors such as a digital camera and a GPS/IMU system and transmits them to the ground segment through a RF link in real-time. The ground segment, which is a deployable ground station installed on a truck, receives the sensory data and rapidly processes them to generate ortho-images, DEMs, etc. In order to generate geo-spatial information, in this system, exterior orientation parameters (EOP) of the acquired images are obtained through direct geo-referencing because it is difficult to acquire coordinates of ground points in disaster area. The main process, since the data acquisition stage until the measurement of EOP, is discussed as follows. First, at the time of data acquisition, image acquisition time synchronized by GPS time is recorded as part of image file name. Second, the acquired data are then transmitted to the ground segment in real-time. Third, by processing software for ground segment, positions/attitudes of acquired images are calculated through a linear interpolation using the GPS time of the received position/attitude data and images. Finally, the EOPs of images are obtained from position/attitude data by deriving the relationships between a camera coordinate system and a GPS/IMU coordinate system. In this study, we evaluated the accuracy of the EOP decided by direct geo-referencing in our system. To perform this, we used the precisely calculated EOP through the digital photogrammetry workstation (DPW) as reference data. The results of the evaluation indicate that the accuracy of the EOP acquired by our system is reasonable in comparison with the performance of GPS/IMU system. Also our system can acquire precise multi-sensory data to generate the geo-spatial information in emergency situations. In the near future, we plan to complete the development of the rapid generation system of the ground segment. Our system is expected to be able to acquire the ortho-image and DEM on the damaged area in near real-time. Its performance along with the accuracy of the generated geo-spatial information will also be evaluated and reported in the future work.

A Pulse Coupled Neural Network Segmentation Algorithm for Reflectance Confocal Images of Epithelial Tissue

PubMed Central

Malik, Bilal H.; Jabbour, Joey M.; Maitland, Kristen C.

2015-01-01

Automatic segmentation of nuclei in reflectance confocal microscopy images is critical for visualization and rapid quantification of nuclear-to-cytoplasmic ratio, a useful indicator of epithelial precancer. Reflectance confocal microscopy can provide three-dimensional imaging of epithelial tissue in vivo with sub-cellular resolution. Changes in nuclear density or nuclear-to-cytoplasmic ratio as a function of depth obtained from confocal images can be used to determine the presence or stage of epithelial cancers. However, low nuclear to background contrast, low resolution at greater imaging depths, and significant variation in reflectance signal of nuclei complicate segmentation required for quantification of nuclear-to-cytoplasmic ratio. Here, we present an automated segmentation method to segment nuclei in reflectance confocal images using a pulse coupled neural network algorithm, specifically a spiking cortical model, and an artificial neural network classifier. The segmentation algorithm was applied to an image model of nuclei with varying nuclear to background contrast. Greater than 90% of simulated nuclei were detected for contrast of 2.0 or greater. Confocal images of porcine and human oral mucosa were used to evaluate application to epithelial tissue. Segmentation accuracy was assessed using manual segmentation of nuclei as the gold standard. PMID:25816131

Fault geometry of 2015, Mw7.2 Murghab, Tajikistan earthquake controls rupture propagation: Insights from InSAR and seismological data

NASA Astrophysics Data System (ADS)

Sangha, Simran; Peltzer, Gilles; Zhang, Ailin; Meng, Lingsen; Liang, Cunren; Lundgren, Paul; Fielding, Eric

2017-03-01

Combining space-based geodetic and array seismology observations can provide detailed information about earthquake ruptures in remote regions. Here we use Landsat-8 imagery and ALOS-2 and Sentinel-1 radar interferometry data combined with data from the European seismology network to describe the source of the December 7, 2015, Mw7.2 Murghab (Tajikistan) earthquake. The earthquake reactivated a ∼79 km-long section of the Sarez-Karakul Fault, a NE oriented sinistral, trans-tensional fault in northern Pamir. Pixel offset data delineate the geometry of the surface break and line of sight ground shifts from two descending and three ascending interferograms constrain the fault dip and slip solution. Two right-stepping, NE-striking segments connected by a more easterly oriented segment, sub-vertical or steeply dipping to the west were involved. The solution shows two main patches of slip with up to 3.5 m of left lateral slip on the southern and central fault segments. The northern segment has a left-lateral and normal oblique slip of up to a meter. Back-projection of high-frequency seismic waves recorded by the European network, processed using the Multitaper-MUSIC approach, focuses sharply along the surface break. The time progression of the high-frequency radiators shows that, after a 10 second initiation phase at slow speed, the rupture progresses in 2 phases at super-shear velocity (∼4.3-5 km/s) separated by a 3 second interval of slower propagation corresponding to the passage through the restraining bend. The intensity of the high-frequency radiation reaches maxima during the initial and middle phases of slow propagation and is reduced by ∼50% during the super-shear phases of the propagation. These findings are consistent with studies of other strike-slip earthquakes in continental domain, showing the importance of fault geometric complexities in controlling the speed of fault propagation and related spatiotemporal pattern of the high-frequency radiation.

Broadband Internet Based Service to Passengers and Crew On-board Aircraft

NASA Astrophysics Data System (ADS)

Azzarelli, Tony

2003-07-01

The Connexion by BoeingSM (CbB) global network will provide broadband information services to aircraft passengers and crews. Through this Ku-band (14 GHz (uplink) and 11/12 GHz (downlink)) satellite-based system, aircraft passengers and crew will no longer be limited to pre-packaged services, but instead will be able to access the full range of broadband services from their seats using their laptop, PDA or the on-board IFE console.The kind of services offered to passengers are based on the internet/intranet access via their own laptops and PDA (using Ethernet wired cable, or wireless 802.11b access), while those offered to the crew can range between various crew application (such as weather updates and travel information) and aircraft health monitoring.The CbB system is divided into four basic layers of infrastructure:(1) an airborne segment, i.e. the Aircraft Earth Station (AES) consisting of proprietary high gain antenna, transceivers and other on-board subsystems providing a nominal return link data rate of 1 Mbps and a forward link data rates up to 20 Mbps;(2) a space segment consisting of leased satellite transponders on existing in-orbit Geostationary satellites;(3) a ground segment consisting of one or more leased satellite land earth stations (LESs) and redundant interconnection facilities; and;(4) a network operations centre (NOC) segment.During 2003, trials with Lufthansa (DLH) and British Airways (BA) have proved very successful. This has resulted in the recent signing of an agreement with Lufthansa which calls for the Connexion by BoeingSM service to be installed on Lufthansa's fleet of approximately 80 long-haul aircraft, including Boeing 747-400 and Airbus A330 and A340 aircraft, beginning in early 2004. BA is expected to follow soon. In addition to the successful recent service demonstrations, both Japan Airlines (JAL) and Scandinavian Airlines System (SAS) have announced their intent to install the revolutionary service on their long-range aircraft.

An overview of the thematic mapper geometric correction system

NASA Technical Reports Server (NTRS)

Beyer, E. P.

1983-01-01

Geometric accuracy specifications for LANDSAT 4 are reviewed and the processing concepts which form the basis of NASA's thematic mapper geometric correction system are summarized for both the flight and ground segments. The flight segment includes the thematic mapper instrument, attitude measurement devices, attitude control, and ephemeris processing. For geometric correction the ground segment uses mirror scan correction data, payload correction data, and control point information to determine where TM detector samples fall on output map projection systems. Then the raw imagery is reformatted and resampled to produce image samples on a selected output projection grid system.

Digital Terrain from a Two-Step Segmentation and Outlier-Based Algorithm

NASA Astrophysics Data System (ADS)

Hingee, Kassel; Caccetta, Peter; Caccetta, Louis; Wu, Xiaoliang; Devereaux, Drew

2016-06-01

We present a novel ground filter for remotely sensed height data. Our filter has two phases: the first phase segments the DSM with a slope threshold and uses gradient direction to identify candidate ground segments; the second phase fits surfaces to the candidate ground points and removes outliers. Digital terrain is obtained by a surface fit to the final set of ground points. We tested the new algorithm on digital surface models (DSMs) for a 9600km2 region around Perth, Australia. This region contains a large mix of land uses (urban, grassland, native forest and plantation forest) and includes both a sandy coastal plain and a hillier region (elevations up to 0.5km). The DSMs are captured annually at 0.2m resolution using aerial stereo photography, resulting in 1.2TB of input data per annum. Overall accuracy of the filter was estimated to be 89.6% and on a small semi-rural subset our algorithm was found to have 40% fewer errors compared to Inpho's Match-T algorithm.

Mathematical Inversion of Lightning Data: Techniques and Applications

NASA Technical Reports Server (NTRS)

Koshak, William

2003-01-01

A survey of some interesting mathematical inversion studies dealing with radio, optical, and electrostatic measurements of lightning are presented. A discussion of why NASA is interested in lightning, what specific physical properties of lightning are retrieved, and what mathematical techniques are used to perform the retrievals are discussed. In particular, a relatively new multi-station VHF time-of-arrival (TOA) antenna network is now on-line in Northern Alabama and will be discussed. The network, called the Lightning Mapping Array (LMA), employs GPS timing and detects VHF radiation from discrete segments (effectively point emitters) that comprise the channel of lightning strokes within cloud and ground flashes. The LMA supports on-going ground-validation activities of the low Earth orbiting Lightning Imaging Sensor (LIS) satellite developed at NASA Marshall Space Flight Center (MSFC) in Huntsville, Alabama. The LMA also provides detailed studies of the distribution and evolution of thunderstorms and lightning in the Tennessee Valley, and offers interesting comparisons with other meteorological/geophysical datasets. In order to take full advantage of these benefits, it is essential that the LMA channel mapping accuracy (in both space and time) be fully characterized and optimized. A new channel mapping retrieval algorithm is introduced for this purpose. To characterize the spatial distribution of retrieval errors, the algorithm has been applied to analyze literally tens of millions of computer-simulated lightning VHF point sources that have been placed at various ranges, azimuths, and altitudes relative to the LMA network. Statistical results are conveniently summarized in high-resolution, color-coded, error maps.

A novel tracing method for the segmentation of cell wall networks.

PubMed

De Vylder, Jonas; Rooms, Filip; Dhondt, Stijn; Inze, Dirk; Philips, Wilfried

2013-01-01

Cell wall networks are a common subject of research in biology, which are important for plant growth analysis, organ studies, etc. In order to automate the detection of individual cells in such cell wall networks, we propose a new segmentation algorithm. The proposed method is a network tracing algorithm, exploiting the prior knowledge of the network structure. The method is applicable on multiple microscopy modalities such as fluorescence, but also for images captured using non invasive microscopes such as differential interference contrast (DIC) microscopes.

The Evolution of Gene Regulatory Networks that Define Arthropod Body Plans.

PubMed

Auman, Tzach; Chipman, Ariel D

2017-09-01

Our understanding of the genetics of arthropod body plan development originally stems from work on Drosophila melanogaster from the late 1970s and onward. In Drosophila, there is a relatively detailed model for the network of gene interactions that proceeds in a sequential-hierarchical fashion to define the main features of the body plan. Over the years, we have a growing understanding of the networks involved in defining the body plan in an increasing number of arthropod species. It is now becoming possible to tease out the conserved aspects of these networks and to try to reconstruct their evolution. In this contribution, we focus on several key nodes of these networks, starting from early patterning in which the main axes are determined and the broad morphological domains of the embryo are defined, and on to later stage wherein the growth zone network is active in sequential addition of posterior segments. The pattern of conservation of networks is very patchy, with some key aspects being highly conserved in all arthropods and others being very labile. Many aspects of early axis patterning are highly conserved, as are some aspects of sequential segment generation. In contrast, regional patterning varies among different taxa, and some networks, such as the terminal patterning network, are only found in a limited range of taxa. The growth zone segmentation network is ancient and is probably plesiomorphic to all arthropods. In some insects, it has undergone significant modification to give rise to a more hardwired network that generates individual segments separately. In other insects and in most arthropods, the sequential segmentation network has undergone a significant amount of systems drift, wherein many of the genes have changed. However, it maintains a conserved underlying logic and function. © The Author 2017. Published by Oxford University Press on behalf of the Society for Integrative and Comparative Biology. All rights reserved. For permissions please email: journals.permissions@oup.com.

Energy-efficient rings mechanism for greening multisegment fiber-wireless access networks

NASA Astrophysics Data System (ADS)

Gong, Xiaoxue; Guo, Lei; Hou, Weigang; Zhang, Lincong

2013-07-01

Through integrating advantages of optical and wireless communications, the Fiber-Wireless (FiWi) has become a promising solution for the "last-mile" broadband access. In particular, greening FiWi has attained extensive attention, because the access network is a main energy contributor in the whole infrastructure. However, prior solutions of greening FiWi shut down or sleep unused/minimally used optical network units for a single segment, where we deploy only one optical linear terminal. We propose a green mechanism referred to as energy-efficient ring (EER) for multisegment FiWi access networks. We utilize an integer linear programming model and a generic algorithm to generate clusters, each having the shortest distance of fully connected segments of its own. Leveraging the backtracking method for each cluster, we then connect segments through fiber links, and the shortest distance fiber ring is constructed. Finally, we sleep low load segments and forward affected traffic to other active segments on the same fiber ring by our sleeping scheme. Experimental results show that our EER mechanism significantly reduces the energy consumption at the slightly additional cost of deploying fiber links.

Solute transport with multisegment, equilibrium-controlled, classical reactions: Problem solvability and feed forward method's applicability for complex segments of at most binary participants

USGS Publications Warehouse

Rubin, Jacob

1992-01-01

The feed forward (FF) method derives efficient operational equations for simulating transport of reacting solutes. It has been shown to be applicable in the presence of networks with any number of homogeneous and/or heterogeneous, classical reaction segments that consist of three, at most binary participants. Using a sequential (network type after network type) exploration approach and, independently, theoretical explanations, it is demonstrated for networks with classical reaction segments containing more than three, at most binary participants that if any one of such networks leads to a solvable transport problem then the FF method is applicable. Ways of helping to avoid networks that produce problem insolvability are developed and demonstrated. A previously suggested algebraic, matrix rank procedure has been adapted and augmented to serve as the main, easy-to-apply solvability test for already postulated networks. Four network conditions that often generate insolvability have been identified and studied. Their early detection during network formulation may help to avoid postulation of insolvable networks.

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation.

PubMed

Hoseini, Farnaz; Shahbahrami, Asadollah; Bayat, Peyman

2018-02-27

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

A feedback model of visual attention.

PubMed

Spratling, M W; Johnson, M H

2004-03-01

Feedback connections are a prominent feature of cortical anatomy and are likely to have a significant functional role in neural information processing. We present a neural network model of cortical feedback that successfully simulates neurophysiological data associated with attention. In this domain, our model can be considered a more detailed, and biologically plausible, implementation of the biased competition model of attention. However, our model is more general as it can also explain a variety of other top-down processes in vision, such as figure/ground segmentation and contextual cueing. This model thus suggests that a common mechanism, involving cortical feedback pathways, is responsible for a range of phenomena and provides a unified account of currently disparate areas of research.

Using NASA's Reference Architecture: Comparing Polar and Geostationary Data Processing Systems

NASA Technical Reports Server (NTRS)

Ullman, Richard; Burnett, Michael

2013-01-01

The JPSS and GOES-R programs are housed at NASA GSFC and jointly implemented by NASA and NOAA to NOAA requirements. NASA's role in the JPSS Ground System is to develop and deploy the system according to NOAA requirements. NASA's role in the GOES-R ground segment is to provide Systems Engineering expertise and oversight for NOAA's development and deployment of the system. NASA's Earth Science Data Systems Reference Architecture is a document developed by NASA's Earth Science Data Systems Standards Process Group that describes a NASA Earth Observing Mission Ground system as a generic abstraction. The authors work within the respective ground segment projects and are also separately contributors to the Reference Architecture document. Opinions expressed are the author's only and are not NOAA, NASA or the Ground Projects' official positions.

Latency features of SafetyNet ground systems architecture for the National Polar-orbiting Operational Environmental Satellite System (NPOESS)

NASA Astrophysics Data System (ADS)

Duda, James L.; Mulligan, Joseph; Valenti, James; Wenkel, Michael

2005-01-01

A key feature of the National Polar-orbiting Operational Environmental Satellite System (NPOESS) is the Northrop Grumman Space Technology patent-pending innovative data routing and retrieval architecture called SafetyNetTM. The SafetyNetTM ground system architecture for the National Polar-orbiting Operational Environmental Satellite System (NPOESS), combined with the Interface Data Processing Segment (IDPS), will together provide low data latency and high data availability to its customers. The NPOESS will cut the time between observation and delivery by a factor of four when compared with today's space-based weather systems, the Defense Meteorological Satellite Program (DMSP) and NOAA's Polar-orbiting Operational Environmental Satellites (POES). SafetyNetTM will be a key element of the NPOESS architecture, delivering near real-time data over commercial telecommunications networks. Scattered around the globe, the 15 unmanned ground receptors are linked by fiber-optic systems to four central data processing centers in the U. S. known as Weather Centrals. The National Environmental Satellite, Data and Information Service; Air Force Weather Agency; Fleet Numerical Meteorology and Oceanography Center, and the Naval Oceanographic Office operate the Centrals. In addition, this ground system architecture will have unused capacity attendant with an infrastructure that can accommodate additional users.

Status of the Direct Data Distribution (D(exp 3)) Experiment

NASA Technical Reports Server (NTRS)

Wald, Lawrence

2001-01-01

NASA Glenn Research Center's Direct Data Distribution (D3) project will demonstrate an advanced, high-performance communications system that transmits information from an advanced technology payload carried by a NASA spacecraft in low Earth orbit (LEO) to a small receiving terminal on Earth. The space-based communications package will utilize a solid-state, K-band phased-array antenna that electronically steers the radiated energy beam toward a low-cost, tracking ground terminal, thereby providing agile, vibration-free, electronic steering at reduced size and weight with increased reliability. The array-based link will also demonstrate new digital processing technology that will allow the transmission of substantially increased amounts of latency-tolerant data collected from the LEO spacecraft directly to NASA field centers, principal investigators, or into the commercial terrestrial communications network. The technologies demonstrated by D3 will facilitate NASA's transition from using Government-owned communication assets to using commercial communication services. The hardware for D3 will incorporate advanced technology components developed under the High Rate Data Delivery (HRDD) Thrust Area of NASA's Office of Aerospace Technology Space Base Program at Glenn's Communications Technology Division. The flight segment components will include the electrically steerable phased-array antenna, which is being built by the Raytheon System Corporation and utilizes monolithic microwave integrated circuit (MMIC) technology operating at 19.05 GHz; and the digital encoder/modulator chipset, which uses four-channel orthogonal frequency division multiplexing (OFDM). The encoder/modulator will use a chipset developed by SICOM, Inc., which is both bandwidth and power efficient. The ground segment components will include a low-cost, open-loop tracking ground terminal incorporating a cryoreceiver to minimize terminal size without compromising receiver capability. The project is planning to hold a critical design review in the second quarter of fiscal year 2002.

Left ventricle segmentation in cardiac MRI images using fully convolutional neural networks

NASA Astrophysics Data System (ADS)

Vázquez Romaguera, Liset; Costa, Marly Guimarães Fernandes; Romero, Francisco Perdigón; Costa Filho, Cicero Ferreira Fernandes

2017-03-01

According to the World Health Organization, cardiovascular diseases are the leading cause of death worldwide, accounting for 17.3 million deaths per year, a number that is expected to grow to more than 23.6 million by 2030. Most cardiac pathologies involve the left ventricle; therefore, estimation of several functional parameters from a previous segmentation of this structure can be helpful in diagnosis. Manual delineation is a time consuming and tedious task that is also prone to high intra and inter-observer variability. Thus, there exists a need for automated cardiac segmentation method to help facilitate the diagnosis of cardiovascular diseases. In this work we propose a deep fully convolutional neural network architecture to address this issue and assess its performance. The model was trained end to end in a supervised learning stage from whole cardiac MRI images input and ground truth to make a per pixel classification. For its design, development and experimentation was used Caffe deep learning framework over an NVidia Quadro K4200 Graphics Processing Unit. The net architecture is: Conv64-ReLU (2x) - MaxPooling - Conv128-ReLU (2x) - MaxPooling - Conv256-ReLU (2x) - MaxPooling - Conv512-ReLu-Dropout (2x) - Conv2-ReLU - Deconv - Crop - Softmax. Training and testing processes were carried out using 5-fold cross validation with short axis cardiac magnetic resonance images from Sunnybrook Database. We obtained a Dice score of 0.92 and 0.90, Hausdorff distance of 4.48 and 5.43, Jaccard index of 0.97 and 0.97, sensitivity of 0.92 and 0.90 and specificity of 0.99 and 0.99, overall mean values with SGD and RMSProp, respectively.

Gebiss: an ImageJ plugin for the specification of ground truth and the performance evaluation of 3D segmentation algorithms

PubMed Central

2011-01-01

Background Image segmentation is a crucial step in quantitative microscopy that helps to define regions of tissues, cells or subcellular compartments. Depending on the degree of user interactions, segmentation methods can be divided into manual, automated or semi-automated approaches. 3D image stacks usually require automated methods due to their large number of optical sections. However, certain applications benefit from manual or semi-automated approaches. Scenarios include the quantification of 3D images with poor signal-to-noise ratios or the generation of so-called ground truth segmentations that are used to evaluate the accuracy of automated segmentation methods. Results We have developed Gebiss; an ImageJ plugin for the interactive segmentation, visualisation and quantification of 3D microscopic image stacks. We integrated a variety of existing plugins for threshold-based segmentation and volume visualisation. Conclusions We demonstrate the application of Gebiss to the segmentation of nuclei in live Drosophila embryos and the quantification of neurodegeneration in Drosophila larval brains. Gebiss was developed as a cross-platform ImageJ plugin and is freely available on the web at http://imaging.bii.a-star.edu.sg/projects/gebiss/. PMID:21668958

High Frequency Near-Field Ground Motion Excited by Strike-Slip Step Overs

NASA Astrophysics Data System (ADS)

Hu, Feng; Wen, Jian; Chen, Xiaofei

2018-03-01

We performed dynamic rupture simulations on step overs with 1-2 km step widths and present their corresponding horizontal peak ground velocity distributions in the near field within different frequency ranges. The rupture speeds on fault segments are determinant in controlling the near-field ground motion. A Mach wave impact area at the free surface, which can be inferred from the distribution of the ratio of the maximum fault-strike particle velocity to the maximum fault-normal particle velocity, is generated in the near field with sustained supershear ruptures on fault segments, and the Mach wave impact area cannot be detected with unsustained supershear ruptures alone. Sub-Rayleigh ruptures produce stronger ground motions beyond the end of fault segments. The existence of a low-velocity layer close to the free surface generates large amounts of high-frequency seismic radiation at step over discontinuities. For near-vertical step overs, normal stress perturbations on the primary fault caused by dipping structures affect the rupture speed transition, which further determines the distribution of the near-field ground motion. The presence of an extensional linking fault enhances the near-field ground motion in the extensional regime. This work helps us understand the characteristics of high-frequency seismic radiation in the vicinities of step overs and provides useful insights for interpreting the rupture speed distributions derived from the characteristics of near-field ground motion.

Spacecraft-level verification of the Van Allen Probes' RF communication system

NASA Astrophysics Data System (ADS)

Crowne, M. J.; Srinivasan, D.; Royster, D.; Weaver, G.; Matlin, D.; Mosavi, N.

This paper presents the verification process, lessons learned, and selected test results of the radio frequency (RF) communication system of the Van Allen Probes, formerly known as the Radiation Belt Storm Probes (RBSP). The Van Allen Probes mission is investigating the doughnut-shaped regions of space known as the Van Allen radiation belts where the Sun interacts with charged particles trapped in Earth's magnetic field. Understanding this dynamic area that surrounds our planet is important to improving our ability to design spacecraft and missions for reliability and astronaut safety. The Van Allen Probes mission features two nearly identical spacecraft designed, built, and operated by the Johns Hopkins University Applied Physics Laboratory (JHU/APL) for the National Aeronautics and Space Administration (NASA). The RF communication system features the JHU/APL Frontier Radio. The Frontier Radio is a software-defined radio (SDR) designed for spaceborne communications, navigation, radio science, and sensor applications. This mission marks the first spaceflight usage of the Frontier Radio. RF ground support equipment (RF GSE) was developed using a ground station receiver similar to what will be used in flight and whose capabilities provided clarity into RF system performance that was previously not obtained until compatibility testing with the ground segments. The Van Allen Probes underwent EMC, acoustic, vibration, and thermal vacuum testing at the environmental test facilities at APL. During this time the RF communication system was rigorously tested to ensure optimal performance, including system-level testing down to threshold power levels. Compatibility tests were performed with the JHU/APL Satellite Communication Facility (SCF), the Universal Space Network (USN), and the Tracking and Data Relay Satellite System (TDRSS). Successful completion of this program as described in this paper validated the design of the system and demonstrated that it will be able to me- t all of the Van Allen Probes's communications requirements with its intended ground segments.

Accurate Segmentation of Cervical Cytoplasm and Nuclei Based on Multiscale Convolutional Network and Graph Partitioning.

PubMed

Song, Youyi; Zhang, Ling; Chen, Siping; Ni, Dong; Lei, Baiying; Wang, Tianfu

2015-10-01

In this paper, a multiscale convolutional network (MSCN) and graph-partitioning-based method is proposed for accurate segmentation of cervical cytoplasm and nuclei. Specifically, deep learning via the MSCN is explored to extract scale invariant features, and then, segment regions centered at each pixel. The coarse segmentation is refined by an automated graph partitioning method based on the pretrained feature. The texture, shape, and contextual information of the target objects are learned to localize the appearance of distinctive boundary, which is also explored to generate markers to split the touching nuclei. For further refinement of the segmentation, a coarse-to-fine nucleus segmentation framework is developed. The computational complexity of the segmentation is reduced by using superpixel instead of raw pixels. Extensive experimental results demonstrate that the proposed cervical nucleus cell segmentation delivers promising results and outperforms existing methods.

Lake Ice Monitoring with Webcams

NASA Astrophysics Data System (ADS)

Xiao, M.; Rothermel, M.; Tom, M.; Galliani, S.; Baltsavias, E.; Schindler, K.

2018-05-01

Continuous monitoring of climate indicators is important for understanding the dynamics and trends of the climate system. Lake ice has been identified as one such indicator, and has been included in the list of Essential Climate Variables (ECVs). Currently there are two main ways to survey lake ice cover and its change over time, in-situ measurements and satellite remote sensing. The challenge with both of them is to ensure sufficient spatial and temporal resolution. Here, we investigate the possibility to monitor lake ice with video streams acquired by publicly available webcams. Main advantages of webcams are their high temporal frequency and dense spatial sampling. By contrast, they have low spectral resolution and limited image quality. Moreover, the uncontrolled radiometry and low, oblique viewpoints result in heavily varying appearance of water, ice and snow. We present a workflow for pixel-wise semantic segmentation of images into these classes, based on state-of-the-art encoder-decoder Convolutional Neural Networks (CNNs). The proposed segmentation pipeline is evaluated on two sequences featuring different ground sampling distances. The experiment suggests that (networks of) webcams have great potential for lake ice monitoring. The overall per-pixel accuracies for both tested data sets exceed 95 %. Furthermore, per-image discrimination between ice-on and ice-off conditions, derived by accumulating per-pixel results, is 100 % correct for our test data, making it possible to precisely recover freezing and thawing dates.

A fusion network for semantic segmentation using RGB-D data

NASA Astrophysics Data System (ADS)

Yuan, Jiahui; Zhang, Kun; Xia, Yifan; Qi, Lin; Dong, Junyu

2018-04-01

Semantic scene parsing is considerable in many intelligent field, including perceptual robotics. For the past few years, pixel-wise prediction tasks like semantic segmentation with RGB images has been extensively studied and has reached very remarkable parsing levels, thanks to convolutional neural networks (CNNs) and large scene datasets. With the development of stereo cameras and RGBD sensors, it is expected that additional depth information will help improving accuracy. In this paper, we propose a semantic segmentation framework incorporating RGB and complementary depth information. Motivated by the success of fully convolutional networks (FCN) in semantic segmentation field, we design a fully convolutional networks consists of two branches which extract features from both RGB and depth data simultaneously and fuse them as the network goes deeper. Instead of aggregating multiple model, our goal is to utilize RGB data and depth data more effectively in a single model. We evaluate our approach on the NYU-Depth V2 dataset, which consists of 1449 cluttered indoor scenes, and achieve competitive results with the state-of-the-art methods.

Use of Open Architecture Middleware for Autonomous Platforms

NASA Astrophysics Data System (ADS)

Naranjo, Hector; Diez, Sergio; Ferrero, Francisco

2011-08-01

Network Enabled Capabilities (NEC) is the vision for next-generation systems in the defence domain formulated by governments, the European Defence Agency (EDA) and the North Atlantic Treaty Organization (NATO). It involves the federation of military information systems, rather than just a simple interconnection, to provide each user with the "right information, right place, right time - and not too much". It defines openness, standardization and flexibility principles in military systems, likewise applicable in the civilian space applications.This paper provides the conclusions drawn from "Architecture for Embarked Middleware" (EMWARE) study, funded by the European Defence Agency (EDA).The aim of the EMWARE project was to provide the information and understanding to facilitate the adoption of informed decisions regarding the specification and implementation of Open Architecture Middleware in future distributed systems, linking it with the NEC goal.EMWARE project included the definition of four business cases, each devoted to a different field of application (Unmanned Aerial Vehicles, Helicopters, Unmanned Ground Vehicles and the Satellite Ground Segment).

Beaver-mediated lateral hydrologic connectivity, fluvial carbon and nutrient flux, and aquatic ecosystem metabolism

NASA Astrophysics Data System (ADS)

Wegener, Pam; Covino, Tim; Wohl, Ellen

2017-06-01

River networks that drain mountain landscapes alternate between narrow and wide valley segments. Within the wide segments, beaver activity can facilitate the development and maintenance of complex, multithread planform. Because the narrow segments have limited ability to retain water, carbon, and nutrients, the wide, multithread segments are likely important locations of retention. We evaluated hydrologic dynamics, nutrient flux, and aquatic ecosystem metabolism along two adjacent segments of a river network in the Rocky Mountains, Colorado: (1) a wide, multithread segment with beaver activity; and, (2) an adjacent (directly upstream) narrow, single-thread segment without beaver activity. We used a mass balance approach to determine the water, carbon, and nutrient source-sink behavior of each river segment across a range of flows. While the single-thread segment was consistently a source of water, carbon, and nitrogen, the beaver impacted multithread segment exhibited variable source-sink dynamics as a function of flow. Specifically, the multithread segment was a sink for water, carbon, and nutrients during high flows, and subsequently became a source as flows decreased. Shifts in river-floodplain hydrologic connectivity across flows related to higher and more variable aquatic ecosystem metabolism rates along the multithread relative to the single-thread segment. Our data suggest that beaver activity in wide valleys can create a physically complex hydrologic environment that can enhance hydrologic and biogeochemical buffering, and promote high rates of aquatic ecosystem metabolism. Given the widespread removal of beaver, determining the cumulative effects of these changes is a critical next step in restoring function in altered river networks.

Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships.

PubMed

Hatipoglu, Nuh; Bilgin, Gokhan

2017-10-01

In many computerized methods for cell detection, segmentation, and classification in digital histopathology that have recently emerged, the task of cell segmentation remains a chief problem for image processing in designing computer-aided diagnosis (CAD) systems. In research and diagnostic studies on cancer, pathologists can use CAD systems as second readers to analyze high-resolution histopathological images. Since cell detection and segmentation are critical for cancer grade assessments, cellular and extracellular structures should primarily be extracted from histopathological images. In response, we sought to identify a useful cell segmentation approach with histopathological images that uses not only prominent deep learning algorithms (i.e., convolutional neural networks, stacked autoencoders, and deep belief networks), but also spatial relationships, information of which is critical for achieving better cell segmentation results. To that end, we collected cellular and extracellular samples from histopathological images by windowing in small patches with various sizes. In experiments, the segmentation accuracies of the methods used improved as the window sizes increased due to the addition of local spatial and contextual information. Once we compared the effects of training sample size and influence of window size, results revealed that the deep learning algorithms, especially convolutional neural networks and partly stacked autoencoders, performed better than conventional methods in cell segmentation.

S-net : Construction of large scale seafloor observatory network for tsunamis and earthquakes along the Japan Trench

NASA Astrophysics Data System (ADS)

Mochizuki, M.; Uehira, K.; Kanazawa, T.; Shiomi, K.; Kunugi, T.; Aoi, S.; Matsumoto, T.; Sekiguchi, S.; Yamamoto, N.; Takahashi, N.; Nakamura, T.; Shinohara, M.; Yamada, T.

2017-12-01

NIED has launched the project of constructing a seafloor observatory network for tsunamis and earthquakes after the occurrence of the 2011 Tohoku Earthquake to enhance reliability of early warnings of tsunamis and earthquakes. The observatory network was named "S-net". The S-net project has been financially supported by MEXT.The S-net consists of 150 seafloor observatories which are connected in line with submarine optical cables. The total length of submarine optical cable is about 5,500 km. The S-net covers the focal region of the 2011 Tohoku Earthquake and its vicinity regions. Each observatory equips two units of a high sensitive pressure gauges as a tsunami meter and four sets of three-component seismometers. The S-net is composed of six segment networks. Five of six segment networks had been already installed. Installation of the last segment network covering the outer rise area have been finally finished by the end of FY2016. The outer rise segment has special features like no other five segments of the S-net. Those features are deep water and long distance. Most of 25 observatories on the outer rise segment are located at the depth of deeper than 6,000m WD. Especially, three observatories are set on the seafloor of deeper than about 7.000m WD, and then the pressure gauges capable of being used even at 8,000m WD are equipped on those three observatories. Total length of the submarine cables of the outer rise segment is about two times longer than those of the other segments. The longer the cable system is, the higher voltage supply is needed, and thus the observatories on the outer rise segment have high withstanding voltage characteristics. We employ a dispersion management line of a low loss formed by combining a plurality of optical fibers for the outer rise segment cable, in order to achieve long-distance, high-speed and large-capacity data transmission Installation of the outer rise segment was finished and then full-scale operation of S-net has started. All the data from 150 seafloor observatories are being transferred to and stored in the Tsukuba DC. Some data are being transmitted directly to JMA and have been used for monitoring of earthquakes and tsunamis. We will report construction and operation of the S-net system as well as the outline of the obtained data in this presentation.

Fully convolutional networks with double-label for esophageal cancer image segmentation by self-transfer learning

NASA Astrophysics Data System (ADS)

Xue, Di-Xiu; Zhang, Rong; Zhao, Yuan-Yuan; Xu, Jian-Ming; Wang, Ya-Lei

2017-07-01

Cancer recognition is the prerequisite to determine appropriate treatment. This paper focuses on the semantic segmentation task of microvascular morphological types on narrowband images to aid clinical examination of esophageal cancer. The most challenge for semantic segmentation is incomplete-labeling. Our key insight is to build fully convolutional networks (FCNs) with double-label to make pixel-wise predictions. The roi-label indicating ROIs (region of interest) is introduced as extra constraint to guild feature learning. Trained end-to-end, the FCN model with two target jointly optimizes both segmentation of sem-label (semantic label) and segmentation of roi-label within the framework of self-transfer learning based on multi-task learning theory. The learning representation ability of shared convolutional networks for sem-label is improved with support of roi-label via achieving a better understanding of information outside the ROIs. Our best FCN model gives satisfactory segmentation result with mean IU up to 77.8% (pixel accuracy > 90%). The results show that the proposed approach is able to assist clinical diagnosis to a certain extent.

Multi-level deep supervised networks for retinal vessel segmentation.

PubMed

Mo, Juan; Zhang, Lei

2017-12-01

Changes in the appearance of retinal blood vessels are an important indicator for various ophthalmologic and cardiovascular diseases, including diabetes, hypertension, arteriosclerosis, and choroidal neovascularization. Vessel segmentation from retinal images is very challenging because of low blood vessel contrast, intricate vessel topology, and the presence of pathologies such as microaneurysms and hemorrhages. To overcome these challenges, we propose a neural network-based method for vessel segmentation. A deep supervised fully convolutional network is developed by leveraging multi-level hierarchical features of the deep networks. To improve the discriminative capability of features in lower layers of the deep network and guide the gradient back propagation to overcome gradient vanishing, deep supervision with auxiliary classifiers is incorporated in some intermediate layers of the network. Moreover, the transferred knowledge learned from other domains is used to alleviate the issue of insufficient medical training data. The proposed approach does not rely on hand-crafted features and needs no problem-specific preprocessing or postprocessing, which reduces the impact of subjective factors. We evaluate the proposed method on three publicly available databases, the DRIVE, STARE, and CHASE_DB1 databases. Extensive experiments demonstrate that our approach achieves better or comparable performance to state-of-the-art methods with a much faster processing speed, making it suitable for real-world clinical applications. The results of cross-training experiments demonstrate its robustness with respect to the training set. The proposed approach segments retinal vessels accurately with a much faster processing speed and can be easily applied to other biomedical segmentation tasks.

Object class segmentation of RGB-D video using recurrent convolutional neural networks.

PubMed

Pavel, Mircea Serban; Schulz, Hannes; Behnke, Sven

2017-04-01

Object class segmentation is a computer vision task which requires labeling each pixel of an image with the class of the object it belongs to. Deep convolutional neural networks (DNN) are able to learn and take advantage of local spatial correlations required for this task. They are, however, restricted by their small, fixed-sized filters, which limits their ability to learn long-range dependencies. Recurrent Neural Networks (RNN), on the other hand, do not suffer from this restriction. Their iterative interpretation allows them to model long-range dependencies by propagating activity. This property is especially useful when labeling video sequences, where both spatial and temporal long-range dependencies occur. In this work, a novel RNN architecture for object class segmentation is presented. We investigate several ways to train such a network. We evaluate our models on the challenging NYU Depth v2 dataset for object class segmentation and obtain competitive results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Algorithm for protecting light-trees in survivable mesh wavelength-division-multiplexing networks

NASA Astrophysics Data System (ADS)

Luo, Hongbin; Li, Lemin; Yu, Hongfang

2006-12-01

Wavelength-division-multiplexing (WDM) technology is expected to facilitate bandwidth-intensive multicast applications such as high-definition television. A single fiber cut in a WDM mesh network, however, can disrupt the dissemination of information to several destinations on a light-tree based multicast session. Thus it is imperative to protect multicast sessions by reserving redundant resources. We propose a novel and efficient algorithm for protecting light-trees in survivable WDM mesh networks. The algorithm is called segment-based protection with sister node first (SSNF), whose basic idea is to protect a light-tree using a set of backup segments with a higher priority to protect the segments from a branch point to its children (sister nodes). The SSNF algorithm differs from the segment protection scheme proposed in the literature in how the segments are identified and protected. Our objective is to minimize the network resources used for protecting each primary light-tree such that the blocking probability can be minimized. To verify the effectiveness of the SSNF algorithm, we conduct extensive simulation experiments. The simulation results demonstrate that the SSNF algorithm outperforms existing algorithms for the same problem.

Developing a Procedure for Segmenting Meshed Heat Networks of Heat Supply Systems without Outflows

NASA Astrophysics Data System (ADS)

Tokarev, V. V.

2018-06-01

The heat supply systems of cities have, as a rule, a ring structure with the possibility of redistributing the flows. Despite the fact that a ring structure is more reliable than a radial one, the operators of heat networks prefer to use them in normal modes according to the scheme without overflows of the heat carrier between the heat mains. With such a scheme, it is easier to adjust the networks and to detect and locate faults in them. The article proposes a formulation of the heat network segmenting problem. The problem is set in terms of optimization with the heat supply system's excessive hydraulic power used as the optimization criterion. The heat supply system computer model has a hierarchically interconnected multilevel structure. Since iterative calculations are only carried out for the level of trunk heat networks, decomposing the entire system into levels allows the dimensionality of the solved subproblems to be reduced by an order of magnitude. An attempt to solve the problem by fully enumerating possible segmentation versions does not seem to be feasible for systems of really existing sizes. The article suggests a procedure for searching rational segmentation of heat supply networks with limiting the search to versions of dividing the system into segments near the flow convergence nodes with subsequent refining of the solution. The refinement is performed in two stages according to the total excess hydraulic power criterion. At the first stage, the loads are redistributed among the sources. After that, the heat networks are divided into independent fragments, and the possibility of increasing the excess hydraulic power in the obtained fragments is checked by shifting the division places inside a fragment. The proposed procedure has been approbated taking as an example a municipal heat supply system involving six heat mains fed from a common source, 24 loops within the feeding mains plane, and more than 5000 consumers. Application of the proposed segmentation procedure made it possible to find a version with required hydraulic power in the heat supply system on 3% less than the one found using the simultaneous segmentation method.

3D deeply supervised network for automated segmentation of volumetric medical images.

PubMed

Dou, Qi; Yu, Lequan; Chen, Hao; Jin, Yueming; Yang, Xin; Qin, Jing; Heng, Pheng-Ann

2017-10-01

While deep convolutional neural networks (CNNs) have achieved remarkable success in 2D medical image segmentation, it is still a difficult task for CNNs to segment important organs or structures from 3D medical images owing to several mutually affected challenges, including the complicated anatomical environments in volumetric images, optimization difficulties of 3D networks and inadequacy of training samples. In this paper, we present a novel and efficient 3D fully convolutional network equipped with a 3D deep supervision mechanism to comprehensively address these challenges; we call it 3D DSN. Our proposed 3D DSN is capable of conducting volume-to-volume learning and inference, which can eliminate redundant computations and alleviate the risk of over-fitting on limited training data. More importantly, the 3D deep supervision mechanism can effectively cope with the optimization problem of gradients vanishing or exploding when training a 3D deep model, accelerating the convergence speed and simultaneously improving the discrimination capability. Such a mechanism is developed by deriving an objective function that directly guides the training of both lower and upper layers in the network, so that the adverse effects of unstable gradient changes can be counteracted during the training procedure. We also employ a fully connected conditional random field model as a post-processing step to refine the segmentation results. We have extensively validated the proposed 3D DSN on two typical yet challenging volumetric medical image segmentation tasks: (i) liver segmentation from 3D CT scans and (ii) whole heart and great vessels segmentation from 3D MR images, by participating two grand challenges held in conjunction with MICCAI. We have achieved competitive segmentation results to state-of-the-art approaches in both challenges with a much faster speed, corroborating the effectiveness of our proposed 3D DSN. Copyright © 2017 Elsevier B.V. All rights reserved.

A Hox regulatory network of hindbrain segmentation is conserved to the base of vertebrates.

PubMed

Parker, Hugo J; Bronner, Marianne E; Krumlauf, Robb

2014-10-23

A defining feature governing head patterning of jawed vertebrates is a highly conserved gene regulatory network that integrates hindbrain segmentation with segmentally restricted domains of Hox gene expression. Although non-vertebrate chordates display nested domains of axial Hox expression, they lack hindbrain segmentation. The sea lamprey, a jawless fish, can provide unique insights into vertebrate origins owing to its phylogenetic position at the base of the vertebrate tree. It has been suggested that lamprey may represent an intermediate state where nested Hox expression has not been coupled to the process of hindbrain segmentation. However, little is known about the regulatory network underlying Hox expression in lamprey or its relationship to hindbrain segmentation. Here, using a novel tool that allows cross-species comparisons of regulatory elements between jawed and jawless vertebrates, we report deep conservation of both upstream regulators and segmental activity of enhancer elements across these distant species. Regulatory regions from diverse gnathostomes drive segmental reporter expression in the lamprey hindbrain and require the same transcriptional inputs (for example, Kreisler (also known as Mafba), Krox20 (also known as Egr2a)) in both lamprey and zebrafish. We find that lamprey hox genes display dynamic segmentally restricted domains of expression; we also isolated a conserved exonic hox2 enhancer from lamprey that drives segmental expression in rhombomeres 2 and 4. Our results show that coupling of Hox gene expression to segmentation of the hindbrain is an ancient trait with origin at the base of vertebrates that probably led to the formation of rhombomeric compartments with an underlying Hox code.

Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm.

PubMed

Savareh, Behrouz Alizadeh; Emami, Hassan; Hajiabadi, Mohamadreza; Azimi, Seyed Majid; Ghafoori, Mahyar

2018-05-29

Manual brain tumor segmentation is a challenging task that requires the use of machine learning techniques. One of the machine learning techniques that has been given much attention is the convolutional neural network (CNN). The performance of the CNN can be enhanced by combining other data analysis tools such as wavelet transform. In this study, one of the famous implementations of CNN, a fully convolutional network (FCN), was used in brain tumor segmentation and its architecture was enhanced by wavelet transform. In this combination, a wavelet transform was used as a complementary and enhancing tool for CNN in brain tumor segmentation. Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. Using mathematical functions and enhancing tools such as wavelet transform and other mathematical functions can improve the performance of CNN in any image processing task such as segmentation and classification.

Biomorphic networks: approach to invariant feature extraction and segmentation for ATR

NASA Astrophysics Data System (ADS)

Baek, Andrew; Farhat, Nabil H.

1998-10-01

Invariant features in two dimensional binary images are extracted in a single layer network of locally coupled spiking (pulsating) model neurons with prescribed synapto-dendritic response. The feature vector for an image is represented as invariant structure in the aggregate histogram of interspike intervals obtained by computing time intervals between successive spikes produced from each neuron over a given period of time and combining such intervals from all neurons in the network into a histogram. Simulation results show that the feature vectors are more pattern-specific and invariant under translation, rotation, and change in scale or intensity than achieved in earlier work. We also describe an application of such networks to segmentation of line (edge-enhanced or silhouette) images. The biomorphic spiking network's capabilities in segmentation and invariant feature extraction may prove to be, when they are combined, valuable in Automated Target Recognition (ATR) and other automated object recognition systems.

Fully convolutional neural networks for polyp segmentation in colonoscopy

NASA Astrophysics Data System (ADS)

Brandao, Patrick; Mazomenos, Evangelos; Ciuti, Gastone; Caliò, Renato; Bianchi, Federico; Menciassi, Arianna; Dario, Paolo; Koulaouzidis, Anastasios; Arezzo, Alberto; Stoyanov, Danail

2017-03-01

Colorectal cancer (CRC) is one of the most common and deadliest forms of cancer, accounting for nearly 10% of all forms of cancer in the world. Even though colonoscopy is considered the most effective method for screening and diagnosis, the success of the procedure is highly dependent on the operator skills and level of hand-eye coordination. In this work, we propose to adapt fully convolution neural networks (FCN), to identify and segment polyps in colonoscopy images. We converted three established networks into a fully convolution architecture and fine-tuned their learned representations to the polyp segmentation task. We validate our framework on the 2015 MICCAI polyp detection challenge dataset, surpassing the state-of-the-art in automated polyp detection. Our method obtained high segmentation accuracy and a detection precision and recall of 73.61% and 86.31%, respectively.

Software for hyperspectral, joint photographic experts group (.JPG), portable network graphics (.PNG) and tagged image file format (.TIFF) segmentation

NASA Astrophysics Data System (ADS)

Bruno, L. S.; Rodrigo, B. P.; Lucio, A. de C. Jorge

2016-10-01

This paper presents a system developed by an application of a neural network Multilayer Perceptron for drone acquired agricultural image segmentation. This application allows a supervised user training the classes that will posteriorly be interpreted by neural network. These classes will be generated manually with pre-selected attributes in the application. After the attribute selection a segmentation process is made to allow the relevant information extraction for different types of images, RGB or Hyperspectral. The application allows extracting the geographical coordinates from the image metadata, geo referencing all pixels on the image. In spite of excessive memory consume on hyperspectral images regions of interest, is possible to perform segmentation, using bands chosen by user that can be combined in different ways to obtain different results.

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.

PubMed

Qin, Siyang; Manduchi, Roberto

2017-11-01

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].

NASDA's view of ground control in mission operations

NASA Technical Reports Server (NTRS)

Tateno, Satoshi

1993-01-01

This paper presents an overview of the present status and future plans of the National Space Development Agency of Japan 's (NASDA's) ground segment and related space missions. The described ground segment consists of the tracking and data acquisition (T&DA) system and the Earth Observation Center (EOC) system. In addition to these systems, the current plan of the Engineering Support Center (ESC) for the Japanese Experiment Module (JEM) attached to Space Station Freedom is introduced. Then, NASDA's fundamental point of view on the future trend of operations and technologies in the coming new space era is discussed. Within the discussion, the increasing importance of international cooperation is also mentioned.

Automatic co-segmentation of lung tumor based on random forest in PET-CT images

NASA Astrophysics Data System (ADS)

Jiang, Xueqing; Xiang, Dehui; Zhang, Bin; Zhu, Weifang; Shi, Fei; Chen, Xinjian

2016-03-01

In this paper, a fully automatic method is proposed to segment the lung tumor in clinical 3D PET-CT images. The proposed method effectively combines PET and CT information to make full use of the high contrast of PET images and superior spatial resolution of CT images. Our approach consists of three main parts: (1) initial segmentation, in which spines are removed in CT images and initial connected regions achieved by thresholding based segmentation in PET images; (2) coarse segmentation, in which monotonic downhill function is applied to rule out structures which have similar standardized uptake values (SUV) to the lung tumor but do not satisfy a monotonic property in PET images; (3) fine segmentation, random forests method is applied to accurately segment the lung tumor by extracting effective features from PET and CT images simultaneously. We validated our algorithm on a dataset which consists of 24 3D PET-CT images from different patients with non-small cell lung cancer (NSCLC). The average TPVF, FPVF and accuracy rate (ACC) were 83.65%, 0.05% and 99.93%, respectively. The correlation analysis shows our segmented lung tumor volumes has strong correlation ( average 0.985) with the ground truth 1 and ground truth 2 labeled by a clinical expert.

An algorithm for calculi segmentation on ureteroscopic images.

PubMed

Rosa, Benoît; Mozer, Pierre; Szewczyk, Jérôme

2011-03-01

The purpose of the study is to develop an algorithm for the segmentation of renal calculi on ureteroscopic images. In fact, renal calculi are common source of urological obstruction, and laser lithotripsy during ureteroscopy is a possible therapy. A laser-based system to sweep the calculus surface and vaporize it was developed to automate a very tedious manual task. The distal tip of the ureteroscope is directed using image guidance, and this operation is not possible without an efficient segmentation of renal calculi on the ureteroscopic images. We proposed and developed a region growing algorithm to segment renal calculi on ureteroscopic images. Using real video images to compute ground truth and compare our segmentation with a reference segmentation, we computed statistics on different image metrics, such as Precision, Recall, and Yasnoff Measure, for comparison with ground truth. The algorithm and its parameters were established for the most likely clinical scenarii. The segmentation results are encouraging: the developed algorithm was able to correctly detect more than 90% of the surface of the calculi, according to an expert observer. Implementation of an algorithm for the segmentation of calculi on ureteroscopic images is feasible. The next step is the integration of our algorithm in the command scheme of a motorized system to build a complete operating prototype.

JAXA-NASA Interoperability Demonstration for Application of DTN Under Simulated Rain Attenuation

NASA Technical Reports Server (NTRS)

Suzuki, Kiyoshisa; Inagawa, Shinichi; Lippincott, Jeff; Cecil, Andrew J.

2014-01-01

As is well known, K-band or higher band communications in space link segment often experience intermittent disruptions caused by heavy rainfall. In view of keeping data integrity and establishing autonomous operations under such situation, it is important to consider introducing a tolerance mechanism such as Delay/Disruption Tolerant Networking (DTN). The Consultative Committee for Space Data Systems (CCSDS) is studying DTN as part of the standardization activities for space data systems. As a contribution to CCSDS and a feasibility study for future utilization of DTN, Japan Aerospace Exploration Agency (JAXA) and National Aeronautics and Space Administration (NASA) conducted an interoperability demonstration for confirming its tolerance mechanism and capability of automatic operation using Data Relay Test Satellite (DRTS) space link and its ground terminals. Both parties used the Interplanetary Overlay Network (ION) open source software, including the Bundle Protocol, the Licklider Transmission Protocol, and Contact Graph Routing. This paper introduces the contents of the interoperability demonstration and its results.

Automated detection of videotaped neonatal seizures based on motion segmentation methods.

PubMed

Karayiannis, Nicolaos B; Tao, Guozhi; Frost, James D; Wise, Merrill S; Hrachovy, Richard A; Mizrahi, Eli M

2006-07-01

This study was aimed at the development of a seizure detection system by training neural networks using quantitative motion information extracted by motion segmentation methods from short video recordings of infants monitored for seizures. The motion of the infants' body parts was quantified by temporal motion strength signals extracted from video recordings by motion segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by direct thresholding, by clustering of the pixel velocities, and by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The computational tools and procedures developed for automated seizure detection were tested and evaluated on 240 short video segments selected and labeled by physicians from a set of video recordings of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). The experimental study described in this paper provided the basis for selecting the most effective strategy for training neural networks to detect neonatal seizures as well as the decision scheme used for interpreting the responses of the trained neural networks. Depending on the decision scheme used for interpreting the responses of the trained neural networks, the best neural networks exhibited sensitivity above 90% or specificity above 90%. The best among the motion segmentation methods developed in this study produced quantitative features that constitute a reliable basis for detecting myoclonic and focal clonic neonatal seizures. The performance targets of this phase of the project may be achieved by combining the quantitative features described in this paper with those obtained by analyzing motion trajectory signals produced by motion tracking methods. A video system based upon automated analysis potentially offers a number of advantages. Infants who are at risk for seizures could be monitored continuously using relatively inexpensive and non-invasive video techniques that supplement direct observation by nursery personnel. This would represent a major advance in seizure surveillance and offers the possibility for earlier identification of potential neurological problems and subsequent intervention.

Update on the activities of the GGOS Bureau of Networks and Observations

NASA Technical Reports Server (NTRS)

Pearlman, Michael R.; Pavlis, Erricos C.; Ma, Chopo; Noll, Carey; Thaller, Daniela; Richter, Bernd; Gross, Richard; Neilan, Ruth; Mueller, Juergen; Barzaghi, Ricardo;

Effects of Network Characteristics on Reaching the Payoff-Dominant Equilibrium in Coordination Games: A Simulation study.

PubMed

Buskens, Vincent; Snijders, Chris

2016-01-01

We study how payoffs and network structure affect reaching the payoff-dominant equilibrium in a [Formula: see text] coordination game that actors play with their neighbors in a network. Using an extensive simulation analysis of over 100,000 networks with 2-25 actors, we show that the importance of network characteristics is restricted to a limited part of the payoff space. In this part, we conclude that the payoff-dominant equilibrium is chosen more often if network density is larger, the network is more centralized, and segmentation of the network is smaller. Moreover, it is more likely that heterogeneity in behavior persists if the network is more segmented and less centralized. Persistence of heterogeneous behavior is not related to network density.

DeepNAT: Deep convolutional neural network for segmenting neuroanatomy.

PubMed

Wachinger, Christian; Reuter, Martin; Klein, Tassilo

2018-04-15

We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images. DeepNAT is an end-to-end learning-based approach to brain segmentation that jointly learns an abstract feature representation and a multi-class classification. We propose a 3D patch-based approach, where we do not only predict the center voxel of the patch but also neighbors, which is formulated as multi-task learning. To address a class imbalance problem, we arrange two networks hierarchically, where the first one separates foreground from background, and the second one identifies 25 brain structures on the foreground. Since patches lack spatial context, we augment them with coordinates. To this end, we introduce a novel intrinsic parameterization of the brain volume, formed by eigenfunctions of the Laplace-Beltrami operator. As network architecture, we use three convolutional layers with pooling, batch normalization, and non-linearities, followed by fully connected layers with dropout. The final segmentation is inferred from the probabilistic output of the network with a 3D fully connected conditional random field, which ensures label agreement between close voxels. The roughly 2.7million parameters in the network are learned with stochastic gradient descent. Our results show that DeepNAT compares favorably to state-of-the-art methods. Finally, the purely learning-based method may have a high potential for the adaptation to young, old, or diseased brains by fine-tuning the pre-trained network with a small training sample on the target application, where the availability of larger datasets with manual annotations may boost the overall segmentation accuracy in the future. Copyright © 2017 Elsevier Inc. All rights reserved.

Cerebral vessels segmentation for light-sheet microscopy image using convolutional neural networks

NASA Astrophysics Data System (ADS)

Hu, Chaoen; Hui, Hui; Wang, Shuo; Dong, Di; Liu, Xia; Yang, Xin; Tian, Jie

2017-03-01

Cerebral vessel segmentation is an important step in image analysis for brain function and brain disease studies. To extract all the cerebrovascular patterns, including arteries and capillaries, some filter-based methods are used to segment vessels. However, the design of accurate and robust vessel segmentation algorithms is still challenging, due to the variety and complexity of images, especially in cerebral blood vessel segmentation. In this work, we addressed a problem of automatic and robust segmentation of cerebral micro-vessels structures in cerebrovascular images acquired by light-sheet microscope for mouse. To segment micro-vessels in large-scale image data, we proposed a convolutional neural networks (CNNs) architecture trained by 1.58 million pixels with manual label. Three convolutional layers and one fully connected layer were used in the CNNs model. We extracted a patch of size 32x32 pixels in each acquired brain vessel image as training data set to feed into CNNs for classification. This network was trained to output the probability that the center pixel of input patch belongs to vessel structures. To build the CNNs architecture, a series of mouse brain vascular images acquired from a commercial light sheet fluorescence microscopy (LSFM) system were used for training the model. The experimental results demonstrated that our approach is a promising method for effectively segmenting micro-vessels structures in cerebrovascular images with vessel-dense, nonuniform gray-level and long-scale contrast regions.

Minimizing eddy currents induced in the ground plane of a large phased-array ultrasound applicator for echo-planar imaging-based MR thermometry.

PubMed

Lechner-Greite, Silke M; Hehn, Nicolas; Werner, Beat; Zadicario, Eyal; Tarasek, Matthew; Yeo, Desmond

2016-01-01

The study aims to investigate different ground plane segmentation designs of an ultrasound transducer to reduce gradient field induced eddy currents and the associated geometric distortion and temperature map errors in echo-planar imaging (EPI)-based MR thermometry in transcranial magnetic resonance (MR)-guided focused ultrasound (tcMRgFUS). Six different ground plane segmentations were considered and the efficacy of each in suppressing eddy currents was investigated in silico and in operando. For the latter case, the segmented ground planes were implemented in a transducer mockup model for validation. Robust spoiled gradient (SPGR) echo sequences and multi-shot EPI sequences were acquired. For each sequence and pattern, geometric distortions were quantified in the magnitude images and expressed in millimeters. Phase images were used for extracting the temperature maps on the basis of the temperature-dependent proton resonance frequency shift phenomenon. The means, standard deviations, and signal-to-noise ratios (SNRs) were extracted and contrasted with the geometric distortions of all patterns. The geometric distortion analysis and temperature map evaluations showed that more than one pattern could be considered the best-performing transducer. In the sagittal plane, the star (d) (3.46 ± 2.33 mm) and star-ring patterns (f) (2.72 ± 2.8 mm) showed smaller geometric distortions than the currently available seven-segment sheet (c) (5.54 ± 4.21 mm) and were both comparable to the reference scenario (a) (2.77 ± 2.24 mm). Contrasting these results with the temperature maps revealed that (d) performs as well as (a) in SPGR and EPI. We demonstrated that segmenting the transducer ground plane into a star pattern reduces eddy currents to a level wherein multi-plane EPI for accurate MR thermometry in tcMRgFUS is feasible.

Source Model of Huge Subduction Earthquakes for Strong Ground Motion Prediction

NASA Astrophysics Data System (ADS)

Iwata, T.; Asano, K.

2012-12-01

It is a quite important issue for strong ground motion prediction to construct the source model of huge subduction earthquakes. Irikura and Miyake (2001, 2011) proposed the characterized source model for strong ground motion prediction, which consists of plural strong ground motion generation area (SMGA, Miyake et al., 2003) patches on the source fault. We obtained the SMGA source models for many events using the empirical Green's function method and found the SMGA size has an empirical scaling relationship with seismic moment. Therefore, the SMGA size can be assumed from that empirical relation under giving the seismic moment for anticipated earthquakes. Concerning to the setting of the SMGAs position, the information of the fault segment is useful for inland crustal earthquakes. For the 1995 Kobe earthquake, three SMGA patches are obtained and each Nojima, Suma, and Suwayama segment respectively has one SMGA from the SMGA modeling (e.g. Kamae and Irikura, 1998). For the 2011 Tohoku earthquake, Asano and Iwata (2012) estimated the SMGA source model and obtained four SMGA patches on the source fault. Total SMGA area follows the extension of the empirical scaling relationship between the seismic moment and the SMGA area for subduction plate-boundary earthquakes, and it shows the applicability of the empirical scaling relationship for the SMGA. The positions of two SMGAs are in Miyagi-Oki segment and those other two SMGAs are in Fukushima-Oki and Ibaraki-Oki segments, respectively. Asano and Iwata (2012) also pointed out that all SMGAs are corresponding to the historical source areas of 1930's. Those SMGAs do not overlap the huge slip area in the shallower part of the source fault which estimated by teleseismic data, long-period strong motion data, and/or geodetic data during the 2011 mainshock. This fact shows the huge slip area does not contribute to strong ground motion generation (10-0.1s). The information of the fault segment in the subduction zone, or historical earthquake source area is also applicable for the construction of SMGA settings for strong ground motion prediction for future earthquakes.

Operational EEW Networks in Turkey

NASA Astrophysics Data System (ADS)

Zulfikar, Can; Pinar, Ali

2016-04-01

There are several EEW networks and algorithms under operation in Turkey. The first EEW system was deployed in Istanbul in 2002 after the 1999 Mw7.4 Kocaeli and Mw7.1 Duzce earthquake events. The system consisted of 10 strong motion stations located as close as possible to the main Marmara Fault line. The system was upgraded by 5 OBS (Ocean Bottom Seismometer) in 2012 located in Marmara Sea. The system works in threshold based algorithm. The alert is given according to exceedance of certain threshold levels of amplitude of ground motion acceleration in certain time interval at least in 3 stations. Currently, there are two end-users of EEW system in Istanbul. The critical facilities of Istanbul Gas Distribution Company (IGDAS) and Marmaray Tube tunnel receives the EEW information in order to activate their automatic shut-off mechanisms. The IGDAS has their own strong motion network located at their district regulators. After receiving the EEW signal if the threshold values of ground motion parameters are exceeded the gas-flow is cut automatically at the district regulators. The IGDAS has 750 district regulators distributed in Istanbul. At the moment, the 110 of them are instrumented with strong motion accelerometers. As a 2nd stage of the on-going project, the IGDAS company proposes to install strong motion accelerometers to all remaining district regulators. The Marmaray railway tube tunnel is the world's deepest immersed tube tunnel with 60m undersea depth. The tunnel has 1.4km length with 13 segments. The tunnel is monitored with 2 strong motion accelerometers in each segment, 26 in total. Once the EEW signal is received, the monitoring system is activated and the recording ground motion parameters are calculated in real-time. Depending on the exceedance of threshold levels, further actions are taken such as reducing the train speed, stopping the train before entering the tunnel etc. In Istanbul, there are also on-site EEW system applied in several high-rise buildings. As similar to threshold based algorithm, once the threshold level is exceeded in several strong motion accelerometers installed in the high-rise building, the automated shut-off mechanism is activated in order to prevent secondary damage effects of the earthquakes. In addition to the threshold based EEW system, the regional EEW algorithms Virtual Seismologist (VS) as implemented in SeisComP3 VS(SC3) and PRESTo have been also implemented in Marmara region of Turkey. These applications use the regional seismic networks. The purpose of the regional EEW systems is to determine the magnitude and location of the event from the P-wave information of the closest 3-4 stations and forward this information to interested sites. The regional EEW systems are also important for Istanbul in order to detect far distance earthquake events and provide alert especially for the high-rise buildings for their long duration shaking.

Emergence of Convolutional Neural Network in Future Medicine: Why and How. A Review on Brain Tumor Segmentation

NASA Astrophysics Data System (ADS)

Alizadeh Savareh, Behrouz; Emami, Hassan; Hajiabadi, Mohamadreza; Ghafoori, Mahyar; Majid Azimi, Seyed

2018-03-01

Manual analysis of brain tumors magnetic resonance images is usually accompanied by some problem. Several techniques have been proposed for the brain tumor segmentation. This study will be focused on searching popular databases for related studies, theoretical and practical aspects of Convolutional Neural Network surveyed in brain tumor segmentation. Based on our findings, details about related studies including the datasets used, evaluation parameters, preferred architectures and complementary steps analyzed. Deep learning as a revolutionary idea in image processing, achieved brilliant results in brain tumor segmentation too. This can be continuing until the next revolutionary idea emerging.

Scene Semantic Segmentation from Indoor Rgb-D Images Using Encode-Decoder Fully Convolutional Networks

NASA Astrophysics Data System (ADS)

Wang, Z.; Li, T.; Pan, L.; Kang, Z.

2017-09-01

With increasing attention for the indoor environment and the development of low-cost RGB-D sensors, indoor RGB-D images are easily acquired. However, scene semantic segmentation is still an open area, which restricts indoor applications. The depth information can help to distinguish the regions which are difficult to be segmented out from the RGB images with similar color or texture in the indoor scenes. How to utilize the depth information is the key problem of semantic segmentation for RGB-D images. In this paper, we propose an Encode-Decoder Fully Convolutional Networks for RGB-D image classification. We use Multiple Kernel Maximum Mean Discrepancy (MK-MMD) as a distance measure to find common and special features of RGB and D images in the network to enhance performance of classification automatically. To explore better methods of applying MMD, we designed two strategies; the first calculates MMD for each feature map, and the other calculates MMD for whole batch features. Based on the result of classification, we use the full connect CRFs for the semantic segmentation. The experimental results show that our method can achieve a good performance on indoor RGB-D image semantic segmentation.

LANDSAT-D program. Volume 2: Ground segment

NASA Technical Reports Server (NTRS)

1984-01-01

Raw digital data, as received from the LANDSAT spacecraft, cannot generate images that meet specifications. Radiometric corrections must be made to compensate for aging and for differences in sensitivity among the instrument sensors. Geometric corrections must be made to compensate for off-nadir look angle, and to calculate spacecraft drift from its prescribed path. Corrections must also be made for look-angle jitter caused by vibrations induced by spacecraft equipment. The major components of the LANDSAT ground segment and their functions are discussed.

Figure-ground segregation modulates apparent motion.

PubMed

Ramachandran, V S; Anstis, S

1986-01-01

We explored the relationship between figure-ground segmentation and apparent motion. Results suggest that: static elements in the surround can eliminate apparent motion of a cluster of dots in the centre, but only if the cluster and surround have similar "grain" or texture; outlines that define occluding surfaces are taken into account by the motion mechanism; the brain uses a hierarchy of precedence rules in attributing motion to different segments of the visual scene. Being designated as "figure" confers a high rank in this scheme of priorities.

Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks

NASA Astrophysics Data System (ADS)

Roth, Holger; Oda, Masahiro; Shimizu, Natsuki; Oda, Hirohisa; Hayashi, Yuichiro; Kitasaka, Takayuki; Fujiwara, Michitaka; Misawa, Kazunari; Mori, Kensaku

2018-03-01

Pancreas segmentation in computed tomography imaging has been historically difficult for automated methods because of the large shape and size variations between patients. In this work, we describe a custom-build 3D fully convolutional network (FCN) that can process a 3D image including the whole pancreas and produce an automatic segmentation. We investigate two variations of the 3D FCN architecture; one with concatenation and one with summation skip connections to the decoder part of the network. We evaluate our methods on a dataset from a clinical trial with gastric cancer patients, including 147 contrast enhanced abdominal CT scans acquired in the portal venous phase. Using the summation architecture, we achieve an average Dice score of 89.7 +/- 3.8 (range [79.8, 94.8])% in testing, achieving the new state-of-the-art performance in pancreas segmentation on this dataset.

Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach

PubMed Central

Wang, Yue; Adalý, Tülay; Kung, Sun-Yuan; Szabo, Zsolt

2007-01-01

This paper presents a probabilistic neural network based technique for unsupervised quantification and segmentation of brain tissues from magnetic resonance images. It is shown that this problem can be solved by distribution learning and relaxation labeling, resulting in an efficient method that may be particularly useful in quantifying and segmenting abnormal brain tissues where the number of tissue types is unknown and the distributions of tissue types heavily overlap. The new technique uses suitable statistical models for both the pixel and context images and formulates the problem in terms of model-histogram fitting and global consistency labeling. The quantification is achieved by probabilistic self-organizing mixtures and the segmentation by a probabilistic constraint relaxation network. The experimental results show the efficient and robust performance of the new algorithm and that it outperforms the conventional classification based approaches. PMID:18172510

Distinct hippocampal functional networks revealed by tractography-based parcellation.

PubMed

Adnan, Areeba; Barnett, Alexander; Moayedi, Massieh; McCormick, Cornelia; Cohn, Melanie; McAndrews, Mary Pat

2016-07-01

Recent research suggests the anterior and posterior hippocampus form part of two distinct functional neural networks. Here we investigate the structural underpinnings of this functional connectivity difference using diffusion-weighted imaging-based parcellation. Using this technique, we substantiated that the hippocampus can be parcellated into distinct anterior and posterior segments. These structurally defined segments did indeed show different patterns of resting state functional connectivity, in that the anterior segment showed greater connectivity with temporal and orbitofrontal cortex, whereas the posterior segment was more highly connected to medial and lateral parietal cortex. Furthermore, we showed that the posterior hippocampal connectivity to memory processing regions, including the dorsolateral prefrontal cortex, parahippocampal, inferior temporal and fusiform gyri and the precuneus, predicted interindividual relational memory performance. These findings provide important support for the integration of structural and functional connectivity in understanding the brain networks underlying episodic memory.

Networks 90: Polymer Networks Group Meeting (10th) and IUPAC international Symposium on Polymer Networks (10th) Held in Jerusalem on 20-25 May 1990. Programme and Abstracts

DTIC Science & Technology

1990-05-25

INCLUDING ORIENTATIONAL INTERACTIONS BETWEEN CHAIN SEGMENTS B. Deloche, E.T. Samulski (France, USA) CHAIN SEGMENT ORDERING IN STRAINED BIMODAL P-2 PDMS...theory of elastomers is difficult because it requires a detailed study of many body interactions . A theory of elasticity must address the following: (1...a Kirchhoff matrix which describes the connectivity of the network (Kc) or the linear chains (Ku). The nonbonded interactions are handled with the

Detection of Gait Modes Using an Artificial Neural Network during Walking with a Powered Ankle-Foot Orthosis

PubMed Central

2016-01-01

This paper presents an algorithm, for use with a Portable Powered Ankle-Foot Orthosis (i.e., PPAFO) that can automatically detect changes in gait modes (level ground, ascent and descent of stairs or ramps), thus allowing for appropriate ankle actuation control during swing phase. An artificial neural network (ANN) algorithm used input signals from an inertial measurement unit and foot switches, that is, vertical velocity and segment angle of the foot. Output from the ANN was filtered and adjusted to generate a final data set used to classify different gait modes. Five healthy male subjects walked with the PPAFO on the right leg for two test scenarios (walking over level ground and up and down stairs or a ramp; three trials per scenario). Success rate was quantified by the number of correctly classified steps with respect to the total number of steps. The results indicated that the proposed algorithm's success rate was high (99.3%, 100%, and 98.3% for level, ascent, and descent modes in the stairs scenario, respectively; 98.9%, 97.8%, and 100% in the ramp scenario). The proposed algorithm continuously detected each step's gait mode with faster timing and higher accuracy compared to a previous algorithm that used a decision tree based on maximizing the reliability of the mode recognition. PMID:28070188

Characterizing system dynamics with a weighted and directed network constructed from time series data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sun, Xiaoran, E-mail: sxr0806@gmail.com; School of Mathematics and Statistics, The University of Western Australia, Crawley WA 6009; Small, Michael, E-mail: michael.small@uwa.edu.au

In this work, we propose a novel method to transform a time series into a weighted and directed network. For a given time series, we first generate a set of segments via a sliding window, and then use a doubly symbolic scheme to characterize every windowed segment by combining absolute amplitude information with an ordinal pattern characterization. Based on this construction, a network can be directly constructed from the given time series: segments corresponding to different symbol-pairs are mapped to network nodes and the temporal succession between nodes is represented by directed links. With this conversion, dynamics underlying the timemore » series has been encoded into the network structure. We illustrate the potential of our networks with a well-studied dynamical model as a benchmark example. Results show that network measures for characterizing global properties can detect the dynamical transitions in the underlying system. Moreover, we employ a random walk algorithm to sample loops in our networks, and find that time series with different dynamics exhibits distinct cycle structure. That is, the relative prevalence of loops with different lengths can be used to identify the underlying dynamics.« less

AISLE: an automatic volumetric segmentation method for the study of lung allometry.

PubMed

Ren, Hongliang; Kazanzides, Peter

2011-01-01

We developed a fully automatic segmentation method for volumetric CT (computer tomography) datasets to support construction of a statistical atlas for the study of allometric laws of the lung. The proposed segmentation method, AISLE (Automated ITK-Snap based on Level-set), is based on the level-set implementation from an existing semi-automatic segmentation program, ITK-Snap. AISLE can segment the lung field without human interaction and provide intermediate graphical results as desired. The preliminary experimental results show that the proposed method can achieve accurate segmentation, in terms of volumetric overlap metric, by comparing with the ground-truth segmentation performed by a radiologist.

Stream network and stream segment temperature models software

USGS Publications Warehouse

Bartholow, John

2010-01-01

This set of programs simulates steady-state stream temperatures throughout a dendritic stream network handling multiple time periods per year. The software requires a math co-processor and 384K RAM. Also included is a program (SSTEMP) designed to predict the steady state stream temperature within a single stream segment for a single time period.

Earthquake cycle modeling of multi-segmented faults: dynamic rupture and ground motion simulation of the 1992 Mw 7.3 Landers earthquake.

NASA Astrophysics Data System (ADS)

Petukhin, A.; Galvez, P.; Somerville, P.; Ampuero, J. P.

2017-12-01

We perform earthquake cycle simulations to study the characteristics of source scaling relations and strong ground motions and in multi-segmented fault ruptures. For earthquake cycle modeling, a quasi-dynamic solver (QDYN, Luo et al, 2016) is used to nucleate events and the fully dynamic solver (SPECFEM3D, Galvez et al., 2014, 2016) is used to simulate earthquake ruptures. The Mw 7.3 Landers earthquake has been chosen as a target earthquake to validate our methodology. The SCEC fault geometry for the three-segmented Landers rupture is included and extended at both ends to a total length of 200 km. We followed the 2-D spatial correlated Dc distributions based on Hillers et. al. (2007) that associates Dc distribution with different degrees of fault maturity. The fault maturity is related to the variability of Dc on a microscopic scale. Large variations of Dc represents immature faults and lower variations of Dc represents mature faults. Moreover we impose a taper (a-b) at the fault edges and limit the fault depth to 15 km. Using these settings, earthquake cycle simulations are performed to nucleate seismic events on different sections of the fault, and dynamic rupture modeling is used to propagate the ruptures. The fault segmentation brings complexity into the rupture process. For instance, the change of strike between fault segments enhances strong variations of stress. In fact, Oglesby and Mai (2012) show the normal stress varies from positive (clamping) to negative (unclamping) between fault segments, which leads to favorable or unfavorable conditions for rupture growth. To replicate these complexities and the effect of fault segmentation in the rupture process, we perform earthquake cycles with dynamic rupture modeling and generate events similar to the Mw 7.3 Landers earthquake. We extract the asperities of these events and analyze the scaling relations between rupture area, average slip and combined area of asperities versus moment magnitude. Finally, the simulated ground motions will be validated by comparison of simulated response spectra with recorded response spectra and with response spectra from ground motion prediction models. This research is sponsored by the Japan Nuclear Regulation Authority.

Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach.

PubMed

Valverde, Sergi; Cabezas, Mariano; Roura, Eloy; González-Villà, Sandra; Pareto, Deborah; Vilanova, Joan C; Ramió-Torrentà, Lluís; Rovira, Àlex; Oliver, Arnau; Lladó, Xavier

2017-07-15

In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume. Copyright © 2017 Elsevier Inc. All rights reserved.

Automated segmentation of lesions including subretinal hyperreflective material in neovascular age-related macular degeneration.

PubMed

Lee, Hyungwoo; Kang, Kyung Eun; Chung, Hyewon; Kim, Hyung Chan

2018-04-12

To evaluate an automated segmentation algorithm with a convolutional neural network (CNN) to quantify and detect intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED), and subretinal hyperreflective material (SHRM) through analyses of spectral domain optical coherence tomography (SD-OCT) images from patients with neovascular age-related macular degeneration (nAMD). Reliability and validity analysis of a diagnostic tool. We constructed a dataset including 930 B-scans from 93 eyes of 93 patients with nAMD. A CNN-based deep neural network was trained using 11550 augmented images derived from 550 B-scans. The performance of the trained network was evaluated using a validation set including 140 B-scans and a test set of 240 B-scans. The Dice coefficient, positive predictive value (PPV), sensitivity, relative area difference (RAD), and intraclass correlation coefficient (ICC) were used to evaluate segmentation and detection performance. Good agreement was observed for both segmentation and detection of lesions between the trained network and clinicians. The Dice coefficients for segmentation of IRF, SRF, SHRM, and PED were 0.78, 0.82, 0.75, and 0.80, respectively; the PPVs were 0.79, 0.80, 0.75, and 0.80, respectively; and the sensitivities were 0.77, 0.84, 0.73, and 0.81, respectively. The RADs were -4.32%, -10.29%, 4.13%, and 0.34%, respectively, and the ICCs were 0.98, 0.98, 0.97, and 0.98, respectively. All lesions were detected with high PPVs (range 0.94-0.99) and sensitivities (range 0.97-0.99). A CNN-based network provides clinicians with quantitative data regarding nAMD through automatic segmentation and detection of pathological lesions, including IRF, SRF, PED, and SHRM. Copyright © 2018 Elsevier Inc. All rights reserved.

Allocation of spectral and spatial modes in multidimensional metro-access optical networks

NASA Astrophysics Data System (ADS)

Gao, Wenbo; Cvijetic, Milorad

2018-04-01

Introduction of spatial division multiplexing (SDM) has added a new dimension in an effort to increase optical fiber channel capacity. At the same time, it can also be explored as an advanced optical networking tool. In this paper, we have investigated the resource allocation to end-users in multidimensional networking structure with plurality of spectral and spatial modes actively deployed in different networking segments. This presents a more comprehensive method as compared to the common practice where the segments of optical network are analyzed independently since the interaction between network hierarchies is included into consideration. We explored the possible transparency from the metro/core network to the optical access network, analyzed the potential bottlenecks from the network architecture perspective, and identified an optimized network structure. In our considerations, the viability of optical grooming through the entire hierarchical all-optical network is investigated by evaluating the effective utilization and spectral efficiency of the network architecture.

Automatic lung nodule graph cuts segmentation with deep learning false positive reduction

NASA Astrophysics Data System (ADS)

Sun, Wenqing; Huang, Xia; Tseng, Tzu-Liang Bill; Qian, Wei

2017-03-01

To automatic detect lung nodules from CT images, we designed a two stage computer aided detection (CAD) system. The first stage is graph cuts segmentation to identify and segment the nodule candidates, and the second stage is convolutional neural network for false positive reduction. The dataset contains 595 CT cases randomly selected from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) and the 305 pulmonary nodules achieved diagnosis consensus by all four experienced radiologists were our detection targets. Consider each slice as an individual sample, 2844 nodules were included in our database. The graph cuts segmentation was conducted in a two-dimension manner, 2733 lung nodule ROIs are successfully identified and segmented. With a false positive reduction by a seven-layer convolutional neural network, 2535 nodules remain detected while the false positive dropped to 31.6%. The average F-measure of segmented lung nodule tissue is 0.8501.

Network-level accident-mapping: Distance based pattern matching using artificial neural network.

PubMed

Deka, Lipika; Quddus, Mohammed

2014-04-01

The objective of an accident-mapping algorithm is to snap traffic accidents onto the correct road segments. Assigning accidents onto the correct segments facilitate to robustly carry out some key analyses in accident research including the identification of accident hot-spots, network-level risk mapping and segment-level accident risk modelling. Existing risk mapping algorithms have some severe limitations: (i) they are not easily 'transferable' as the algorithms are specific to given accident datasets; (ii) they do not perform well in all road-network environments such as in areas of dense road network; and (iii) the methods used do not perform well in addressing inaccuracies inherent in and type of road environment. The purpose of this paper is to develop a new accident mapping algorithm based on the common variables observed in most accident databases (e.g. road name and type, direction of vehicle movement before the accident and recorded accident location). The challenges here are to: (i) develop a method that takes into account uncertainties inherent to the recorded traffic accident data and the underlying digital road network data, (ii) accurately determine the type and proportion of inaccuracies, and (iii) develop a robust algorithm that can be adapted for any accident set and road network of varying complexity. In order to overcome these challenges, a distance based pattern-matching approach is used to identify the correct road segment. This is based on vectors containing feature values that are common in the accident data and the network data. Since each feature does not contribute equally towards the identification of the correct road segments, an ANN approach using the single-layer perceptron is used to assist in "learning" the relative importance of each feature in the distance calculation and hence the correct link identification. The performance of the developed algorithm was evaluated based on a reference accident dataset from the UK confirming that the accuracy is much better than other methods. Crown Copyright © 2014. Published by Elsevier Ltd. All rights reserved.

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

NASA Technical Reports Server (NTRS)

Hall, Lawrence O.; Bensaid, Amine M.; Clarke, Laurence P.; Velthuizen, Robert P.; Silbiger, Martin S.; Bezdek, James C.

1992-01-01

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms and a supervised computational neural network, a dynamic multilayered perception trained with the cascade correlation learning algorithm. Initial clinical results are presented on both normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. However, for a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed.

Transition from one revolving cluster to two revolving clusters in the ground-state rotational bands of nuclei in the lanthanon region.

PubMed

Pauling, L

1991-02-01

Whereas 234(92)U142 and other actinon nuclei have ground-state bands that indicate that each nucleus consists of a sphere and a single revolving cluster with constant composition and with only a steady increase in the moment of inertia with increase in J, the angular-momentum quantum number, many of the lanthanon ground-state bands show discontinuities, usually with an initial slightly or strongly curved segment followed by one or two nearly straight segments. The transition to nearly straight segments is interpreted as a change in structure from one revolving cluster to two revolving clusters. The proton-neutron compositions of the clusters and the central sphere are assigned, leading to values of the radius of revolution. The approximation of the two-cluster sequences to linearity is attributed to the very small values of the quadrupole polarizability of the central sphere. Values of the nucleon numbers of clusters and spheres, of the radius of revolution, and of promotion energy are discussed.

Promon's participation in the Brasilsat program: first & second generations

NASA Astrophysics Data System (ADS)

Depaiva, Ricardo N.

This paper presents an overview of the Brasilsat program, space and ground segments, developed by Hughes and Promon. Promon is a Brazilian engineering company that has been actively participating in the Brasilsat Satellite Telecommunications Program since its beginning. During the first generation, as subcontractor of the Spar/Hughes/SED consortium, Promon had a significant participation in the site installation of the Ground Segment, including the antennas. During the second generation, as partner of a consortium with Hughes, Promon participated in the upgrade of Brasilsat's Ground Segment systems: the TT&C (TCR1, TCR2, and SCC) and the COCC (Communications and Operations Control Center). This upgrade consisted of the design and development of hardware and software to support the second generation requirements, followed by integration and tests, factory acceptance tests, transport to site, site installation, site acceptance tests and warranty support. The upgraded systems are distributed over four sites with remote access to the main ground station. The solutions adopted provide a high level of automation, and easy operator interaction. The hardware and software technologies were selected to provide the flexibility to incorporate new technologies and services from the demanding satellite telecommunications market.

Fast algorithm for automatically computing Strahler stream order

USGS Publications Warehouse

Lanfear, Kenneth J.

1990-01-01

An efficient algorithm was developed to determine Strahler stream order for segments of stream networks represented in a Geographic Information System (GIS). The algorithm correctly assigns Strahler stream order in topologically complex situations such as braided streams and multiple drainage outlets. Execution time varies nearly linearly with the number of stream segments in the network. This technique is expected to be particularly useful for studying the topology of dense stream networks derived from digital elevation model data.

Nodal network generator for CAVE3

NASA Technical Reports Server (NTRS)

Palmieri, J. V.; Rathjen, K. A.

1982-01-01

A new extension of CAVE3 code was developed that automates the creation of a finite difference math model in digital form ready for input to the CAVE3 code. The new software, Nodal Network Generator, is broken into two segments. One segment generates the model geometry using a Tektronix Tablet Digitizer and the other generates the actual finite difference model and allows for graphic verification using Tektronix 4014 Graphic Scope. Use of the Nodal Network Generator is described.

The Deep Space Network

NASA Technical Reports Server (NTRS)

1979-01-01

Deep Space Network progress in flight project support, tracking and data acquisition, research and technology, network engineering, hardware and software implementation, and operations is cited. Topics covered include: tracking and ground based navigation; spacecraft/ground communication; station control and operations technology; ground communications; and deep space stations.

Joint Segmentation of Multiple Thoracic Organs in CT Images with Two Collaborative Deep Architectures.

PubMed

Trullo, Roger; Petitjean, Caroline; Nie, Dong; Shen, Dinggang; Ruan, Su

2017-09-01

Computed Tomography (CT) is the standard imaging technique for radiotherapy planning. The delineation of Organs at Risk (OAR) in thoracic CT images is a necessary step before radiotherapy, for preventing irradiation of healthy organs. However, due to low contrast, multi-organ segmentation is a challenge. In this paper, we focus on developing a novel framework for automatic delineation of OARs. Different from previous works in OAR segmentation where each organ is segmented separately, we propose two collaborative deep architectures to jointly segment all organs, including esophagus, heart, aorta and trachea. Since most of the organ borders are ill-defined, we believe spatial relationships must be taken into account to overcome the lack of contrast. The aim of combining two networks is to learn anatomical constraints with the first network, which will be used in the second network, when each OAR is segmented in turn. Specifically, we use the first deep architecture, a deep SharpMask architecture, for providing an effective combination of low-level representations with deep high-level features, and then take into account the spatial relationships between organs by the use of Conditional Random Fields (CRF). Next, the second deep architecture is employed to refine the segmentation of each organ by using the maps obtained on the first deep architecture to learn anatomical constraints for guiding and refining the segmentations. Experimental results show superior performance on 30 CT scans, comparing with other state-of-the-art methods.

High-Capacity Ground Communications to Support Future Space Missions: A Forecast of Ground Communications Challenges in the 2010-2020 Period

NASA Technical Reports Server (NTRS)

Markley, Richard W.

2003-01-01

The purpose of this presentation is to identify major challenges involved in space ground communications networks to support space flight missions over the next 20 years. The presentation focus is on the Deep Space Network and its customers, but the forecast is applicable to all space ground communications networks.

Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks.

PubMed

Bi, Lei; Kim, Jinman; Ahn, Euijoon; Kumar, Ashnil; Fulham, Michael; Feng, Dagan

2017-09-01

Segmentation of skin lesions is an important step in the automated computer aided diagnosis of melanoma. However, existing segmentation methods have a tendency to over- or under-segment the lesions and perform poorly when the lesions have fuzzy boundaries, low contrast with the background, inhomogeneous textures, or contain artifacts. Furthermore, the performance of these methods are heavily reliant on the appropriate tuning of a large number of parameters as well as the use of effective preprocessing techniques, such as illumination correction and hair removal. We propose to leverage fully convolutional networks (FCNs) to automatically segment the skin lesions. FCNs are a neural network architecture that achieves object detection by hierarchically combining low-level appearance information with high-level semantic information. We address the issue of FCN producing coarse segmentation boundaries for challenging skin lesions (e.g., those with fuzzy boundaries and/or low difference in the textures between the foreground and the background) through a multistage segmentation approach in which multiple FCNs learn complementary visual characteristics of different skin lesions; early stage FCNs learn coarse appearance and localization information while late-stage FCNs learn the subtle characteristics of the lesion boundaries. We also introduce a new parallel integration method to combine the complementary information derived from individual segmentation stages to achieve a final segmentation result that has accurate localization and well-defined lesion boundaries, even for the most challenging skin lesions. We achieved an average Dice coefficient of 91.18% on the ISBI 2016 Skin Lesion Challenge dataset and 90.66% on the PH2 dataset. Our extensive experimental results on two well-established public benchmark datasets demonstrate that our method is more effective than other state-of-the-art methods for skin lesion segmentation.

The collateral network concept: a reassessment of the anatomy of spinal cord perfusion.

PubMed

Etz, Christian D; Kari, Fabian A; Mueller, Christoph S; Silovitz, Daniel; Brenner, Robert M; Lin, Hung-Mo; Griepp, Randall B

2011-04-01

Prevention of paraplegia after repair of thoracoabdominal aortic aneurysm requires understanding the anatomy and physiology of the spinal cord blood supply. Recent laboratory studies and clinical observations suggest that a robust collateral network must exist to explain preservation of spinal cord perfusion when segmental vessels are interrupted. An anatomic study was undertaken. Twelve juvenile Yorkshire pigs underwent aortic cannulation and infusion of a low-viscosity acrylic resin at physiologic pressures. After curing of the resin and digestion of all organic tissue, the anatomy of the blood supply to the spinal cord was studied grossly and with light and electron microscopy. All vascular structures at least 8 μm in diameter were preserved. Thoracic and lumbar segmental arteries give rise not only to the anterior spinal artery but to an extensive paraspinous network feeding the erector spinae, iliopsoas, and associated muscles. The anterior spinal artery, mean diameter 134 ± 20 μm, is connected at multiple points to repetitive circular epidural arteries with mean diameters of 150 ± 26 μm. The capacity of the paraspinous muscular network is 25-fold the capacity of the circular epidural arterial network and anterior spinal artery combined. Extensive arterial collateralization is apparent between the intraspinal and paraspinous networks, and within each network. Only 75% of all segmental arteries provide direct anterior spinal artery-supplying branches. The anterior spinal artery is only one component of an extensive paraspinous and intraspinal collateral vascular network. This network provides an anatomic explanation of the physiological resiliency of spinal cord perfusion when segmental arteries are sacrificed during thoracoabdominal aortic aneurysm repair. Copyright © 2011 The American Association for Thoracic Surgery. Published by Mosby, Inc. All rights reserved.

Exploring the use of grounded theory as a methodological approach to examine the 'black box' of network leadership in the national quality forum.

PubMed

Hoflund, A Bryce

2013-01-01

This paper describes how grounded theory was used to investigate the "black box" of network leadership in the creation of the National Quality Forum. Scholars are beginning to recognize the importance of network organizations and are in the embryonic stages of collecting and analyzing data about network leadership processes. Grounded theory, with its focus on deriving theory from empirical data, offers researchers a distinctive way of studying little-known phenomena and is therefore well suited to exploring network leadership processes. Specifically, this paper provides an overview of grounded theory, a discussion of the appropriateness of grounded theory to investigating network phenomena, a description of how the research was conducted, and a discussion of the limitations and lessons learned from using this approach.

Design of a ground-water-quality monitoring network for the Salinas River basin, California

USGS Publications Warehouse

Showalter, P.K.; Akers, J.P.; Swain, L.A.

1984-01-01

A regional ground-water quality monitoring network for the entire Salinas River drainage basin was designed to meet the needs of the California State Water Resources Control Board. The project included phase 1--identifying monitoring networks that exist in the region; phase 2--collecting information about the wells in each network; and phase 3--studying the factors--such as geology, land use, hydrology, and geohydrology--that influence the ground-water quality, and designing a regional network. This report is the major product of phase 3. Based on the authors ' understanding of the ground-water-quality monitoring system and input from local offices, an ideal network was designed. The proposed network includes 317 wells and 8 stream-gaging stations. Because limited funds are available to implement the monitoring network, the proposed network is designed to correspond to the ideal network insofar as practicable, and is composed mainly of 214 wells that are already being monitored by a local agency. In areas where network wells are not available, arrangements will be made to add wells to local networks. The data collected by this network will be used to assess the ground-water quality of the entire Salinas River drainage basin. After 2 years of data are collected, the network will be evaluated to test whether it is meeting the network objectives. Subsequent network evaluations will be done very 5 years. (USGS)

A Comparison of Two Commercial Volumetry Software Programs in the Analysis of Pulmonary Ground-Glass Nodules: Segmentation Capability and Measurement Accuracy

PubMed Central

Kim, Hyungjin; Lee, Sang Min; Lee, Hyun-Ju; Goo, Jin Mo

2013-01-01

Objective To compare the segmentation capability of the 2 currently available commercial volumetry software programs with specific segmentation algorithms for pulmonary ground-glass nodules (GGNs) and to assess their measurement accuracy. Materials and Methods In this study, 55 patients with 66 GGNs underwent unenhanced low-dose CT. GGN segmentation was performed by using 2 volumetry software programs (LungCARE, Siemens Healthcare; LungVCAR, GE Healthcare). Successful nodule segmentation was assessed visually and morphologic features of GGNs were evaluated to determine factors affecting segmentation by both types of software. In addition, the measurement accuracy of the software programs was investigated by using an anthropomorphic chest phantom containing simulated GGNs. Results The successful nodule segmentation rate was significantly higher in LungCARE (90.9%) than in LungVCAR (72.7%) (p = 0.012). Vascular attachment was a negatively influencing morphologic feature of nodule segmentation for both software programs. As for measurement accuracy, mean relative volume measurement errors in nodules ≥ 10 mm were 14.89% with LungCARE and 19.96% with LungVCAR. The mean relative attenuation measurement errors in nodules ≥ 10 mm were 3.03% with LungCARE and 5.12% with LungVCAR. Conclusion LungCARE shows significantly higher segmentation success rates than LungVCAR. Measurement accuracy of volume and attenuation of GGNs is acceptable in GGNs ≥ 10 mm by both software programs. PMID:23901328

Multitask assessment of roads and vehicles network (MARVN)

NASA Astrophysics Data System (ADS)

Yang, Fang; Yi, Meng; Cai, Yiran; Blasch, Erik; Sullivan, Nichole; Sheaff, Carolyn; Chen, Genshe; Ling, Haibin

2018-05-01

Vehicle detection in wide area motion imagery (WAMI) has drawn increasing attention from the computer vision research community in recent decades. In this paper, we present a new architecture for vehicle detection on road using multi-task network, which is able to detect and segment vehicles, estimate their pose, and meanwhile yield road isolation for a given region. The multi-task network consists of three components: 1) vehicle detection, 2) vehicle and road segmentation, and 3) detection screening. Segmentation and detection components share the same backbone network and are trained jointly in an end-to-end way. Unlike background subtraction or frame differencing based methods, the proposed Multitask Assessment of Roads and Vehicles Network (MARVN) method can detect vehicles which are slowing down, stopped, and/or partially occluded in a single image. In addition, the method can eliminate the detections which are located at outside road using yielded road segmentation so as to decrease the false positive rate. As few WAMI datasets have road mask and vehicles bounding box anotations, we extract 512 frames from WPAFB 2009 dataset and carefully refine the original annotations. The resulting dataset is thus named as WAMI512. We extensively compare the proposed method with state-of-the-art methods on WAMI512 dataset, and demonstrate superior performance in terms of efficiency and accuracy.

Valley segments, stream reaches, and channel units [Chapter 2

Treesearch

Peter A. Bisson; David R. Montgomery; John M. Buffington

2006-01-01

Valley segments, stream reaches, and channel units are three hierarchically nested subdivisions of the drainage network (Frissell et al. 1986), falling in size between landscapes and watersheds (see Chapter 1) and individual point measurements made along the stream network (Table 2.1; also see Chapters 3 and 4). These three subdivisions compose the habitat for large,...

Traffic sign recognition by color segmentation and neural network

NASA Astrophysics Data System (ADS)

Surinwarangkoon, Thongchai; Nitsuwat, Supot; Moore, Elvin J.

2011-12-01

An algorithm is proposed for traffic sign detection and identification based on color filtering, color segmentation and neural networks. Traffic signs in Thailand are classified by color into four types: namely, prohibitory signs (red or blue), general warning signs (yellow) and construction area warning signs (amber). A color filtering method is first used to detect traffic signs and classify them by type. Then color segmentation methods adapted for each color type are used to extract inner features, e.g., arrows, bars etc. Finally, neural networks trained to recognize signs in each color type are used to identify any given traffic sign. Experiments show that the algorithm can improve the accuracy of traffic sign detection and recognition for the traffic signs used in Thailand.

Annual Industrial Capabilities Report to Congress

DTIC Science & Technology

2008-03-01

61 5.1 Aircraft Sector Industrial Summary...basis, key contractor workforce capabilities necessary for successful programs. Industry segment-level baseline assessments ( aircraft ; command, control...monitored representative individual corporate divisions for each major industry segment ( aircraft parts and components, water craft, ground vehicles

Composition and assembly of a spectral and agronomic data base for 1980 spring small grain segments

NASA Technical Reports Server (NTRS)

Helmer, D.; Krantz, J.; Kinsler, M.; Tomkins, M.

1983-01-01

A data set was assembled which consolidates the LANDSAT spectral data, ground truth observation data, and analyst cloud screening data for 28 spring small grain segments collected during the 1980 crop year.

Estimation of Blood Flow Rates in Large Microvascular Networks

PubMed Central

Fry, Brendan C.; Lee, Jack; Smith, Nicolas P.; Secomb, Timothy W.

2012-01-01

Objective Recent methods for imaging microvascular structures provide geometrical data on networks containing thousands of segments. Prediction of functional properties, such as solute transport, requires information on blood flow rates also, but experimental measurement of many individual flows is difficult. Here, a method is presented for estimating flow rates in a microvascular network based on incomplete information on the flows in the boundary segments that feed and drain the network. Methods With incomplete boundary data, the equations governing blood flow form an underdetermined linear system. An algorithm was developed that uses independent information about the distribution of wall shear stresses and pressures in microvessels to resolve this indeterminacy, by minimizing the deviation of pressures and wall shear stresses from target values. Results The algorithm was tested using previously obtained experimental flow data from four microvascular networks in the rat mesentery. With two or three prescribed boundary conditions, predicted flows showed relatively small errors in most segments and fewer than 10% incorrect flow directions on average. Conclusions The proposed method can be used to estimate flow rates in microvascular networks, based on incomplete boundary data and provides a basis for deducing functional properties of microvessel networks. PMID:22506980

The COSMO-SkyMed ground and ILS and OPS segments upgrades for full civilian capacity exploitation

NASA Astrophysics Data System (ADS)

Fasano, L.; De Luca, G. F.; Cardone, M.; Loizzo, R.; Sacco, P.; Daraio, M. G.

2015-10-01

COSMO-SkyMed (CSK), is an Earth Observation joint program between Agenzia Spaziale Italiana (Italian Space Agency, ASI) and Italian Ministry of Defense (It-MoD). It consists of a constellation of four X Band Synthetic Aperture Radar (SAR) whose first satellite of has been launched on June 2007. Today the full constellation is fully qualified and is in an operative phase. The COSMO-SkyMed System includes 3 Segments: the Space Segment, the Ground Segment and the Integrated Logistic Support and Operations Segment (ILS and OPS) As part of a more complex re-engineering process aimed to improve the expected constellation lifetime, to fully exploit several system capabilities, to manage the obsolescence, to reduce the maintenance costs and to exploit the entire constellation capability for Civilian users a series of activities have been performed. In the next months these activities are planned to be completed and start to be operational so that it will be possible the programming, planning, acquisition, raw processing and archiving of all the images that the constellation can acquire.

Spatial Statistics for Segmenting Histological Structures in H&E Stained Tissue Images.

PubMed

Nguyen, Luong; Tosun, Akif Burak; Fine, Jeffrey L; Lee, Adrian V; Taylor, D Lansing; Chennubhotla, S Chakra

2017-07-01

Segmenting a broad class of histological structures in transmitted light and/or fluorescence-based images is a prerequisite for determining the pathological basis of cancer, elucidating spatial interactions between histological structures in tumor microenvironments (e.g., tumor infiltrating lymphocytes), facilitating precision medicine studies with deep molecular profiling, and providing an exploratory tool for pathologists. This paper focuses on segmenting histological structures in hematoxylin- and eosin-stained images of breast tissues, e.g., invasive carcinoma, carcinoma in situ, atypical and normal ducts, adipose tissue, and lymphocytes. We propose two graph-theoretic segmentation methods based on local spatial color and nuclei neighborhood statistics. For benchmarking, we curated a data set of 232 high-power field breast tissue images together with expertly annotated ground truth. To accurately model the preference for histological structures (ducts, vessels, tumor nets, adipose, etc.) over the remaining connective tissue and non-tissue areas in ground truth annotations, we propose a new region-based score for evaluating segmentation algorithms. We demonstrate the improvement of our proposed methods over the state-of-the-art algorithms in both region- and boundary-based performance measures.

Comparison of thyroid segmentation techniques for 3D ultrasound

NASA Astrophysics Data System (ADS)

Wunderling, T.; Golla, B.; Poudel, P.; Arens, C.; Friebe, M.; Hansen, C.

2017-02-01

The segmentation of the thyroid in ultrasound images is a field of active research. The thyroid is a gland of the endocrine system and regulates several body functions. Measuring the volume of the thyroid is regular practice of diagnosing pathological changes. In this work, we compare three approaches for semi-automatic thyroid segmentation in freehand-tracked three-dimensional ultrasound images. The approaches are based on level set, graph cut and feature classification. For validation, sixteen 3D ultrasound records were created with ground truth segmentations, which we make publicly available. The properties analyzed are the Dice coefficient when compared against the ground truth reference and the effort of required interaction. Our results show that in terms of Dice coefficient, all algorithms perform similarly. For interaction, however, each algorithm has advantages over the other. The graph cut-based approach gives the practitioner direct influence on the final segmentation. Level set and feature classifier require less interaction, but offer less control over the result. All three compared methods show promising results for future work and provide several possible extensions.

ESTRACK Support for CCSDS Space Communication Cross Support Service Management

NASA Astrophysics Data System (ADS)

Dreihahn, H.; Unal, M.; Hoffmann, A.

2011-08-01

The CCSDS Recommended Standard for Space Communication Cross Support Service Management (SCCS SM) published as Blue Book in August 2009 is intended to provide standardised interfaces to negotiate, schedule, and manage the support of space missions by ground station network operators. ESA as a member of CCSDS has actively supported the development of the SCCS SM standard and is obviously interested in adopting it. Support of SCCS SM conforming interfaces and procedures includes:• Provision of SCCS SM conforming interfaces to non ESA missions;• Use of SCCS SM interfaces provided by other ground station operators to manage cross support of ESA missions;• In longer terms potentially use of SCCS SM interfaces and procedures also internally for support of ESA missions by ESTRACK.In the recent years ESOC has automated management and scheduling of ESA Tracking Network (ESTRACK) services by the specification, development, and deployment of the ESTRACK Management System (EMS), more specifically its planning and scheduling components ESTRACK Planning System and ESTRACK Scheduling System. While full support of the SCCS SM standard will involve also other elements of the ground segment operated by ESOC such as the Flight Dynamic System, EMS is at the core of service management and it is therefore appropriate to initially focus on the question to what extent EMS can support SCCS SM. This paper presents results of the initial analysis phase. After briefly presenting the SCCS SM standard and the relevant components of the ESTRACK management system, we will discuss the initial deployment options, open issues and a tentative roadmap for the way to proceed. Obviously the adoption of a cross support standard requires and discussion and coordination of the involved parties and agencies, especially in the light of the fact that the SCCS SM standard has many optional parts.

NPOESS C3S Expandability: SafetyNetTM and McMurdo Improvements

NASA Astrophysics Data System (ADS)

Jamilkowski, M. L.; Paciaroni, J.; Pela, F.

2010-12-01

The National Oceanic & Atmospheric Administration (NOAA), Department of Defense (DoD), and National Aeronautics & Space Administration (NASA) are jointly acquiring the next-generation weather & environmental satellite system; the National Polar-orbiting Operational Environmental Satellite System (NPOESS). NPOESS replaces the current NOAA Polar-orbiting Operational Environmental Satellites (POES) and Dod's Defense Meteorological Satellite Program (DMSP). The NPOESS satellites carry a suite of sensors that collect meteorological, oceanographic, climatological, and solar-geophysical observations of the earth, atmosphere, and space. The command & telemetry portion of NPOESS is the Command, Control and Communications Segment (C3S), developed by Raytheon Intelligence & Information Systems. C3S is responsible for managing the overall NPOESS mission from control and status of the space and ground assets to ensuring delivery of timely, high quality data from the Space Segment (SS) to the Interface Data Processing Segment (IDPS) for processing. In addition, the C3S provides the globally distributed ground assets necessary to collect and transport mission, telemetry, and command data between the satellites and the processing locations. The C3S provides all functions required for day-to-day commanding & state-of-health monitoring of the NPP & NPOESS satellites, and delivery of Stored Mission Data (SMD) to each US Weather Central Interface Data Processor (IDP) for data products development and transfer to System subscribers. The C3S also monitors and reports system-wide health and status & data communications with external systems and between NPOESS segments. Two crucial elements of NPOESS C3S expandability are SafetyNetTM and communications improvements to McMurdo Station, Antarctica. SafetyNetTM is a key feature of NPOESS and a vital element of the C3S and Northrop Grumman Aerospace Systems patented data collection architecture. The centerpiece of SafetyNetTM is the system of fifteen globally-distributed ground receptors developed by Raytheon Company. These antennae will collect up to five times as much environmental data approximately four times faster than current polar-orbiting weather satellites. Once collected, these data will be forwarded near-instantaneously to US weather centrals via the global fiber optic network for processing in environmental prediction models. In January 2008, Raytheon Company achieved a significant milestone for the NPOESS program by successfully completing the first phase of a major communications upgrade for Antarctica. The upgrade of the off-continent satellite communications link at McMurdo Station more than tripled the bandwidth available for scientific research, weather prediction, and health & safety of those stationed at McMurdo. The project is part of the company’s C3S under development for NPOESS. This upgrade paves the way for a second major communications upgrade planned for 2012 in preparation for the use of McMurdo Station as one of the 15 NPOESS ground stations worldwide that will be receiving environmental data collected by the NPOESS satellites. SafetyNet is a trademark of Northrop Grumman Aerospace Systems.

JPSS CGS Evolution

NASA Astrophysics Data System (ADS)

Miller, S. W.; Grant, K. D.; Jamilkowski, M. L.

2012-12-01

The National Oceanic and Atmospheric Administration (NOAA) and National Aeronautics and Space Administration (NASA) are jointly acquiring the next-generation civilian weather and environmental satellite system: the Joint Polar Satellite System (JPSS). JPSS will contribute the afternoon orbit component and ground processing system. As such, the Joint Polar Satellite System replaces the current Polar-orbiting Operational Environmental Satellites (POES) managed by NOAA. It also replaces the ground processing component of both Polar-orbiting Operational Environmental Satellites, as well as components of the Defense Meteorological Satellite Program (DMSP) replacement, previously known as the Defense Weather Satellite System (DWSS), managed by the Department of Defense (DoD). The JPSS satellites will carry a suite of sensors designed to collect meteorological, oceanographic, climatological and solar-geophysical observations of the earth, atmosphere and space. The ground processing system for JPSS is known as the JPSS Common Ground System (JPSS CGS), which consists of a Command, Control and Communications Segment (C3S) and an Interface Data Processing Segment (IDPS). Both segments are developed by Raytheon Intelligence and Information Systems (IIS). The C3S is currently flying the Suomi National Polar Partnership (Suomi NPP) satellite and transfers mission data from Suomi NPP and between the ground facilities. The IDPS processes Suomi NPP satellite data to provide Environmental Data Records (EDRs) to NOAA and DoD processing centers operated by the United States government. When the JPSS-1 satellite is launched in early 2017, the responsibilities of the C3S and the IDPS will be expanded to support both Suomi NPP and JPSS-1. The CGS also employs its ground stations at Svalbard, Norway and McMurdo Station, Antarctica, along with a global fiber communications network, to provide data acquisition and routing for multiple additional missions. These include POES, DMSP, NASA Space Communications and Navigation (SCaN, which includes the Earth Observing System [EOS]), Metop for the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT), Coriolis/WindSat for the DoD, as well as research activities of the National Science Foundation (NSF). The CGS architecture is evolving over the next few years for several key reasons: 1. "Operationalizing" Suomi NPP, which had originally been intended as a risk reduction mission 2. Leveraging lessons learned to date in multi-mission support 3. Taking advantage of newer, more reliable and efficient technologies 4. Satisfying new requirements and constraints due to the continually evolving budgetary environment Three key aspects of the CGS architecture are being prototyped as part of the path to improve operations in the 2015 timeframe. First, the front end architecture for mission data transport is being re-architected to improve reliability and address the incorporation of new ground stations. Second, the IDPS is undergoing a decoupling process to enhance its flexibility and modularity for supporting an array of potential new missions beyond those listed above. Finally, a solution for complete situational awareness across the CGS is being developed, to facilitate quicker and more efficient identification and resolution of system anomalies. This paper discusses the evolution of the CGS architecture to address these future mission needs.

Enhanced networks operations using the X Window System

NASA Technical Reports Server (NTRS)

Linares, Irving

1993-01-01

We propose an X Window Graphical User Interface (GUI) which is tailored to the operations of NASA GSFC's Network Control Center (NCC), the NASA Ground Terminal (NGT), the White Sands Ground Terminal (WSGT), and the Second Tracking and Data Relay Satellite System (TDRSS) Ground Terminal (STGT). The proposed GUI can also be easily extended to other Ground Network (GN) Tracking Stations due to its standardized nature.

A fourth order PDE based fuzzy c- means approach for segmentation of microscopic biopsy images in presence of Poisson noise for cancer detection.

PubMed

Kumar, Rajesh; Srivastava, Subodh; Srivastava, Rajeev

2017-07-01

For cancer detection from microscopic biopsy images, image segmentation step used for segmentation of cells and nuclei play an important role. Accuracy of segmentation approach dominate the final results. Also the microscopic biopsy images have intrinsic Poisson noise and if it is present in the image the segmentation results may not be accurate. The objective is to propose an efficient fuzzy c-means based segmentation approach which can also handle the noise present in the image during the segmentation process itself i.e. noise removal and segmentation is combined in one step. To address the above issues, in this paper a fourth order partial differential equation (FPDE) based nonlinear filter adapted to Poisson noise with fuzzy c-means segmentation method is proposed. This approach is capable of effectively handling the segmentation problem of blocky artifacts while achieving good tradeoff between Poisson noise removals and edge preservation of the microscopic biopsy images during segmentation process for cancer detection from cells. The proposed approach is tested on breast cancer microscopic biopsy data set with region of interest (ROI) segmented ground truth images. The microscopic biopsy data set contains 31 benign and 27 malignant images of size 896 × 768. The region of interest selected ground truth of all 58 images are also available for this data set. Finally, the result obtained from proposed approach is compared with the results of popular segmentation algorithms; fuzzy c-means, color k-means, texture based segmentation, and total variation fuzzy c-means approaches. The experimental results shows that proposed approach is providing better results in terms of various performance measures such as Jaccard coefficient, dice index, Tanimoto coefficient, area under curve, accuracy, true positive rate, true negative rate, false positive rate, false negative rate, random index, global consistency error, and variance of information as compared to other segmentation approaches used for cancer detection. Copyright © 2017 Elsevier B.V. All rights reserved.

Automated separation of merged Langerhans islets

NASA Astrophysics Data System (ADS)

Švihlík, Jan; Kybic, Jan; Habart, David

2016-03-01

This paper deals with separation of merged Langerhans islets in segmentations in order to evaluate correct histogram of islet diameters. A distribution of islet diameters is useful for determining the feasibility of islet transplantation in diabetes. First, the merged islets at training segmentations are manually separated by medical experts. Based on the single islets, the merged islets are identified and the SVM classifier is trained on both classes (merged/single islets). The testing segmentations were over-segmented using watershed transform and the most probable back merging of islets were found using trained SVM classifier. Finally, the optimized segmentation is compared with ground truth segmentation (correctly separated islets).

GPS net­work operations for the International GPS Geodynamics Service

USGS Publications Warehouse

Neilan, Ruth E.

1993-01-01

As GPS technology comes of age in the 1990’s, it is evident that an internationally sponsored GPS tracking system is called for to provide consistent, timely ground tracking data and data products to the geophysical community. The planning group for the International GPS Geodynamics Service (IGS), sponsored by the International Association of Geodesy (IAG), is addressing all elements of the end-to-end tracking system, ranging from data collection to data analysis and distribution of products (Mueller, 1992). Part of the planning process is to formulate how these various elements work together to create the common infrastructure needed to support a wide variety of GPS investigations. A key element for any permanent satellite tracking system is certainly the acquisition segment; the reliability and robustness of the ground network operations directly determine the fates and limitations of final products. The IGS planning group therefore included a committee tasked to develop and establish standards governing data acquisition and site-specific characteristics deemed necessary to ensure the collection of a high quality, continuous data set.

Simultaneous scalp electroencephalography (EEG), electromyography (EMG), and whole-body segmental inertial recording for multi-modal neural decoding.

PubMed

Bulea, Thomas C; Kilicarslan, Atilla; Ozdemir, Recep; Paloski, William H; Contreras-Vidal, Jose L

2013-07-26

Recent studies support the involvement of supraspinal networks in control of bipedal human walking. Part of this evidence encompasses studies, including our previous work, demonstrating that gait kinematics and limb coordination during treadmill walking can be inferred from the scalp electroencephalogram (EEG) with reasonably high decoding accuracies. These results provide impetus for development of non-invasive brain-machine-interface (BMI) systems for use in restoration and/or augmentation of gait- a primary goal of rehabilitation research. To date, studies examining EEG decoding of activity during gait have been limited to treadmill walking in a controlled environment. However, to be practically viable a BMI system must be applicable for use in everyday locomotor tasks such as over ground walking and turning. Here, we present a novel protocol for non-invasive collection of brain activity (EEG), muscle activity (electromyography (EMG)), and whole-body kinematic data (head, torso, and limb trajectories) during both treadmill and over ground walking tasks. By collecting these data in the uncontrolled environment insight can be gained regarding the feasibility of decoding unconstrained gait and surface EMG from scalp EEG.

Convolutional neural network regression for short-axis left ventricle segmentation in cardiac cine MR sequences.

PubMed

Tan, Li Kuo; Liew, Yih Miin; Lim, Einly; McLaughlin, Robert A

2017-07-01

Automated left ventricular (LV) segmentation is crucial for efficient quantification of cardiac function and morphology to aid subsequent management of cardiac pathologies. In this paper, we parameterize the complete (all short axis slices and phases) LV segmentation task in terms of the radial distances between the LV centerpoint and the endo- and epicardial contours in polar space. We then utilize convolutional neural network regression to infer these parameters. Utilizing parameter regression, as opposed to conventional pixel classification, allows the network to inherently reflect domain-specific physical constraints. We have benchmarked our approach primarily against the publicly-available left ventricle segmentation challenge (LVSC) dataset, which consists of 100 training and 100 validation cardiac MRI cases representing a heterogeneous mix of cardiac pathologies and imaging parameters across multiple centers. Our approach attained a .77 Jaccard index, which is the highest published overall result in comparison to other automated algorithms. To test general applicability, we also evaluated against the Kaggle Second Annual Data Science Bowl, where the evaluation metric was the indirect clinical measures of LV volume rather than direct myocardial contours. Our approach attained a Continuous Ranked Probability Score (CRPS) of .0124, which would have ranked tenth in the original challenge. With this we demonstrate the effectiveness of convolutional neural network regression paired with domain-specific features in clinical segmentation. Copyright © 2017 Elsevier B.V. All rights reserved.

Ground-motion signature of dynamic ruptures on rough faults

NASA Astrophysics Data System (ADS)

Mai, P. Martin; Galis, Martin; Thingbaijam, Kiran K. S.; Vyas, Jagdish C.

2016-04-01

Natural earthquakes occur on faults characterized by large-scale segmentation and small-scale roughness. This multi-scale geometrical complexity controls the dynamic rupture process, and hence strongly affects the radiated seismic waves and near-field shaking. For a fault system with given segmentation, the question arises what are the conditions for producing large-magnitude multi-segment ruptures, as opposed to smaller single-segment events. Similarly, for variable degrees of roughness, ruptures may be arrested prematurely or may break the entire fault. In addition, fault roughness induces rupture incoherence that determines the level of high-frequency radiation. Using HPC-enabled dynamic-rupture simulations, we generate physically self-consistent rough-fault earthquake scenarios (M~6.8) and their associated near-source seismic radiation. Because these computations are too expensive to be conducted routinely for simulation-based seismic hazard assessment, we thrive to develop an effective pseudo-dynamic source characterization that produces (almost) the same ground-motion characteristics. Therefore, we examine how variable degrees of fault roughness affect rupture properties and the seismic wavefield, and develop a planar-fault kinematic source representation that emulates the observed dynamic behaviour. We propose an effective workflow for improved pseudo-dynamic source modelling that incorporates rough-fault effects and its associated high-frequency radiation in broadband ground-motion computation for simulation-based seismic hazard assessment.

Machine Learning Technique to Find Quantum Many-Body Ground States of Bosons on a Lattice

NASA Astrophysics Data System (ADS)

Saito, Hiroki; Kato, Masaya

2018-01-01

We have developed a variational method to obtain many-body ground states of the Bose-Hubbard model using feedforward artificial neural networks. A fully connected network with a single hidden layer works better than a fully connected network with multiple hidden layers, and a multilayer convolutional network is more efficient than a fully connected network. AdaGrad and Adam are optimization methods that work well. Moreover, we show that many-body ground states with different numbers of particles can be generated by a single network.

Hubble Identifies Source of Ultraviolet Light in an Old Galaxy

NASA Technical Reports Server (NTRS)

2000-01-01

This videotape is comprised of four segments: (1) a Video zoom in on galaxy M32 using ground images, (2) Hubble images of galaxy M32, (3) Ground base color image of galaxies M31 and M32, and (4) Black and white ground based images of galaxy M32.

Neural network fusion: a novel CT-MR aortic aneurysm image segmentation method

NASA Astrophysics Data System (ADS)

Wang, Duo; Zhang, Rui; Zhu, Jin; Teng, Zhongzhao; Huang, Yuan; Spiga, Filippo; Du, Michael Hong-Fei; Gillard, Jonathan H.; Lu, Qingsheng; Liò, Pietro

2018-03-01

Medical imaging examination on patients usually involves more than one imaging modalities, such as Computed Tomography (CT), Magnetic Resonance (MR) and Positron Emission Tomography(PET) imaging. Multimodal imaging allows examiners to benefit from the advantage of each modalities. For example, for Abdominal Aortic Aneurysm, CT imaging shows calcium deposits in the aorta clearly while MR imaging distinguishes thrombus and soft tissues better.1 Analysing and segmenting both CT and MR images to combine the results will greatly help radiologists and doctors to treat the disease. In this work, we present methods on using deep neural network models to perform such multi-modal medical image segmentation. As CT image and MR image of the abdominal area cannot be well registered due to non-affine deformations, a naive approach is to train CT and MR segmentation network separately. However, such approach is time-consuming and resource-inefficient. We propose a new approach to fuse the high-level part of the CT and MR network together, hypothesizing that neurons recognizing the high level concepts of Aortic Aneurysm can be shared across multiple modalities. Such network is able to be trained end-to-end with non-registered CT and MR image using shorter training time. Moreover network fusion allows a shared representation of Aorta in both CT and MR images to be learnt. Through experiments we discovered that for parts of Aorta showing similar aneurysm conditions, their neural presentations in neural network has shorter distances. Such distances on the feature level is helpful for registering CT and MR image.

A Higher-Order Neural Network Design for Improving Segmentation Performance in Medical Image Series

NASA Astrophysics Data System (ADS)

Selvi, Eşref; Selver, M. Alper; Güzeliş, Cüneyt; Dicle, Oǧuz

2014-03-01

Segmentation of anatomical structures from medical image series is an ongoing field of research. Although, organs of interest are three-dimensional in nature, slice-by-slice approaches are widely used in clinical applications because of their ease of integration with the current manual segmentation scheme. To be able to use slice-by-slice techniques effectively, adjacent slice information, which represents likelihood of a region to be the structure of interest, plays critical role. Recent studies focus on using distance transform directly as a feature or to increase the feature values at the vicinity of the search area. This study presents a novel approach by constructing a higher order neural network, the input layer of which receives features together with their multiplications with the distance transform. This allows higher-order interactions between features through the non-linearity introduced by the multiplication. The application of the proposed method to 9 CT datasets for segmentation of the liver shows higher performance than well-known higher order classification neural networks.

The Time Course of Segmentation and Cue-Selectivity in the Human Visual Cortex

PubMed Central

Appelbaum, Lawrence G.; Ales, Justin M.; Norcia, Anthony M.

2012-01-01

Texture discontinuities are a fundamental cue by which the visual system segments objects from their background. The neural mechanisms supporting texture-based segmentation are therefore critical to visual perception and cognition. In the present experiment we employ an EEG source-imaging approach in order to study the time course of texture-based segmentation in the human brain. Visual Evoked Potentials were recorded to four types of stimuli in which periodic temporal modulation of a central 3° figure region could either support figure-ground segmentation, or have identical local texture modulations but not produce changes in global image segmentation. The image discontinuities were defined either by orientation or phase differences across image regions. Evoked responses to these four stimuli were analyzed both at the scalp and on the cortical surface in retinotopic and functional regions-of-interest (ROIs) defined separately using fMRI on a subject-by-subject basis. Texture segmentation (tsVEP: segmenting versus non-segmenting) and cue-specific (csVEP: orientation versus phase) responses exhibited distinctive patterns of activity. Alternations between uniform and segmented images produced highly asymmetric responses that were larger after transitions from the uniform to the segmented state. Texture modulations that signaled the appearance of a figure evoked a pattern of increased activity starting at ∼143 ms that was larger in V1 and LOC ROIs, relative to identical modulations that didn't signal figure-ground segmentation. This segmentation-related activity occurred after an initial response phase that did not depend on the global segmentation structure of the image. The two cue types evoked similar tsVEPs up to 230 ms when they differed in the V4 and LOC ROIs. The evolution of the response proceeded largely in the feed-forward direction, with only weak evidence for feedback-related activity. PMID:22479566

Simulation of brain tumors in MR images for evaluation of segmentation efficacy.

PubMed

Prastawa, Marcel; Bullitt, Elizabeth; Gerig, Guido

2009-04-01

Obtaining validation data and comparison metrics for segmentation of magnetic resonance images (MRI) are difficult tasks due to the lack of reliable ground truth. This problem is even more evident for images presenting pathology, which can both alter tissue appearance through infiltration and cause geometric distortions. Systems for generating synthetic images with user-defined degradation by noise and intensity inhomogeneity offer the possibility for testing and comparison of segmentation methods. Such systems do not yet offer simulation of sufficiently realistic looking pathology. This paper presents a system that combines physical and statistical modeling to generate synthetic multi-modal 3D brain MRI with tumor and edema, along with the underlying anatomical ground truth, Main emphasis is placed on simulation of the major effects known for tumor MRI, such as contrast enhancement, local distortion of healthy tissue, infiltrating edema adjacent to tumors, destruction and deformation of fiber tracts, and multi-modal MRI contrast of healthy tissue and pathology. The new method synthesizes pathology in multi-modal MRI and diffusion tensor imaging (DTI) by simulating mass effect, warping and destruction of white matter fibers, and infiltration of brain tissues by tumor cells. We generate synthetic contrast enhanced MR images by simulating the accumulation of contrast agent within the brain. The appearance of the the brain tissue and tumor in MRI is simulated by synthesizing texture images from real MR images. The proposed method is able to generate synthetic ground truth and synthesized MR images with tumor and edema that exhibit comparable segmentation challenges to real tumor MRI. Such image data sets will find use in segmentation reliability studies, comparison and validation of different segmentation methods, training and teaching, or even in evaluating standards for tumor size like the RECIST criteria (response evaluation criteria in solid tumors).

Translation-aware semantic segmentation via conditional least-square generative adversarial networks

NASA Astrophysics Data System (ADS)

Zhang, Mi; Hu, Xiangyun; Zhao, Like; Pang, Shiyan; Gong, Jinqi; Luo, Min

2017-10-01

Semantic segmentation has recently made rapid progress in the field of remote sensing and computer vision. However, many leading approaches cannot simultaneously translate label maps to possible source images with a limited number of training images. The core issue is insufficient adversarial information to interpret the inverse process and proper objective loss function to overcome the vanishing gradient problem. We propose the use of conditional least squares generative adversarial networks (CLS-GAN) to delineate visual objects and solve these problems. We trained the CLS-GAN network for semantic segmentation to discriminate dense prediction information either from training images or generative networks. We show that the optimal objective function of CLS-GAN is a special class of f-divergence and yields a generator that lies on the decision boundary of discriminator that reduces possible vanished gradient. We also demonstrate the effectiveness of the proposed architecture at translating images from label maps in the learning process. Experiments on a limited number of high resolution images, including close-range and remote sensing datasets, indicate that the proposed method leads to the improved semantic segmentation accuracy and can simultaneously generate high quality images from label maps.

Recurrent network dynamics reconciles visual motion segmentation and integration.

PubMed

Medathati, N V Kartheek; Rankin, James; Meso, Andrew I; Kornprobst, Pierre; Masson, Guillaume S

2017-09-12

In sensory systems, a range of computational rules are presumed to be implemented by neuronal subpopulations with different tuning functions. For instance, in primate cortical area MT, different classes of direction-selective cells have been identified and related either to motion integration, segmentation or transparency. Still, how such different tuning properties are constructed is unclear. The dominant theoretical viewpoint based on a linear-nonlinear feed-forward cascade does not account for their complex temporal dynamics and their versatility when facing different input statistics. Here, we demonstrate that a recurrent network model of visual motion processing can reconcile these different properties. Using a ring network, we show how excitatory and inhibitory interactions can implement different computational rules such as vector averaging, winner-take-all or superposition. The model also captures ordered temporal transitions between these behaviors. In particular, depending on the inhibition regime the network can switch from motion integration to segmentation, thus being able to compute either a single pattern motion or to superpose multiple inputs as in motion transparency. We thus demonstrate that recurrent architectures can adaptively give rise to different cortical computational regimes depending upon the input statistics, from sensory flow integration to segmentation.

Large deep neural networks for MS lesion segmentation

NASA Astrophysics Data System (ADS)

Prieto, Juan C.; Cavallari, Michele; Palotai, Miklos; Morales Pinzon, Alfredo; Egorova, Svetlana; Styner, Martin; Guttmann, Charles R. G.

2017-02-01

Multiple sclerosis (MS) is a multi-factorial autoimmune disorder, characterized by spatial and temporal dissemination of brain lesions that are visible in T2-weighted and Proton Density (PD) MRI. Assessment of lesion burden and is useful for monitoring the course of the disease, and assessing correlates of clinical outcomes. Although there are established semi-automated methods to measure lesion volume, most of them require human interaction and editing, which are time consuming and limits the ability to analyze large sets of data with high accuracy. The primary objective of this work is to improve existing segmentation algorithms and accelerate the time consuming operation of identifying and validating MS lesions. In this paper, a Deep Neural Network for MS Lesion Segmentation is implemented. The MS lesion samples are extracted from the Partners Comprehensive Longitudinal Investigation of Multiple Sclerosis (CLIMB) study. A set of 900 subjects with T2, PD and a manually corrected label map images were used to train a Deep Neural Network and identify MS lesions. Initial tests using this network achieved a 90% accuracy rate. A secondary goal was to enable this data repository for big data analysis by using this algorithm to segment the remaining cases available in the CLIMB repository.

The deep space network, volume 18. [Deep Space Instrumentation Facility, Ground Communication Facility, and Network Control System

NASA Technical Reports Server (NTRS)

1973-01-01

The objectives, functions, and organization of the Deep Space Network are summarized. The Deep Space Instrumentation Facility, the Ground Communications Facility, and the Network Control System are described.

Classification of microscopy images of Langerhans islets

NASA Astrophysics Data System (ADS)

Å vihlík, Jan; Kybic, Jan; Habart, David; Berková, Zuzana; Girman, Peter; Kříž, Jan; Zacharovová, Klára

2014-03-01

Evaluation of images of Langerhans islets is a crucial procedure for planning an islet transplantation, which is a promising diabetes treatment. This paper deals with segmentation of microscopy images of Langerhans islets and evaluation of islet parameters such as area, diameter, or volume (IE). For all the available images, the ground truth and the islet parameters were independently evaluated by four medical experts. We use a pixelwise linear classifier (perceptron algorithm) and SVM (support vector machine) for image segmentation. The volume is estimated based on circle or ellipse fitting to individual islets. The segmentations were compared with the corresponding ground truth. Quantitative islet parameters were also evaluated and compared with parameters given by medical experts. We can conclude that accuracy of the presented fully automatic algorithm is fully comparable with medical experts.

Visual probes and methods for placing visual probes into subsurface areas

DOEpatents

Clark, Don T.; Erickson, Eugene E.; Casper, William L.; Everett, David M.

2004-11-23

Visual probes and methods for placing visual probes into subsurface areas in either contaminated or non-contaminated sites are described. In one implementation, the method includes driving at least a portion of a visual probe into the ground using direct push, sonic drilling, or a combination of direct push and sonic drilling. Such is accomplished without providing an open pathway for contaminants or fugitive gases to reach the surface. According to one implementation, the invention includes an entry segment configured for insertion into the ground or through difficult materials (e.g., concrete, steel, asphalt, metals, or items associated with waste), at least one extension segment configured to selectively couple with the entry segment, at least one push rod, and a pressure cap. Additional implementations are contemplated.

Centralized vs decentralized options for an European Data Relay Satellite system

NASA Astrophysics Data System (ADS)

Saint Aubert, S.; Hervieux, M.; Perbos, J. L.; Saggese, E.; Soprano, C.

1985-10-01

The European Data Relay Satellite (DRS) is now being planned to support future European missions in the nineties and in particular the various elements of the in-orbit infrastructure. Studies are being conducted to investigate the usefulness of the relay system as well as to provide the basis for issuing technical specifications for a development and launch in 1993. This paper presents the results of a study issued by ESA on possible options for a DRS System, concentrating on the comparison between a centralized and a decentralized data distribution concept. After recalling the space programs foreseen in Europe, the paper discusses the architecture and design of the various elements of the System: space segment, DRS ground segment, and user ground segment for different options of data dissemination.

Centralized vs decentralized options for a european data relay satellite system

NASA Astrophysics Data System (ADS)

Aubert, Ph. Saint; Hervieux, M.; Perbos, J. L.; Saggese, E.; Soprano, C.

The European Data Relay Satellite (DRS) is now being planned to support future European missions in the nineties and in particular the various elements of the in-orbit infrastructure. Studies are being conducted to investigate the usefulness of the Relay System as well as to provide the basis for issuing technical specifications for a development and launch in 1993. This paper presents the results of a study issued by ESA on possible options for a DRS System, concentrating on the comparison between a centralized and a decentralized data distribution concept. After recalling the space programmes foreseen in Europe, the paper discusses the architecture and design of the various elements of the System: space segment, DRS ground segment and user ground segment for different options of data dissemination.

Space Shuttle Projects

NASA Image and Video Library

1978-09-01

This photograph shows stacking of the left side of the solid rocket booster (SRB) segments in the Dynamic Test Stand at the east test area of the Marshall Space Flight Center (MSFC). Staging shown here are the aft skirt, aft segment, and aft center segment. The SRB was attached to the external tank (ET) and then the orbiter later for the Mated Vertical Ground Vibration Test (MVGVT), that resumed in October 1978. The stacking of a complete Shuttle in the Dynamic Test Stand allowed test engineers to perform ground vibration testing on the Shuttle in its liftoff configuration. The purpose of the MVGVT is to verify that the Space Shuttle would perform as predicted during launch. The platforms inside the Dynamic Test Stand were modified to accommodate two SRB's to which the ET was attached.

Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.

Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology.

PubMed

Rachmadi, Muhammad Febrian; Valdés-Hernández, Maria Del C; Agan, Maria Leonora Fatimah; Di Perri, Carol; Komura, Taku

2018-06-01

We propose an adaptation of a convolutional neural network (CNN) scheme proposed for segmenting brain lesions with considerable mass-effect, to segment white matter hyperintensities (WMH) characteristic of brains with none or mild vascular pathology in routine clinical brain magnetic resonance images (MRI). This is a rather difficult segmentation problem because of the small area (i.e., volume) of the WMH and their similarity to non-pathological brain tissue. We investigate the effectiveness of the 2D CNN scheme by comparing its performance against those obtained from another deep learning approach: Deep Boltzmann Machine (DBM), two conventional machine learning approaches: Support Vector Machine (SVM) and Random Forest (RF), and a public toolbox: Lesion Segmentation Tool (LST), all reported to be useful for segmenting WMH in MRI. We also introduce a way to incorporate spatial information in convolution level of CNN for WMH segmentation named global spatial information (GSI). Analysis of covariance corroborated known associations between WMH progression, as assessed by all methods evaluated, and demographic and clinical data. Deep learning algorithms outperform conventional machine learning algorithms by excluding MRI artefacts and pathologies that appear similar to WMH. Our proposed approach of incorporating GSI also successfully helped CNN to achieve better automatic WMH segmentation regardless of network's settings tested. The mean Dice Similarity Coefficient (DSC) values for LST-LGA, SVM, RF, DBM, CNN and CNN-GSI were 0.2963, 0.1194, 0.1633, 0.3264, 0.5359 and 5389 respectively. Crown Copyright © 2018. Published by Elsevier Ltd. All rights reserved.

Automatic temporal segment detection via bilateral long short-term memory recurrent neural networks

NASA Astrophysics Data System (ADS)

Sun, Bo; Cao, Siming; He, Jun; Yu, Lejun; Li, Liandong

2017-03-01

Constrained by the physiology, the temporal factors associated with human behavior, irrespective of facial movement or body gesture, are described by four phases: neutral, onset, apex, and offset. Although they may benefit related recognition tasks, it is not easy to accurately detect such temporal segments. An automatic temporal segment detection framework using bilateral long short-term memory recurrent neural networks (BLSTM-RNN) to learn high-level temporal-spatial features, which synthesizes the local and global temporal-spatial information more efficiently, is presented. The framework is evaluated in detail over the face and body database (FABO). The comparison shows that the proposed framework outperforms state-of-the-art methods for solving the problem of temporal segment detection.

Fully automatic cervical vertebrae segmentation framework for X-ray images.

PubMed

Al Arif, S M Masudur Rahman; Knapp, Karen; Slabaugh, Greg

2018-04-01

The cervical spine is a highly flexible anatomy and therefore vulnerable to injuries. Unfortunately, a large number of injuries in lateral cervical X-ray images remain undiagnosed due to human errors. Computer-aided injury detection has the potential to reduce the risk of misdiagnosis. Towards building an automatic injury detection system, in this paper, we propose a deep learning-based fully automatic framework for segmentation of cervical vertebrae in X-ray images. The framework first localizes the spinal region in the image using a deep fully convolutional neural network. Then vertebra centers are localized using a novel deep probabilistic spatial regression network. Finally, a novel shape-aware deep segmentation network is used to segment the vertebrae in the image. The framework can take an X-ray image and produce a vertebrae segmentation result without any manual intervention. Each block of the fully automatic framework has been trained on a set of 124 X-ray images and tested on another 172 images, all collected from real-life hospital emergency rooms. A Dice similarity coefficient of 0.84 and a shape error of 1.69 mm have been achieved. Copyright © 2018 Elsevier B.V. All rights reserved.

A top-down manner-based DCNN architecture for semantic image segmentation.

PubMed

Qiao, Kai; Chen, Jian; Wang, Linyuan; Zeng, Lei; Yan, Bin

2017-01-01

Given their powerful feature representation for recognition, deep convolutional neural networks (DCNNs) have been driving rapid advances in high-level computer vision tasks. However, their performance in semantic image segmentation is still not satisfactory. Based on the analysis of visual mechanism, we conclude that DCNNs in a bottom-up manner are not enough, because semantic image segmentation task requires not only recognition but also visual attention capability. In the study, superpixels containing visual attention information are introduced in a top-down manner, and an extensible architecture is proposed to improve the segmentation results of current DCNN-based methods. We employ the current state-of-the-art fully convolutional network (FCN) and FCN with conditional random field (DeepLab-CRF) as baselines to validate our architecture. Experimental results of the PASCAL VOC segmentation task qualitatively show that coarse edges and error segmentation results are well improved. We also quantitatively obtain about 2%-3% intersection over union (IOU) accuracy improvement on the PASCAL VOC 2011 and 2012 test sets.

Combined texture feature analysis of segmentation and classification of benign and malignant tumour CT slices.

PubMed

Padma, A; Sukanesh, R

2013-01-01

A computer software system is designed for the segmentation and classification of benign from malignant tumour slices in brain computed tomography (CT) images. This paper presents a method to find and select both the dominant run length and co-occurrence texture features of region of interest (ROI) of the tumour region of each slice to be segmented by Fuzzy c means clustering (FCM) and evaluate the performance of support vector machine (SVM)-based classifiers in classifying benign and malignant tumour slices. Two hundred and six tumour confirmed CT slices are considered in this study. A total of 17 texture features are extracted by a feature extraction procedure, and six features are selected using Principal Component Analysis (PCA). This study constructed the SVM-based classifier with the selected features and by comparing the segmentation results with the experienced radiologist labelled ground truth (target). Quantitative analysis between ground truth and segmented tumour is presented in terms of segmentation accuracy, segmentation error and overlap similarity measures such as the Jaccard index. The classification performance of the SVM-based classifier with the same selected features is also evaluated using a 10-fold cross-validation method. The proposed system provides some newly found texture features have an important contribution in classifying benign and malignant tumour slices efficiently and accurately with less computational time. The experimental results showed that the proposed system is able to achieve the highest segmentation and classification accuracy effectiveness as measured by jaccard index and sensitivity and specificity.

Brain tumor segmentation based on local independent projection-based classification.

PubMed

Huang, Meiyan; Yang, Wei; Wu, Yao; Jiang, Jun; Chen, Wufan; Feng, Qianjin

2014-10-01

Brain tumor segmentation is an important procedure for early tumor diagnosis and radiotherapy planning. Although numerous brain tumor segmentation methods have been presented, enhancing tumor segmentation methods is still challenging because brain tumor MRI images exhibit complex characteristics, such as high diversity in tumor appearance and ambiguous tumor boundaries. To address this problem, we propose a novel automatic tumor segmentation method for MRI images. This method treats tumor segmentation as a classification problem. Additionally, the local independent projection-based classification (LIPC) method is used to classify each voxel into different classes. A novel classification framework is derived by introducing the local independent projection into the classical classification model. Locality is important in the calculation of local independent projections for LIPC. Locality is also considered in determining whether local anchor embedding is more applicable in solving linear projection weights compared with other coding methods. Moreover, LIPC considers the data distribution of different classes by learning a softmax regression model, which can further improve classification performance. In this study, 80 brain tumor MRI images with ground truth data are used as training data and 40 images without ground truth data are used as testing data. The segmentation results of testing data are evaluated by an online evaluation tool. The average dice similarities of the proposed method for segmenting complete tumor, tumor core, and contrast-enhancing tumor on real patient data are 0.84, 0.685, and 0.585, respectively. These results are comparable to other state-of-the-art methods.

A novel adaptive scoring system for segmentation validation with multiple reference masks

NASA Astrophysics Data System (ADS)

Moltz, Jan H.; Rühaak, Jan; Hahn, Horst K.; Peitgen, Heinz-Otto

2011-03-01

The development of segmentation algorithms for different anatomical structures and imaging protocols is an important task in medical image processing. The validation of these methods, however, is often treated as a subordinate task. Since manual delineations, which are widely used as a surrogate for the ground truth, exhibit an inherent uncertainty, it is preferable to use multiple reference segmentations for an objective validation. This requires a consistent framework that should fulfill three criteria: 1) it should treat all reference masks equally a priori and not demand consensus between the experts; 2) it should evaluate the algorithmic performance in relation to the inter-reference variability, i.e., be more tolerant where the experts disagree about the true segmentation; 3) it should produce results that are comparable for different test data. We show why current state-of-the-art frameworks as the one used at several MICCAI segmentation challenges do not fulfill these criteria and propose a new validation methodology. A score is computed in an adaptive way for each individual segmentation problem, using a combination of volume- and surface-based comparison metrics. These are transformed into the score by relating them to the variability between the reference masks which can be measured by comparing the masks with each other or with an estimated ground truth. We present examples from a study on liver tumor segmentation in CT scans where our score shows a more adequate assessment of the segmentation results than the MICCAI framework.

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields

PubMed Central

Robinson, Sean; Guyon, Laurent; Nevalainen, Jaakko; Toriseva, Mervi

2015-01-01

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy. PMID:26630674

Segmentation of Image Data from Complex Organotypic 3D Models of Cancer Tissues with Markov Random Fields.

PubMed

Robinson, Sean; Guyon, Laurent; Nevalainen, Jaakko; Toriseva, Mervi; Åkerfelt, Malin; Nees, Matthias

2015-01-01

Organotypic, three dimensional (3D) cell culture models of epithelial tumour types such as prostate cancer recapitulate key aspects of the architecture and histology of solid cancers. Morphometric analysis of multicellular 3D organoids is particularly important when additional components such as the extracellular matrix and tumour microenvironment are included in the model. The complexity of such models has so far limited their successful implementation. There is a great need for automatic, accurate and robust image segmentation tools to facilitate the analysis of such biologically relevant 3D cell culture models. We present a segmentation method based on Markov random fields (MRFs) and illustrate our method using 3D stack image data from an organotypic 3D model of prostate cancer cells co-cultured with cancer-associated fibroblasts (CAFs). The 3D segmentation output suggests that these cell types are in physical contact with each other within the model, which has important implications for tumour biology. Segmentation performance is quantified using ground truth labels and we show how each step of our method increases segmentation accuracy. We provide the ground truth labels along with the image data and code. Using independent image data we show that our segmentation method is also more generally applicable to other types of cellular microscopy and not only limited to fluorescence microscopy.

Object Segmentation and Ground Truth in 3D Embryonic Imaging.

PubMed

Rajasekaran, Bhavna; Uriu, Koichiro; Valentin, Guillaume; Tinevez, Jean-Yves; Oates, Andrew C

2016-01-01

Many questions in developmental biology depend on measuring the position and movement of individual cells within developing embryos. Yet, tools that provide this data are often challenged by high cell density and their accuracy is difficult to measure. Here, we present a three-step procedure to address this problem. Step one is a novel segmentation algorithm based on image derivatives that, in combination with selective post-processing, reliably and automatically segments cell nuclei from images of densely packed tissue. Step two is a quantitative validation using synthetic images to ascertain the efficiency of the algorithm with respect to signal-to-noise ratio and object density. Finally, we propose an original method to generate reliable and experimentally faithful ground truth datasets: Sparse-dense dual-labeled embryo chimeras are used to unambiguously measure segmentation errors within experimental data. Together, the three steps outlined here establish a robust, iterative procedure to fine-tune image analysis algorithms and microscopy settings associated with embryonic 3D image data sets.

Object Segmentation and Ground Truth in 3D Embryonic Imaging

PubMed Central

Rajasekaran, Bhavna; Uriu, Koichiro; Valentin, Guillaume; Tinevez, Jean-Yves; Oates, Andrew C.

2016-01-01

Many questions in developmental biology depend on measuring the position and movement of individual cells within developing embryos. Yet, tools that provide this data are often challenged by high cell density and their accuracy is difficult to measure. Here, we present a three-step procedure to address this problem. Step one is a novel segmentation algorithm based on image derivatives that, in combination with selective post-processing, reliably and automatically segments cell nuclei from images of densely packed tissue. Step two is a quantitative validation using synthetic images to ascertain the efficiency of the algorithm with respect to signal-to-noise ratio and object density. Finally, we propose an original method to generate reliable and experimentally faithful ground truth datasets: Sparse-dense dual-labeled embryo chimeras are used to unambiguously measure segmentation errors within experimental data. Together, the three steps outlined here establish a robust, iterative procedure to fine-tune image analysis algorithms and microscopy settings associated with embryonic 3D image data sets. PMID:27332860

Learning normalized inputs for iterative estimation in medical image segmentation.

PubMed

Drozdzal, Michal; Chartrand, Gabriel; Vorontsov, Eugene; Shakeri, Mahsa; Di Jorio, Lisa; Tang, An; Romero, Adriana; Bengio, Yoshua; Pal, Chris; Kadoury, Samuel

2018-02-01

In this paper, we introduce a simple, yet powerful pipeline for medical image segmentation that combines Fully Convolutional Networks (FCNs) with Fully Convolutional Residual Networks (FC-ResNets). We propose and examine a design that takes particular advantage of recent advances in the understanding of both Convolutional Neural Networks as well as ResNets. Our approach focuses upon the importance of a trainable pre-processing when using FC-ResNets and we show that a low-capacity FCN model can serve as a pre-processor to normalize medical input data. In our image segmentation pipeline, we use FCNs to obtain normalized images, which are then iteratively refined by means of a FC-ResNet to generate a segmentation prediction. As in other fully convolutional approaches, our pipeline can be used off-the-shelf on different image modalities. We show that using this pipeline, we exhibit state-of-the-art performance on the challenging Electron Microscopy benchmark, when compared to other 2D methods. We improve segmentation results on CT images of liver lesions, when contrasting with standard FCN methods. Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods. The obtained results illustrate the strong potential and versatility of the pipeline by achieving accurate segmentations on a variety of image modalities and different anatomical regions. Copyright © 2017 Elsevier B.V. All rights reserved.

Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation.

PubMed

Brosch, Tom; Tang, Lisa Y W; Youngjin Yoo; Li, David K B; Traboulsee, Anthony; Tam, Roger

2016-05-01

We propose a novel segmentation approach based on deep 3D convolutional encoder networks with shortcut connections and apply it to the segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. Our model is a neural network that consists of two interconnected pathways, a convolutional pathway, which learns increasingly more abstract and higher-level image features, and a deconvolutional pathway, which predicts the final segmentation at the voxel level. The joint training of the feature extraction and prediction pathways allows for the automatic learning of features at different scales that are optimized for accuracy for any given combination of image types and segmentation task. In addition, shortcut connections between the two pathways allow high- and low-level features to be integrated, which enables the segmentation of lesions across a wide range of sizes. We have evaluated our method on two publicly available data sets (MICCAI 2008 and ISBI 2015 challenges) with the results showing that our method performs comparably to the top-ranked state-of-the-art methods, even when only relatively small data sets are available for training. In addition, we have compared our method with five freely available and widely used MS lesion segmentation methods (EMS, LST-LPA, LST-LGA, Lesion-TOADS, and SLS) on a large data set from an MS clinical trial. The results show that our method consistently outperforms these other methods across a wide range of lesion sizes.

Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks.

PubMed

Yu, Lequan; Chen, Hao; Dou, Qi; Qin, Jing; Heng, Pheng-Ann

2017-04-01

Automated melanoma recognition in dermoscopy images is a very challenging task due to the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of many artifacts in the image. In order to meet these challenges, we propose a novel method for melanoma recognition by leveraging very deep convolutional neural networks (CNNs). Compared with existing methods employing either low-level hand-crafted features or CNNs with shallower architectures, our substantially deeper networks (more than 50 layers) can acquire richer and more discriminative features for more accurate recognition. To take full advantage of very deep networks, we propose a set of schemes to ensure effective training and learning under limited training data. First, we apply the residual learning to cope with the degradation and overfitting problems when a network goes deeper. This technique can ensure that our networks benefit from the performance gains achieved by increasing network depth. Then, we construct a fully convolutional residual network (FCRN) for accurate skin lesion segmentation, and further enhance its capability by incorporating a multi-scale contextual information integration scheme. Finally, we seamlessly integrate the proposed FCRN (for segmentation) and other very deep residual networks (for classification) to form a two-stage framework. This framework enables the classification network to extract more representative and specific features based on segmented results instead of the whole dermoscopy images, further alleviating the insufficiency of training data. The proposed framework is extensively evaluated on ISBI 2016 Skin Lesion Analysis Towards Melanoma Detection Challenge dataset. Experimental results demonstrate the significant performance gains of the proposed framework, ranking the first in classification and the second in segmentation among 25 teams and 28 teams, respectively. This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chang, J; Gu, X; Lu, W

Purpose: A novel distance-dose weighting method for label fusion was developed to increase segmentation accuracy in dosimetrically important regions for prostate radiation therapy. Methods: Label fusion as implemented in the original SIMPLE (OS) for multi-atlas segmentation relies iteratively on the majority vote to generate an estimated ground truth and DICE similarity measure to screen candidates. The proposed distance-dose weighting puts more values on dosimetrically important regions when calculating similarity measure. Specifically, we introduced distance-to-dose error (DDE), which converts distance to dosimetric importance, in performance evaluation. The DDE calculates an estimated DE error derived from surface distance differences between the candidatemore » and estimated ground truth label by multiplying a regression coefficient. To determine the coefficient at each simulation point on the rectum, we fitted DE error with respect to simulated voxel shift. The DEs were calculated by the multi-OAR geometry-dosimetry training model previously developed in our research group. Results: For both the OS and the distance-dose weighted SIMPLE (WS) results, the evaluation metrics for twenty patients were calculated using the ground truth segmentation. The mean difference of DICE, Hausdorff distance, and mean absolute distance (MAD) between OS and WS have shown 0, 0.10, and 0.11, respectively. In partial MAD of WS which calculates MAD within a certain PTV expansion voxel distance, the lower MADs were observed at the closer distances from 1 to 8 than those of OS. The DE results showed that the segmentation from WS produced more accurate results than OS. The mean DE error of V75, V70, V65, and V60 were decreased by 1.16%, 1.17%, 1.14%, and 1.12%, respectively. Conclusion: We have demonstrated that the method can increase the segmentation accuracy in rectum regions adjacent to PTV. As a result, segmentation using WS have shown improved dosimetric accuracy than OS. The WS will provide dosimetrically important label selection strategy in multi-atlas segmentation. CPRIT grant RP150485.« less

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain.

PubMed

Hall, L O; Bensaid, A M; Clarke, L P; Velthuizen, R P; Silbiger, M S; Bezdek, J C

1992-01-01

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms, and a supervised computational neural network. Initial clinical results are presented on normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. For a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed, with fuzz-c-means approaches being slightly preferred over feedforward cascade correlation results. Various facets of both approaches, such as supervised versus unsupervised learning, time complexity, and utility for the diagnostic process, are compared.

Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks.

PubMed

Joshi, Vinayak S; Reinhardt, Joseph M; Garvin, Mona K; Abramoff, Michael D

2014-01-01

The separation of the retinal vessel network into distinct arterial and venous vessel trees is of high interest. We propose an automated method for identification and separation of retinal vessel trees in a retinal color image by converting a vessel segmentation image into a vessel segment map and identifying the individual vessel trees by graph search. Orientation, width, and intensity of each vessel segment are utilized to find the optimal graph of vessel segments. The separated vessel trees are labeled as primary vessel or branches. We utilize the separated vessel trees for arterial-venous (AV) classification, based on the color properties of the vessels in each tree graph. We applied our approach to a dataset of 50 fundus images from 50 subjects. The proposed method resulted in an accuracy of 91.44% correctly classified vessel pixels as either artery or vein. The accuracy of correctly classified major vessel segments was 96.42%.

A coarse-to-fine approach for pericardial effusion localization and segmentation in chest CT scans

NASA Astrophysics Data System (ADS)

Liu, Jiamin; Chellamuthu, Karthik; Lu, Le; Bagheri, Mohammadhadi; Summers, Ronald M.

2018-02-01

Pericardial effusion on CT scans demonstrates very high shape and volume variability and very low contrast to adjacent structures. This inhibits traditional automated segmentation methods from achieving high accuracies. Deep neural networks have been widely used for image segmentation in CT scans. In this work, we present a two-stage method for pericardial effusion localization and segmentation. For the first step, we localize the pericardial area from the entire CT volume, providing a reliable bounding box for the more refined segmentation step. A coarse-scaled holistically-nested convolutional networks (HNN) model is trained on entire CT volume. The resulting HNN per-pixel probability maps are then threshold to produce a bounding box covering the pericardial area. For the second step, a fine-scaled HNN model is trained only on the bounding box region for effusion segmentation to reduce the background distraction. Quantitative evaluation is performed on a dataset of 25 CT scans of patient (1206 images) with pericardial effusion. The segmentation accuracy of our two-stage method, measured by Dice Similarity Coefficient (DSC), is 75.59+/-12.04%, which is significantly better than the segmentation accuracy (62.74+/-15.20%) of only using the coarse-scaled HNN model.

Protecting core networks with dual-homing: A study on enhanced network availability, resource efficiency, and energy-savings

NASA Astrophysics Data System (ADS)

Abeywickrama, Sandu; Furdek, Marija; Monti, Paolo; Wosinska, Lena; Wong, Elaine

2016-12-01

Core network survivability affects the reliability performance of telecommunication networks and remains one of the most important network design considerations. This paper critically examines the benefits arising from utilizing dual-homing in the optical access networks to provide resource-efficient protection against link and node failures in the optical core segment. Four novel, heuristic-based RWA algorithms that provide dedicated path protection in networks with dual-homing are proposed and studied. These algorithms protect against different failure scenarios (i.e. single link or node failures) and are implemented with different optimization objectives (i.e., minimization of wavelength usage and path length). Results obtained through simulations and comparison with baseline architectures indicate that exploiting dual-homed architecture in the access segment can bring significant improvements in terms of core network resource usage, connection availability, and power consumption.

a Universal De-Noising Algorithm for Ground-Based LIDAR Signal

NASA Astrophysics Data System (ADS)

Ma, Xin; Xiang, Chengzhi; Gong, Wei

2016-06-01

Ground-based lidar, working as an effective remote sensing tool, plays an irreplaceable role in the study of atmosphere, since it has the ability to provide the atmospheric vertical profile. However, the appearance of noise in a lidar signal is unavoidable, which leads to difficulties and complexities when searching for more information. Every de-noising method has its own characteristic but with a certain limitation, since the lidar signal will vary with the atmosphere changes. In this paper, a universal de-noising algorithm is proposed to enhance the SNR of a ground-based lidar signal, which is based on signal segmentation and reconstruction. The signal segmentation serving as the keystone of the algorithm, segments the lidar signal into three different parts, which are processed by different de-noising method according to their own characteristics. The signal reconstruction is a relatively simple procedure that is to splice the signal sections end to end. Finally, a series of simulation signal tests and real dual field-of-view lidar signal shows the feasibility of the universal de-noising algorithm.

Multi-objects recognition for distributed intelligent sensor networks

NASA Astrophysics Data System (ADS)

He, Haibo; Chen, Sheng; Cao, Yuan; Desai, Sachi; Hohil, Myron E.

2008-04-01

This paper proposes an innovative approach for multi-objects recognition for homeland security and defense based intelligent sensor networks. Unlike the conventional way of information analysis, data mining in such networks is typically characterized with high information ambiguity/uncertainty, data redundancy, high dimensionality and real-time constrains. Furthermore, since a typical military based network normally includes multiple mobile sensor platforms, ground forces, fortified tanks, combat flights, and other resources, it is critical to develop intelligent data mining approaches to fuse different information resources to understand dynamic environments, to support decision making processes, and finally to achieve the goals. This paper aims to address these issues with a focus on multi-objects recognition. Instead of classifying a single object as in the traditional image classification problems, the proposed method can automatically learn multiple objectives simultaneously. Image segmentation techniques are used to identify the interesting regions in the field, which correspond to multiple objects such as soldiers or tanks. Since different objects will come with different feature sizes, we propose a feature scaling method to represent each object in the same number of dimensions. This is achieved by linear/nonlinear scaling and sampling techniques. Finally, support vector machine (SVM) based learning algorithms are developed to learn and build the associations for different objects, and such knowledge will be adaptively accumulated for objects recognition in the testing stage. We test the effectiveness of proposed method in different simulated military environments.

Deep Deconvolutional Neural Network for Target Segmentation of Nasopharyngeal Cancer in Planning Computed Tomography Images.

PubMed

Men, Kuo; Chen, Xinyuan; Zhang, Ye; Zhang, Tao; Dai, Jianrong; Yi, Junlin; Li, Yexiong

2017-01-01

Radiotherapy is one of the main treatment methods for nasopharyngeal carcinoma (NPC). It requires exact delineation of the nasopharynx gross tumor volume (GTVnx), the metastatic lymph node gross tumor volume (GTVnd), the clinical target volume (CTV), and organs at risk in the planning computed tomography images. However, this task is time-consuming and operator dependent. In the present study, we developed an end-to-end deep deconvolutional neural network (DDNN) for segmentation of these targets. The proposed DDNN is an end-to-end architecture enabling fast training and testing. It consists of two important components: an encoder network and a decoder network. The encoder network was used to extract the visual features of a medical image and the decoder network was used to recover the original resolution by deploying deconvolution. A total of 230 patients diagnosed with NPC stage I or stage II were included in this study. Data from 184 patients were chosen randomly as a training set to adjust the parameters of DDNN, and the remaining 46 patients were the test set to assess the performance of the model. The Dice similarity coefficient (DSC) was used to quantify the segmentation results of the GTVnx, GTVnd, and CTV. In addition, the performance of DDNN was compared with the VGG-16 model. The proposed DDNN method outperformed the VGG-16 in all the segmentation. The mean DSC values of DDNN were 80.9% for GTVnx, 62.3% for the GTVnd, and 82.6% for CTV, whereas VGG-16 obtained 72.3, 33.7, and 73.7% for the DSC values, respectively. DDNN can be used to segment the GTVnx and CTV accurately. The accuracy for the GTVnd segmentation was relatively low due to the considerable differences in its shape, volume, and location among patients. The accuracy is expected to increase with more training data and combination of MR images. In conclusion, DDNN has the potential to improve the consistency of contouring and streamline radiotherapy workflows, but careful human review and a considerable amount of editing will be required.

Segment of brick perimeter wall extending around the naval asylum ...

Library of Congress Historic Buildings Survey, Historic Engineering Record, Historic Landscapes Survey

Segment of brick perimeter wall extending around the naval asylum grounds at twenty-fourth street with Gray's Ferry Avenue branching to the left and Bainbridge Street to the right, looking southwest. - U. S. Naval Asylum, Biddle Hall, Gray's Ferry Avenue, Philadelphia, Philadelphia County, PA

Estimates of the Lightning NOx Profile in the Vicinity of the North Alabama Lightning Mapping Array

NASA Technical Reports Server (NTRS)

Koshak, William J.; Peterson, Harold

2010-01-01

The NASA Marshall Space Flight Center Lightning Nitrogen Oxides Model (LNOM) is applied to August 2006 North Alabama Lightning Mapping Array (LMA) data to estimate the raw (i.e., unmixed and otherwise environmentally unmodified) vertical profile of lightning nitrogen oxides, NOx = NO + NO 2 . This is part of a larger effort aimed at building a more realistic lightning NOx emissions inventory for use by the U.S. Environmental Protection Agency (EPA) Community Multiscale Air Quality (CMAQ) modeling system. Data from the National Lightning Detection Network TM (NLDN) is also employed. Overall, special attention is given to several important lightning variables including: the frequency and geographical distribution of lightning in the vicinity of the LMA network, lightning type (ground or cloud flash), lightning channel length, channel altitude, channel peak current, and the number of strokes per flash. Laboratory spark chamber results from the literature are used to convert 1-meter channel segments (that are located at a particular known altitude; i.e., air density) to NOx concentration. The resulting raw NOx profiles are discussed.

Hard-to-reach? Using health access status as a way to more effectively target segments of the Latino audience.

PubMed

Wilkin, Holley A; Ball-Rokeach, Sandra J

2011-04-01

Health issues disproportionately affect Latinos, but variations within this ethnic group may mean that some Latinos are harder to reach with health messages than others. This paper introduces a methodology grounded in communication infrastructure theory to better target 'hard-to-reach' audiences. A random digit dialing telephone survey of 739 Latinos living in two Los Angeles communities was conducted. The relationships between health access difficulties and connections to an integrated storytelling network as well as individual health communication source connections were explored. Findings suggest that Latinos who are connected to an integrated storytelling network report marginally greater ease finding healthcare, despite not being any more likely to have insurance or a regular place for healthcare. Latinos who have health access problems tended to rely more upon Spanish-language television for health information. In addition, those without healthcare access problems are more likely to indicate that they use health professionals, the Internet, mainstream TV and printed materials like health pamphlets for health information. The theoretical and methodological contributions of this work, its major findings, implications, limitations and policy guidelines are discussed.

Estimates of the Lightning NOx Profile in the Vicinity of the North Alabama Lightning Mapping Array

NASA Technical Reports Server (NTRS)

Koshak, William J.; Peterson, Harold S.; McCaul, Eugene W.; Blazar, Arastoo

2010-01-01

The NASA Marshall Space Flight Center Lightning Nitrogen Oxides Model (LNOM) is applied to August 2006 North Alabama Lightning Mapping Array (NALMA) data to estimate the (unmixed and otherwise environmentally unmodified) vertical source profile of lightning nitrogen oxides, NOx = NO + NO2. Data from the National Lightning Detection Network (Trademark) (NLDN) is also employed. This is part of a larger effort aimed at building a more realistic lightning NOx emissions inventory for use by the U.S. Environmental Protection Agency (EPA) Community Multiscale Air Quality (CMAQ) modeling system. Overall, special attention is given to several important lightning variables including: the frequency and geographical distribution of lightning in the vicinity of the NALMA network, lightning type (ground or cloud flash), lightning channel length, channel altitude, channel peak current, and the number of strokes per flash. Laboratory spark chamber results from the literature are used to convert 1-meter channel segments (that are located at a particular known altitude; i.e., air density) to NOx concentration. The resulting lightning NOx source profiles are discussed.

A TDMA Broadcast Satellite/Ground Architecture for the Aeronautical Telecommunications Network

NASA Technical Reports Server (NTRS)

Shamma, Mohammed A.; Raghavan, Rajesh S.

2003-01-01

An initial evaluation of a TDMA satellite broadcast architecture with an integrated ground network is proposed in this study as one option for the Aeronautical Telecommunications Network (ATN). The architecture proposed consists of a ground based network that is dedicated to the reception and transmissions of Automatic Dependent Surveillance Broadcast (ADS-B) messages from Mode-S or UAT type systems, along with tracks from primary and secondary surveillance radars. Additionally, the ground network could contain VHF Digital Link Mode 2, 3 or 4 transceivers for the reception and transmissions of Controller-Pilot Data Link Communications (CPDLC) messages and for voice. The second part of the ATN network consists of a broadcast satellite based system that is mainly dedicated for the transmission of surveillance data as well as En-route Flight Information Service Broadcast (FIS-B) to all aircraft. The system proposed integrates those two network to provide a nation wide comprehensive service utilizing near term or existing technologies and hence keeping the economic factor in prospective. The next few sections include a background introduction, the ground subnetwork, the satellite subnetwork, modeling and simulations, and conclusion and recommendations.

Development of Land Segmentation, Stream-Reach Network, and Watersheds in Support of Hydrological Simulation Program-Fortran (HSPF) Modeling, Chesapeake Bay Watershed, and Adjacent Parts of Maryland, Delaware, and Virginia

USGS Publications Warehouse

Martucci, Sarah K.; Krstolic, Jennifer L.; Raffensperger, Jeff P.; Hopkins, Katherine J.

2006-01-01

The U.S. Geological Survey, U.S. Environmental Protection Agency Chesapeake Bay Program Office, Interstate Commission on the Potomac River Basin, Maryland Department of the Environment, Virginia Department of Conservation and Recreation, Virginia Department of Environmental Quality, and the University of Maryland Center for Environmental Science are collaborating on the Chesapeake Bay Regional Watershed Model, using Hydrological Simulation Program - FORTRAN to simulate streamflow and concentrations and loads of nutrients and sediment to Chesapeake Bay. The model will be used to provide information for resource managers. In order to establish a framework for model simulation, digital spatial datasets were created defining the discretization of the model region (including the Chesapeake Bay watershed, as well as the adjacent parts of Maryland, Delaware, and Virginia outside the watershed) into land segments, a stream-reach network, and associated watersheds. Land segmentation was based on county boundaries represented by a 1:100,000-scale digital dataset. Fifty of the 254 counties and incorporated cities in the model region were divided on the basis of physiography and topography, producing a total of 309 land segments. The stream-reach network for the Chesapeake Bay watershed part of the model region was based on the U.S. Geological Survey Chesapeake Bay SPARROW (SPAtially Referenced Regressions On Watershed attributes) model stream-reach network. Because that network was created only for the Chesapeake Bay watershed, the rest of the model region uses a 1:500,000-scale stream-reach network. Streams with mean annual streamflow of less than 100 cubic feet per second were excluded based on attributes from the dataset. Additional changes were made to enhance the data and to allow for inclusion of stream reaches with monitoring data that were not part of the original network. Thirty-meter-resolution Digital Elevation Model data were used to delineate watersheds for each stream reach. State watershed boundaries replaced the Digital Elevation Model-derived watersheds where coincident. After a number of corrections, the watersheds were coded to indicate major and minor basin, mean annual streamflow, and each watershed's unique identifier as well as that of the downstream watershed. Land segments and watersheds were intersected to create land-watershed segments for the model.

Retinal vascular segmentation using superpixel-based line operator and its application to vascular topology estimation.

PubMed

Na, Tong; Xie, Jianyang; Zhao, Yitian; Zhao, Yifan; Liu, Yue; Wang, Yongtian; Liu, Jiang

2018-05-09

Automatic methods of analyzing of retinal vascular networks, such as retinal blood vessel detection, vascular network topology estimation, and arteries/veins classification are of great assistance to the ophthalmologist in terms of diagnosis and treatment of a wide spectrum of diseases. We propose a new framework for precisely segmenting retinal vasculatures, constructing retinal vascular network topology, and separating the arteries and veins. A nonlocal total variation inspired Retinex model is employed to remove the image intensity inhomogeneities and relatively poor contrast. For better generalizability and segmentation performance, a superpixel-based line operator is proposed as to distinguish between lines and the edges, thus allowing more tolerance in the position of the respective contours. The concept of dominant sets clustering is adopted to estimate retinal vessel topology and classify the vessel network into arteries and veins. The proposed segmentation method yields competitive results on three public data sets (STARE, DRIVE, and IOSTAR), and it has superior performance when compared with unsupervised segmentation methods, with accuracy of 0.954, 0.957, and 0.964, respectively. The topology estimation approach has been applied to five public databases (DRIVE,STARE, INSPIRE, IOSTAR, and VICAVR) and achieved high accuracy of 0.830, 0.910, 0.915, 0.928, and 0.889, respectively. The accuracies of arteries/veins classification based on the estimated vascular topology on three public databases (INSPIRE, DRIVE and VICAVR) are 0.90.9, 0.910, and 0.907, respectively. The experimental results show that the proposed framework has effectively addressed crossover problem, a bottleneck issue in segmentation and vascular topology reconstruction. The vascular topology information significantly improves the accuracy on arteries/veins classification. © 2018 American Association of Physicists in Medicine.

Recommended data sets, corn segments and spring wheat segments, for use in program development

NASA Technical Reports Server (NTRS)

Austin, W. W. (Principal Investigator)

1981-01-01

The sets of Large Area Crop Inventory Experiment sites, crop year 1978, which are recommended for use in the development and evaluation of classification techniques based on LANDSAT spectral data are presented. For each site, the following exists: (1) accuracy assessment digitized ground truth; (2) a minimum of 5 percent of the scene ground truth identified as corn or spring wheat; and (3) at least four acquisitions of acceptable data quality during the growing season of the crop of interest. The recommended data sets consist of 41 corn/soybean sites and 17 spring wheat sites.

Quantifying the spatio-temporal pattern of the ground impact of space weather events using dynamical networks formed from the SuperMAG database of ground based magnetometer stations.

NASA Astrophysics Data System (ADS)

Dods, Joe; Chapman, Sandra; Gjerloev, Jesper

2016-04-01

Quantitative understanding of the full spatial-temporal pattern of space weather is important in order to estimate the ground impact. Geomagnetic indices such as AE track the peak of a geomagnetic storm or substorm, but cannot capture the full spatial-temporal pattern. Observations by the ~100 ground based magnetometers in the northern hemisphere have the potential to capture the detailed evolution of a given space weather event. We present the first analysis of the full available set of ground based magnetometer observations of substorms using dynamical networks. SuperMAG offers a database containing ground station magnetometer data at a cadence of 1min from 100s stations situated across the globe. We use this data to form dynamic networks which capture spatial dynamics on timescales from the fast reconfiguration seen in the aurora, to that of the substorm cycle. Windowed linear cross-correlation between pairs of magnetometer time series along with a threshold is used to determine which stations are correlated and hence connected in the network. Variations in ground conductivity and differences in the response functions of magnetometers at individual stations are overcome by normalizing to long term averages of the cross-correlation. These results are tested against surrogate data in which phases have been randomised. The network is then a collection of connected points (ground stations); the structure of the network and its variation as a function of time quantify the detailed dynamical processes of the substorm. The network properties can be captured quantitatively in time dependent dimensionless network parameters and we will discuss their behaviour for examples of 'typical' substorms and storms. The network parameters provide a detailed benchmark to compare data with models of substorm dynamics, and can provide new insights on the similarities and differences between substorms and how they correlate with external driving and the internal state of the magnetosphere. We can also investigate the solar wind control of the magnetospheric-ionospheric convection system using dynamical networks. The dynamical networks are first interpolated onto a regular grid. Statistically averaged network responses are then formed for a variety of solar wind conditions, including investigating the network response to southward turnings. [1] Dods, J., S. C. Chapman, and J. W. Gjerloev (2015), Network analysis of geomagnetic substorms using the SuperMAG database of ground-based magnetometer stations, J. Geophys. Res. Space Physics, 120, 7774-7784, doi:10.1002/2015JA021456

Strategy-aligned fuzzy approach for market segment evaluation and selection: a modular decision support system by dynamic network process (DNP)

NASA Astrophysics Data System (ADS)

Mohammadi Nasrabadi, Ali; Hosseinpour, Mohammad Hossein; Ebrahimnejad, Sadoullah

2013-05-01

In competitive markets, market segmentation is a critical point of business, and it can be used as a generic strategy. In each segment, strategies lead companies to their targets; thus, segment selection and the application of the appropriate strategies over time are very important to achieve successful business. This paper aims to model a strategy-aligned fuzzy approach to market segment evaluation and selection. A modular decision support system (DSS) is developed to select an optimum segment with its appropriate strategies. The suggested DSS has two main modules. The first one is SPACE matrix which indicates the risk of each segment. Also, it determines the long-term strategies. The second module finds the most preferred segment-strategies over time. Dynamic network process is applied to prioritize segment-strategies according to five competitive force factors. There is vagueness in pairwise comparisons, and this vagueness has been modeled using fuzzy concepts. To clarify, an example is illustrated by a case study in Iran's coffee market. The results show that success possibility of segments could be different, and choosing the best ones could help companies to be sure in developing their business. Moreover, changing the priority of strategies over time indicates the importance of long-term planning. This fact has been supported by a case study on strategic priority difference in short- and long-term consideration.

Volumetric multimodality neural network for brain tumor segmentation

NASA Astrophysics Data System (ADS)

Silvana Castillo, Laura; Alexandra Daza, Laura; Carlos Rivera, Luis; Arbeláez, Pablo

2017-11-01

Brain lesion segmentation is one of the hardest tasks to be solved in computer vision with an emphasis on the medical field. We present a convolutional neural network that produces a semantic segmentation of brain tumors, capable of processing volumetric data along with information from multiple MRI modalities at the same time. This results in the ability to learn from small training datasets and highly imbalanced data. Our method is based on DeepMedic, the state of the art in brain lesion segmentation. We develop a new architecture with more convolutional layers, organized in three parallel pathways with different input resolution, and additional fully connected layers. We tested our method over the 2015 BraTS Challenge dataset, reaching an average dice coefficient of 84%, while the standard DeepMedic implementation reached 74%.

Ω-Net (Omega-Net): Fully automatic, multi-view cardiac MR detection, orientation, and segmentation with deep neural networks.

PubMed

Vigneault, Davis M; Xie, Weidi; Ho, Carolyn Y; Bluemke, David A; Noble, J Alison

2018-05-22

Pixelwise segmentation of the left ventricular (LV) myocardium and the four cardiac chambers in 2-D steady state free precession (SSFP) cine sequences is an essential preprocessing step for a wide range of analyses. Variability in contrast, appearance, orientation, and placement of the heart between patients, clinical views, scanners, and protocols makes fully automatic semantic segmentation a notoriously difficult problem. Here, we present Ω-Net (Omega-Net): A novel convolutional neural network (CNN) architecture for simultaneous localization, transformation into a canonical orientation, and semantic segmentation. First, an initial segmentation is performed on the input image; second, the features learned during this initial segmentation are used to predict the parameters needed to transform the input image into a canonical orientation; and third, a final segmentation is performed on the transformed image. In this work, Ω-Nets of varying depths were trained to detect five foreground classes in any of three clinical views (short axis, SA; four-chamber, 4C; two-chamber, 2C), without prior knowledge of the view being segmented. This constitutes a substantially more challenging problem compared with prior work. The architecture was trained using three-fold cross-validation on a cohort of patients with hypertrophic cardiomyopathy (HCM, N=42) and healthy control subjects (N=21). Network performance, as measured by weighted foreground intersection-over-union (IoU), was substantially improved for the best-performing Ω-Net compared with U-Net segmentation without localization or orientation (0.858 vs 0.834). In addition, to be comparable with other works, Ω-Net was retrained from scratch using five-fold cross-validation on the publicly available 2017 MICCAI Automated Cardiac Diagnosis Challenge (ACDC) dataset. The Ω-Net outperformed the state-of-the-art method in segmentation of the LV and RV bloodpools, and performed slightly worse in segmentation of the LV myocardium. We conclude that this architecture represents a substantive advancement over prior approaches, with implications for biomedical image segmentation more generally. Published by Elsevier B.V.

Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images.

PubMed

Pereira, Sergio; Pinto, Adriano; Alves, Victor; Silva, Carlos A

2016-05-01

Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of oncological patients. Magnetic resonance imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, automatic and reliable segmentation methods are required; however, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. In this paper, we propose an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 ×3 kernels. The use of small kernels allows designing a deeper architecture, besides having a positive effect against overfitting, given the fewer number of weights in the network. We also investigated the use of intensity normalization as a pre-processing step, which though not common in CNN-based segmentation methods, proved together with data augmentation to be very effective for brain tumor segmentation in MRI images. Our proposal was validated in the Brain Tumor Segmentation Challenge 2013 database (BRATS 2013), obtaining simultaneously the first position for the complete, core, and enhancing regions in Dice Similarity Coefficient metric (0.88, 0.83, 0.77) for the Challenge data set. Also, it obtained the overall first position by the online evaluation platform. We also participated in the on-site BRATS 2015 Challenge using the same model, obtaining the second place, with Dice Similarity Coefficient metric of 0.78, 0.65, and 0.75 for the complete, core, and enhancing regions, respectively.

Video Segmentation Descriptors for Event Recognition

DTIC Science & Technology

2014-12-08

Velastin, 3D Extended Histogram of Oriented Gradients (3DHOG) for Classification of Road Users in Urban Scenes , BMVC, 2009. [3] M.-Y. Chen and A. Hauptmann...computed on 3D volume outputted by the hierarchical segmentation . Each video is described as follows. Each supertube is temporally divided in n-frame...strength of these descriptors is their adaptability to the scene variations since they are grounded on a video segmentation . This makes them naturally robust

Continuous assessment of land mapping accuracy at High Resolution from global networks of atmospheric and field observatories -concept and demonstration

NASA Astrophysics Data System (ADS)

Sicard, Pierre; Martin-lauzer, François-regis

2017-04-01

In the context of global climate change and adjustment/resilience policies' design and implementation, there is a need not only i. for environmental monitoring, e.g. through a range of Earth Observations (EO) land "products" but ii. for a precise assessment of uncertainties of the aforesaid information that feed environmental decision-making (to be introduced in the EO metadata) and also iii. for a perfect handing of the thresholds which help translate "environment tolerance limits" to match detected EO changes through ecosystem modelling. Uncertainties' insight means precision and accuracy's knowledge and subsequent ability of setting thresholds for change detection systems. Traditionally, the validation of satellite-derived products has taken the form of intensive field campaigns to sanction the introduction of data processors in Payload Data Ground Segments chains. It is marred by logistical challenges and cost issues, reason why it is complemented by specific surveys at ground-based monitoring sites which can provide near-continuous observations at a high temporal resolution (e.g. RadCalNet). Unfortunately, most of the ground-level monitoring sites, in the number of 100th or 1000th, which are part of wider observation networks (e.g. FLUXNET, NEON, IMAGINES) mainly monitor the state of the atmosphere and the radiation exchange at the surface, which are different to the products derived from EO data. In addition they are "point-based" compared to the EO cover to be obtained from Sentinel-2 or Sentinel-3. Yet, data from these networks, processed by spatial extrapolation models, are well-suited to the bottom-up approach and relevant to the validation of vegetation parameters' consistency (e.g. leaf area index, fraction of absorbed photosynthetically active radiation). Consistency means minimal errors on spatial and temporal gradients of EO products. Test of the procedure for land-cover products' consistency assessment with field measurements delivered by worldwide networks will be presented. The samples' extrapolation models will make use of the conventional geographic variables (e.g. major biogeographical or biomes, climatic and socio-economic zones and different ecosystem types and land cover classes, focusing on important ecosystems such as forests and grasslands). Focus will be on i. upscaling procedures, from in-situ data to land products matchup, ii. continuous calibration (spectral, radiometric) and adjustment (geometric, radiometric) of processors.

Are the users of social networking sites homogeneous? A cross-cultural study.

PubMed

Alarcón-Del-Amo, María-Del-Carmen; Gómez-Borja, Miguel-Ángel; Lorenzo-Romero, Carlota

2015-01-01

The growing use of Social Networking Sites (SNS) around the world has made it necessary to understand individuals' behaviors within these sites according to different cultures. Based on a comparative study between two different European countries (The Netherlands versus Spain), a comparison of typologies of networked Internet users has been obtained through a latent segmentation approach. These typologies are based on the frequency with which users perform different activities, their socio-demographic variables, and experience in social networking and interaction patterns. The findings show new insights regarding international segmentation in order to analyse SNS user behaviors in both countries. These results are relevant for marketing strategists eager to use the communication potential of networked individuals and for marketers willing to explore the potential of online networking as a low cost and a highly efficient alternative to traditional networking approaches. For most businesses, expert users could be valuable opinion leaders and potential brand influencers.

Are the users of social networking sites homogeneous? A cross-cultural study

PubMed Central

Alarcón-del-Amo, María-del-Carmen; Gómez-Borja, Miguel-Ángel; Lorenzo-Romero, Carlota

2015-01-01

The growing use of Social Networking Sites (SNS) around the world has made it necessary to understand individuals' behaviors within these sites according to different cultures. Based on a comparative study between two different European countries (The Netherlands versus Spain), a comparison of typologies of networked Internet users has been obtained through a latent segmentation approach. These typologies are based on the frequency with which users perform different activities, their socio-demographic variables, and experience in social networking and interaction patterns. The findings show new insights regarding international segmentation in order to analyse SNS user behaviors in both countries. These results are relevant for marketing strategists eager to use the communication potential of networked individuals and for marketers willing to explore the potential of online networking as a low cost and a highly efficient alternative to traditional networking approaches. For most businesses, expert users could be valuable opinion leaders and potential brand influencers. PMID:26321971

Semantic segmentation of mFISH images using convolutional networks.

PubMed

Pardo, Esteban; Morgado, José Mário T; Malpica, Norberto

2018-04-30

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

Large File Transfers from Space Using Multiple Ground Terminals and Delay-Tolerant Networking

NASA Technical Reports Server (NTRS)

Ivancic, William D.; Paulsen, Phillip; Stewart, Dave; Eddy, Wesley; McKim, James; Taylor, John; Lynch, Scott; Heberle, Jay; Northam, James; Jackson, Chris;

Volcano monitoring using the Global Positioning System: Filtering strategies

USGS Publications Warehouse

Larson, K.M.; Cervelli, Peter; Lisowski, M.; Miklius, Asta; Segall, P.; Owen, S.

2001-01-01

Permanent Global Positioning System (GPS) networks are routinely used for producing improved orbits and monitoring secular tectonic deformation. For these applications, data are transferred to an analysis center each day and routinely processed in 24-hour segments. To use GPS for monitoring volcanic events, which may last only a few hours, real-time or near real-time data processing and subdaily position estimates are valuable. Strategies have been researched for obtaining station coordinates every 15 min using a Kalman filter; these strategies have been tested on data collected by a GPS network on Kilauea Volcano. Data from this network are tracked continuously, recorded every 30 s, and telemetered hourly to the Hawaiian Volcano Observatory. A white noise model is heavily impacted by data outages and poor satellite geometry, but a properly constrained random walk model fits the data well. Using a borehole tiltmeter at Kilauea's summit as ground-truth, solutions using different random walk constraints were compared. This study indicates that signals on the order of 5 mm/h are resolvable using a random walk standard deviation of 0.45 cm/???h. Values lower than this suppress small signals, and values greater than this have significantly higher noise at periods of 1-6 hours. Copyright 2001 by the American Geophysical Union.

UFCN: a fully convolutional neural network for road extraction in RGB imagery acquired by remote sensing from an unmanned aerial vehicle

NASA Astrophysics Data System (ADS)

Kestur, Ramesh; Farooq, Shariq; Abdal, Rameen; Mehraj, Emad; Narasipura, Omkar; Mudigere, Meenavathi

2018-01-01

Road extraction in imagery acquired by low altitude remote sensing (LARS) carried out using an unmanned aerial vehicle (UAV) is presented. LARS is carried out using a fixed wing UAV with a high spatial resolution vision spectrum (RGB) camera as the payload. Deep learning techniques, particularly fully convolutional network (FCN), are adopted to extract roads by dense semantic segmentation. The proposed model, UFCN (U-shaped FCN) is an FCN architecture, which is comprised of a stack of convolutions followed by corresponding stack of mirrored deconvolutions with the usage of skip connections in between for preserving the local information. The limited dataset (76 images and their ground truths) is subjected to real-time data augmentation during training phase to increase the size effectively. Classification performance is evaluated using precision, recall, accuracy, F1 score, and brier score parameters. The performance is compared with support vector machine (SVM) classifier, a one-dimensional convolutional neural network (1D-CNN) model, and a standard two-dimensional CNN (2D-CNN). The UFCN model outperforms the SVM, 1D-CNN, and 2D-CNN models across all the performance parameters. Further, the prediction time of the proposed UFCN model is comparable with SVM, 1D-CNN, and 2D-CNN models.

Network of European regions using space technologies an update on the NEREUS constitution

NASA Astrophysics Data System (ADS)

Morelli, Marianna; Campostrini, Pierpaolo

2010-01-01

The EU and ESA space research and development programmes give a consolidated model for international cooperation. They represent a good framework to develop and enhance different initiatives at global, regional and local level. The impact of space activities covers different areas of interest such as: the development of Earth observation applications for environment monitoring and risk prevention and management, the development of satellite communications and information systems, the exploitation of global satellite positioning and navigation systems, the knowledge of the Universe, the utilisation of ground segment engineering. These activities involve also the regional and local governments. This is particularly evident if we look at the competences of the European regional governments. Several European regions deal with a number of issues in areas linked to space activities. In line with these reflections a number of European regional governments supported by the Committee of the Regions launched the idea to create a Network of European Regions Using Space technologies—NEREUS. This Network is an International non-profit association (AISBL— Association International Sans But Lucratif) under Belgian law. The aim of this paper is to review the course of the initiative since its launch in April 2006, giving an update of the work done for its constitution.

Applying a cloud computing approach to storage architectures for spacecraft

NASA Astrophysics Data System (ADS)

Baldor, Sue A.; Quiroz, Carlos; Wood, Paul

As sensor technologies, processor speeds, and memory densities increase, spacecraft command, control, processing, and data storage systems have grown in complexity to take advantage of these improvements and expand the possible missions of spacecraft. Spacecraft systems engineers are increasingly looking for novel ways to address this growth in complexity and mitigate associated risks. Looking to conventional computing, many solutions have been executed to solve both the problem of complexity and heterogeneity in systems. In particular, the cloud-based paradigm provides a solution for distributing applications and storage capabilities across multiple platforms. In this paper, we propose utilizing a cloud-like architecture to provide a scalable mechanism for providing mass storage in spacecraft networks that can be reused on multiple spacecraft systems. By presenting a consistent interface to applications and devices that request data to be stored, complex systems designed by multiple organizations may be more readily integrated. Behind the abstraction, the cloud storage capability would manage wear-leveling, power consumption, and other attributes related to the physical memory devices, critical components in any mass storage solution for spacecraft. Our approach employs SpaceWire networks and SpaceWire-capable devices, although the concept could easily be extended to non-heterogeneous networks consisting of multiple spacecraft and potentially the ground segment.

Delineation and validation of river network spatial scales for water resources and fisheries management.

PubMed

Wang, Lizhu; Brenden, Travis; Cao, Yong; Seelbach, Paul

2012-11-01

Identifying appropriate spatial scales is critically important for assessing health, attributing data, and guiding management actions for rivers. We describe a process for identifying a three-level hierarchy of spatial scales for Michigan rivers. Additionally, we conduct a variance decomposition of fish occurrence, abundance, and assemblage metric data to evaluate how much observed variability can be explained by the three spatial scales as a gage of their utility for water resources and fisheries management. The process involved the development of geographic information system programs, statistical models, modification by experienced biologists, and simplification to meet the needs of policy makers. Altogether, 28,889 reaches, 6,198 multiple-reach segments, and 11 segment classes were identified from Michigan river networks. The segment scale explained the greatest amount of variation in fish abundance and occurrence, followed by segment class, and reach. Segment scale also explained the greatest amount of variation in 13 of the 19 analyzed fish assemblage metrics, with segment class explaining the greatest amount of variation in the other six fish metrics. Segments appear to be a useful spatial scale/unit for measuring and synthesizing information for managing rivers and streams. Additionally, segment classes provide a useful typology for summarizing the numerous segments into a few categories. Reaches are the foundation for the identification of segments and segment classes and thus are integral elements of the overall spatial scale hierarchy despite reaches not explaining significant variation in fish assemblage data.

Scene segmentation of natural images using texture measures and back-propagation

NASA Technical Reports Server (NTRS)

Sridhar, Banavar; Phatak, Anil; Chatterji, Gano

1993-01-01

Knowledge of the three-dimensional world is essential for many guidance and navigation applications. A sequence of images from an electro-optical sensor can be processed using optical flow algorithms to provide a sparse set of ranges as a function of azimuth and elevation. A natural way to enhance the range map is by interpolation. However, this should be undertaken with care since interpolation assumes continuity of range. The range is continuous in certain parts of the image and can jump at object boundaries. In such situations, the ability to detect homogeneous object regions by scene segmentation can be used to determine regions in the range map that can be enhanced by interpolation. The use of scalar features derived from the spatial gray-level dependence matrix for texture segmentation is explored. Thresholding of histograms of scalar texture features is done for several images to select scalar features which result in a meaningful segmentation of the images. Next, the selected scalar features are used with a neural net to automate the segmentation procedure. Back-propagation is used to train the feed forward neural network. The generalization of the network approach to subsequent images in the sequence is examined. It is shown that the use of multiple scalar features as input to the neural network result in a superior segmentation when compared with a single scalar feature. It is also shown that the scalar features, which are not useful individually, result in a good segmentation when used together. The methodology is applied to both indoor and outdoor images.

A Hybrid Hierarchical Approach for Brain Tissue Segmentation by Combining Brain Atlas and Least Square Support Vector Machine

PubMed Central

Kasiri, Keyvan; Kazemi, Kamran; Dehghani, Mohammad Javad; Helfroush, Mohammad Sadegh

2013-01-01

In this paper, we present a new semi-automatic brain tissue segmentation method based on a hybrid hierarchical approach that combines a brain atlas as a priori information and a least-square support vector machine (LS-SVM). The method consists of three steps. In the first two steps, the skull is removed and the cerebrospinal fluid (CSF) is extracted. These two steps are performed using the toolbox FMRIB's automated segmentation tool integrated in the FSL software (FSL-FAST) developed in Oxford Centre for functional MRI of the brain (FMRIB). Then, in the third step, the LS-SVM is used to segment grey matter (GM) and white matter (WM). The training samples for LS-SVM are selected from the registered brain atlas. The voxel intensities and spatial positions are selected as the two feature groups for training and test. SVM as a powerful discriminator is able to handle nonlinear classification problems; however, it cannot provide posterior probability. Thus, we use a sigmoid function to map the SVM output into probabilities. The proposed method is used to segment CSF, GM and WM from the simulated magnetic resonance imaging (MRI) using Brainweb MRI simulator and real data provided by Internet Brain Segmentation Repository. The semi-automatically segmented brain tissues were evaluated by comparing to the corresponding ground truth. The Dice and Jaccard similarity coefficients, sensitivity and specificity were calculated for the quantitative validation of the results. The quantitative results show that the proposed method segments brain tissues accurately with respect to corresponding ground truth. PMID:24696800

Pattern of metastasis outside tumor-bearing segments in primary lung cancer: rationale for segmentectomy.

PubMed

Sakairi, Yuichi; Yoshino, Ichiro; Yoshida, Shigetoshi; Suzuki, Hidemi; Tagawa, Tetsuzo; Iwata, Takekazu; Mizobuchi, Teruaki

2014-05-01

Patterns of intrapulmonary metastasis, particularly metastasis outside tumor-bearing segments, were investigated in lung cancer patients to address the rationale for segmentectomy. In a consecutive series of patients who underwent resection of two or more pulmonary segments for primary lung cancer, intrapulmonary spread patterns, such as segmental/intersegmental node metastasis and pulmonary parenchymal metastasis, were pathologically examined. Eligible 244 lesions included 167 adenocarcinomas, 66 squamous cell carcinomas, and 11 large cell carcinomas. Pathologic stages included 0 to IA (n=111), IB (n=56), IIA (n=31), IIB (n=20), IIIA (n=23), and IIIB to IV (n=3); and N1 (n=26) and N2 (n=22). Intrapulmonary spread was observed in 24 cases (9.8%). Of these, metastasis outside tumor-bearing segments was only observed in 4 cases (1.6%), and such cancer spread was more frequently seen in cases with extrapulmonary (hilar to mediastinal) nodal metastasis (7.9%) than in cases without extrapulmonary metastasis (0.5%; p=0.01). Metastasis outside tumor-bearing segments was not observed in 64 tumors with pure or mixed ground glass opacity features on computed tomography. Although tumor location (peripheral or central/intermediate) was not related to the incidence of metastasis outside tumor-bearing segments, intrapulmonary spread was observed in only 1 of 52 peripheral small (≤20 mm) tumors. Metastasis outside tumor-bearing segments is rarely observed in cases with tumors (1) without extrapulmonary nodal metastasis and (2) with ground glass opacity or peripheral small (≤20 mm) features. Copyright © 2014 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks

PubMed Central

Ibragimov, Bulat; Xing, Lei

2017-01-01

Purpose Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software and inter-observer variability. Methods Convolutional neural networks (CNNs) – a concept from the field of deep learning – were used to study consistent intensity patterns of OARs from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end-points and edges, and combined them into more complex high-order features that can efficiently describe the OAR. The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN, performed dilate-erode operations to remov cavities of the component, which resulted in segmentation of the OAR in the test image. Results The performance of CNNs was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient (DSC) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state-of-the-art algorithms and commercial software reported in the literature, and observed that CNNs demonstrate similar or superior performance on segmentation of spinal cord, mandible, parotid glands, larynx, pharynx, eye globes and optic nerves, but inferior performance on segmentation of submandibular glands and optic chiasm. Conclusion We concluded that convolution neural networks can accurately segment most of OARs using a representative database of 50 HaN CT images. At the same time, inclusion of additional information, e.g. MR images, may be beneficial for some OARs with poorly-visible boundaries. PMID:28205307

Real-time object detection and semantic segmentation for autonomous driving

NASA Astrophysics Data System (ADS)

Li, Baojun; Liu, Shun; Xu, Weichao; Qiu, Wei

2018-02-01

In this paper, we proposed a Highly Coupled Network (HCNet) for joint objection detection and semantic segmentation. It follows that our method is faster and performs better than the previous approaches whose decoder networks of different tasks are independent. Besides, we present multi-scale loss architecture to learn better representation for different scale objects, but without extra time in the inference phase. Experiment results show that our method achieves state-of-the-art results on the KITTI datasets. Moreover, it can run at 35 FPS on a GPU and thus is a practical solution to object detection and semantic segmentation for autonomous driving.

A neural network approach to lung nodule segmentation

NASA Astrophysics Data System (ADS)

Hu, Yaoxiu; Menon, Prahlad G.

2016-03-01

Computed tomography (CT) imaging is a sensitive and specific lung cancer screening tool for the high-risk population and shown to be promising for detection of lung cancer. This study proposes an automatic methodology for detecting and segmenting lung nodules from CT images. The proposed methods begin with thorax segmentation, lung extraction and reconstruction of the original shape of the parenchyma using morphology operations. Next, a multi-scale hessian-based vesselness filter is applied to extract lung vasculature in lung. The lung vasculature mask is subtracted from the lung region segmentation mask to extract 3D regions representing candidate pulmonary nodules. Finally, the remaining structures are classified as nodules through shape and intensity features which are together used to train an artificial neural network. Up to 75% sensitivity and 98% specificity was achieved for detection of lung nodules in our testing dataset, with an overall accuracy of 97.62%+/-0.72% using 11 selected features as input to the neural network classifier, based on 4-fold cross-validation studies. Receiver operator characteristics for identifying nodules revealed an area under curve of 0.9476.

Improving Spleen Volume Estimation via Computer Assisted Segmentation on Clinically Acquired CT Scans

PubMed Central

Xu, Zhoubing; Gertz, Adam L.; Burke, Ryan P.; Bansal, Neil; Kang, Hakmook; Landman, Bennett A.; Abramson, Richard G.

2016-01-01

OBJECTIVES Multi-atlas fusion is a promising approach for computer-assisted segmentation of anatomical structures. The purpose of this study was to evaluate the accuracy and time efficiency of multi-atlas segmentation for estimating spleen volumes on clinically-acquired CT scans. MATERIALS AND METHODS Under IRB approval, we obtained 294 deidentified (HIPAA-compliant) abdominal CT scans on 78 subjects from a recent clinical trial. We compared five pipelines for obtaining splenic volumes: Pipeline 1–manual segmentation of all scans, Pipeline 2–automated segmentation of all scans, Pipeline 3–automated segmentation of all scans with manual segmentation for outliers on a rudimentary visual quality check, Pipelines 4 and 5–volumes derived from a unidimensional measurement of craniocaudal spleen length and three-dimensional splenic index measurements, respectively. Using Pipeline 1 results as ground truth, the accuracy of Pipelines 2–5 (Dice similarity coefficient [DSC], Pearson correlation, R-squared, and percent and absolute deviation of volume from ground truth) were compared for point estimates of splenic volume and for change in splenic volume over time. Time cost was also compared for Pipelines 1–5. RESULTS Pipeline 3 was dominant in terms of both accuracy and time cost. With a Pearson correlation coefficient of 0.99, average absolute volume deviation 23.7 cm3, and 1 minute per scan, Pipeline 3 yielded the best results. The second-best approach was Pipeline 5, with a Pearson correlation coefficient 0.98, absolute deviation 46.92 cm3, and 1 minute 30 seconds per scan. Manual segmentation (Pipeline 1) required 11 minutes per scan. CONCLUSION A computer-automated segmentation approach with manual correction of outliers generated accurate splenic volumes with reasonable time efficiency. PMID:27519156

3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images.

PubMed

Li, Xiaomeng; Dou, Qi; Chen, Hao; Fu, Chi-Wing; Qi, Xiaojuan; Belavý, Daniel L; Armbrecht, Gabriele; Felsenberg, Dieter; Zheng, Guoyan; Heng, Pheng-Ann

2018-04-01

Intervertebral discs (IVDs) are small joints that lie between adjacent vertebrae. The localization and segmentation of IVDs are important for spine disease diagnosis and measurement quantification. However, manual annotation is time-consuming and error-prone with limited reproducibility, particularly for volumetric data. In this work, our goal is to develop an automatic and accurate method based on fully convolutional networks (FCN) for the localization and segmentation of IVDs from multi-modality 3D MR data. Compared with single modality data, multi-modality MR images provide complementary contextual information, which contributes to better recognition performance. However, how to effectively integrate such multi-modality information to generate accurate segmentation results remains to be further explored. In this paper, we present a novel multi-scale and modality dropout learning framework to locate and segment IVDs from four-modality MR images. First, we design a 3D multi-scale context fully convolutional network, which processes the input data in multiple scales of context and then merges the high-level features to enhance the representation capability of the network for handling the scale variation of anatomical structures. Second, to harness the complementary information from different modalities, we present a random modality voxel dropout strategy which alleviates the co-adaption issue and increases the discriminative capability of the network. Our method achieved the 1st place in the MICCAI challenge on automatic localization and segmentation of IVDs from multi-modality MR images, with a mean segmentation Dice coefficient of 91.2% and a mean localization error of 0.62 mm. We further conduct extensive experiments on the extended dataset to validate our method. We demonstrate that the proposed modality dropout strategy with multi-modality images as contextual information improved the segmentation accuracy significantly. Furthermore, experiments conducted on extended data collected from two different time points demonstrate the efficacy of our method on tracking the morphological changes in a longitudinal study. Copyright © 2018 Elsevier B.V. All rights reserved.

A Novel Unsupervised Segmentation Quality Evaluation Method for Remote Sensing Images

PubMed Central

Tang, Yunwei; Jing, Linhai; Ding, Haifeng

2017-01-01

The segmentation of a high spatial resolution remote sensing image is a critical step in geographic object-based image analysis (GEOBIA). Evaluating the performance of segmentation without ground truth data, i.e., unsupervised evaluation, is important for the comparison of segmentation algorithms and the automatic selection of optimal parameters. This unsupervised strategy currently faces several challenges in practice, such as difficulties in designing effective indicators and limitations of the spectral values in the feature representation. This study proposes a novel unsupervised evaluation method to quantitatively measure the quality of segmentation results to overcome these problems. In this method, multiple spectral and spatial features of images are first extracted simultaneously and then integrated into a feature set to improve the quality of the feature representation of ground objects. The indicators designed for spatial stratified heterogeneity and spatial autocorrelation are included to estimate the properties of the segments in this integrated feature set. These two indicators are then combined into a global assessment metric as the final quality score. The trade-offs of the combined indicators are accounted for using a strategy based on the Mahalanobis distance, which can be exhibited geometrically. The method is tested on two segmentation algorithms and three testing images. The proposed method is compared with two existing unsupervised methods and a supervised method to confirm its capabilities. Through comparison and visual analysis, the results verified the effectiveness of the proposed method and demonstrated the reliability and improvements of this method with respect to other methods. PMID:29064416

Localization of the transverse processes in ultrasound for spinal curvature measurement

NASA Astrophysics Data System (ADS)

Kamali, Shahrokh; Ungi, Tamas; Lasso, Andras; Yan, Christina; Lougheed, Matthew; Fichtinger, Gabor

2017-03-01

PURPOSE: In scoliosis monitoring, tracked ultrasound has been explored as a safer imaging alternative to traditional radiography. The use of ultrasound in spinal curvature measurement requires identification of vertebral landmarks such as transverse processes, but as bones have reduced visibility in ultrasound imaging, skeletal landmarks are typically segmented manually, which is an exceedingly laborious and long process. We propose an automatic algorithm to segment and localize the surface of bony areas in the transverse process for scoliosis in ultrasound. METHODS: The algorithm uses cascade of filters to remove low intensity pixels, smooth the image and detect bony edges. By applying first differentiation, candidate bony areas are classified. The average intensity under each area has a correlation with the possibility of a shadow, and areas with strong shadow are kept for bone segmentation. The segmented images are used to reconstruct a 3-D volume to represent the whole spinal structure around the transverse processes. RESULTS: A comparison between the manual ground truth segmentation and the automatic algorithm in 50 images showed 0.17 mm average difference. The time to process all 1,938 images was about 37 Sec. (0.0191 Sec. / Image), including reading the original sequence file. CONCLUSION: Initial experiments showed the algorithm to be sufficiently accurate and fast for segmentation transverse processes in ultrasound for spinal curvature measurement. An extensive evaluation of the method is currently underway on images from a larger patient cohort and using multiple observers in producing ground truth segmentation.

Hippocampal unified multi-atlas network (HUMAN): protocol and scale validation of a novel segmentation tool.

PubMed

Amoroso, N; Errico, R; Bruno, S; Chincarini, A; Garuccio, E; Sensi, F; Tangaro, S; Tateo, A; Bellotti, R

2015-11-21

In this study we present a novel fully automated Hippocampal Unified Multi-Atlas-Networks (HUMAN) algorithm for the segmentation of the hippocampus in structural magnetic resonance imaging. In multi-atlas approaches atlas selection is of crucial importance for the accuracy of the segmentation. Here we present an optimized method based on the definition of a small peri-hippocampal region to target the atlas learning with linear and non-linear embedded manifolds. All atlases were co-registered to a data driven template resulting in a computationally efficient method that requires only one test registration. The optimal atlases identified were used to train dedicated artificial neural networks whose labels were then propagated and fused to obtain the final segmentation. To quantify data heterogeneity and protocol inherent effects, HUMAN was tested on two independent data sets provided by the Alzheimer's Disease Neuroimaging Initiative and the Open Access Series of Imaging Studies. HUMAN is accurate and achieves state-of-the-art performance (Dice[Formula: see text] and Dice[Formula: see text]). It is also a robust method that remains stable when applied to the whole hippocampus or to sub-regions (patches). HUMAN also compares favorably with a basic multi-atlas approach and a benchmark segmentation tool such as FreeSurfer.

Topology and Dynamics of the Zebrafish Segmentation Clock Core Circuit

PubMed Central

Schröter, Christian; Isakova, Alina; Hens, Korneel; Soroldoni, Daniele; Gajewski, Martin; Jülicher, Frank; Maerkl, Sebastian J.; Deplancke, Bart; Oates, Andrew C.

2012-01-01

During vertebrate embryogenesis, the rhythmic and sequential segmentation of the body axis is regulated by an oscillating genetic network termed the segmentation clock. We describe a new dynamic model for the core pace-making circuit of the zebrafish segmentation clock based on a systematic biochemical investigation of the network's topology and precise measurements of somitogenesis dynamics in novel genetic mutants. We show that the core pace-making circuit consists of two distinct negative feedback loops, one with Her1 homodimers and the other with Her7:Hes6 heterodimers, operating in parallel. To explain the observed single and double mutant phenotypes of her1, her7, and hes6 mutant embryos in our dynamic model, we postulate that the availability and effective stability of the dimers with DNA binding activity is controlled in a “dimer cloud” that contains all possible dimeric combinations between the three factors. This feature of our model predicts that Hes6 protein levels should oscillate despite constant hes6 mRNA production, which we confirm experimentally using novel Hes6 antibodies. The control of the circuit's dynamics by a population of dimers with and without DNA binding activity is a new principle for the segmentation clock and may be relevant to other biological clocks and transcriptional regulatory networks. PMID:22911291

Hippocampal unified multi-atlas network (HUMAN): protocol and scale validation of a novel segmentation tool

NASA Astrophysics Data System (ADS)

Amoroso, N.; Errico, R.; Bruno, S.; Chincarini, A.; Garuccio, E.; Sensi, F.; Tangaro, S.; Tateo, A.; Bellotti, R.; Alzheimers Disease Neuroimaging Initiative,the

2015-11-01

In this study we present a novel fully automated Hippocampal Unified Multi-Atlas-Networks (HUMAN) algorithm for the segmentation of the hippocampus in structural magnetic resonance imaging. In multi-atlas approaches atlas selection is of crucial importance for the accuracy of the segmentation. Here we present an optimized method based on the definition of a small peri-hippocampal region to target the atlas learning with linear and non-linear embedded manifolds. All atlases were co-registered to a data driven template resulting in a computationally efficient method that requires only one test registration. The optimal atlases identified were used to train dedicated artificial neural networks whose labels were then propagated and fused to obtain the final segmentation. To quantify data heterogeneity and protocol inherent effects, HUMAN was tested on two independent data sets provided by the Alzheimer’s Disease Neuroimaging Initiative and the Open Access Series of Imaging Studies. HUMAN is accurate and achieves state-of-the-art performance (Dice{{}\\text{ADNI}} =0.929+/- 0.003 and Dice{{}\\text{OASIS}} =0.869+/- 0.002 ). It is also a robust method that remains stable when applied to the whole hippocampus or to sub-regions (patches). HUMAN also compares favorably with a basic multi-atlas approach and a benchmark segmentation tool such as FreeSurfer.

An improved pulse coupled neural network with spectral residual for infrared pedestrian segmentation

NASA Astrophysics Data System (ADS)

He, Fuliang; Guo, Yongcai; Gao, Chao

2017-12-01

Pulse coupled neural network (PCNN) has become a significant tool for the infrared pedestrian segmentation, and a variety of relevant methods have been developed at present. However, these existing models commonly have several problems of the poor adaptability of infrared noise, the inaccuracy of segmentation results, and the fairly complex determination of parameters in current methods. This paper presents an improved PCNN model that integrates the simplified framework and spectral residual to alleviate the above problem. In this model, firstly, the weight matrix of the feeding input field is designed by the anisotropic Gaussian kernels (ANGKs), in order to suppress the infrared noise effectively. Secondly, the normalized spectral residual saliency is introduced as linking coefficient to enhance the edges and structural characteristics of segmented pedestrians remarkably. Finally, the improved dynamic threshold based on the average gray values of the iterative segmentation is employed to simplify the original PCNN model. Experiments on the IEEE OTCBVS benchmark and the infrared pedestrian image database built by our laboratory, demonstrate that the superiority of both subjective visual effects and objective quantitative evaluations in information differences and segmentation errors in our model, compared with other classic segmentation methods.

Restoring Wood-Rich Hotspots in Mountain Stream Networks

NASA Astrophysics Data System (ADS)

Wohl, E.; Scott, D.

2016-12-01

Mountain streams commonly include substantial longitudinal variability in valley and channel geometry, alternating repeatedly between steep, narrow and relatively wide, low gradient segments. Segments that are wider and lower gradient than neighboring steeper sections are hotspots with respect to: retention of large wood (LW) and finer sediment and organic matter; uptake of nutrients; and biomass and biodiversity of aquatic and riparian organisms. These segments are also more likely to be transport-limited with respect to floodplain and instream LW. Management designed to protect and restore riverine LW and the physical and ecological processes facilitated by the presence of LW is likely to be most effective if focused on relatively low-gradient stream segments. These segments can be identified using a simple, reach-scale gradient analysis based on high-resolution DEMs, with field visits to identify factors that potentially limit or facilitate LW recruitment and retention, such as forest disturbance history or land use. Drawing on field data from the western US, this presentation outlines a procedure for mapping relatively low-gradient segments in a stream network and for identifying those segments where LW reintroduction or retention is most likely to balance maximizing environmental benefits derived from the presence of LW while minimizing hazards associated with LW.

An analytical method to determine ground water supply well network designs.

PubMed

MacMillan, Gordon James

2009-01-01

An analytical method is provided where the ground water practitioner can quickly determine the size (number of wells) and spacing of a well network capable of meeting a known ground water demand. In order to apply the method, two new parameters are derived that relate theoretical drawdown to the maximum drawdown that is achievable without mining the aquifer. The size of a well network is shown to be proportional to the ground water demand and inversely proportional to the transmissivity and available head. The spacing between wells in a supply well network is shown to be most sensitive to a derived parameter r(HA/3) , which is related to the available head and the propagation of drawdown away from a theoretical well if the total ground water demand was applied to that well. The method can be used to quickly determine the required spacing between wells in well networks of various sizes that are completed in confined aquifers with no leakance. Copyright © 2009 The Author(s). Journal Compilation © 2009 National Ground Water Association.

Enhancing MPLS Protection Method with Adaptive Segment Repair

NASA Astrophysics Data System (ADS)

Chen, Chin-Ling

We propose a novel adaptive segment repair mechanism to improve traditional MPLS (Multi-Protocol Label Switching) failure recovery. The proposed mechanism protects one or more contiguous high failure probability links by dynamic setup of segment protection. Simulations demonstrate that the proposed mechanism reduces failure recovery time while also increasing network resource utilization.

Breast Cancer Diagnostics Based on Spatial Genome Organization

DTIC Science & Technology

2012-07-01

using an already established imaging tool, called NMFA-FLO (Nuclei Manual and FISH automatic). In order to achieve accurate segmentation of nuclei...in tissue we used an artificial neuronal network (ANN)-based supervised pattern recognition approach to screen out well segmented nuclei, after image ... segmentation used to process images for automated nuclear segmentation . Part a) has been adapted from [15] and b) from [16]. Figure 4. Comparison of

Asynchronous transfer mode link performance over ground networks

NASA Technical Reports Server (NTRS)

Chow, E. T.; Markley, R. W.

1993-01-01

The results of an experiment to determine the feasibility of using asynchronous transfer mode (ATM) technology to support advanced spacecraft missions that require high-rate ground communications and, in particular, full-motion video are reported. Potential nodes in such a ground network include Deep Space Network (DSN) antenna stations, the Jet Propulsion Laboratory, and a set of national and international end users. The experiment simulated a lunar microrover, lunar lander, the DSN ground communications system, and distributed science users. The users were equipped with video-capable workstations. A key feature was an optical fiber link between two high-performance workstations equipped with ATM interfaces. Video was also transmitted through JPL's institutional network to a user 8 km from the experiment. Variations in video depending on the networks and computers were observed, the results are reported.

Myocardial scar segmentation from magnetic resonance images using convolutional neural network

NASA Astrophysics Data System (ADS)

Zabihollahy, Fatemeh; White, James A.; Ukwatta, Eranga

2018-02-01

Accurate segmentation of the myocardial fibrosis or scar may provide important advancements for the prediction and management of malignant ventricular arrhythmias in patients with cardiovascular disease. In this paper, we propose a semi-automated method for segmentation of myocardial scar from late gadolinium enhancement magnetic resonance image (LGE-MRI) using a convolutional neural network (CNN). In contrast to image intensitybased methods, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of high-level features from a combination of convolutional, detection and pooling layers. Our developed algorithm was trained using 2,336,703 image patches extracted from 420 slices of five 3D LGE-MR datasets, then validated on 2,204,178 patches from a testing dataset of seven 3D LGE-MR images including 624 slices, all obtained from patients with chronic myocardial infarction. For evaluation of the algorithm, we compared the algorithmgenerated segmentations to manual delineations by experts. Our CNN-based method reported an average Dice similarity coefficient (DSC), precision, and recall of 94.50 +/- 3.62%, 96.08 +/- 3.10%, and 93.96 +/- 3.75% as the accuracy of segmentation, respectively. As compared to several intensity threshold-based methods for scar segmentation, the results of our developed method have a greater agreement with manual expert segmentation.

Design of an MSAT-X mobile transceiver and related base and gateway stations

NASA Technical Reports Server (NTRS)

Fang, Russell J. F.; Bhaskar, Udaya; Hemmati, Farhad; Mackenthun, Kenneth M.; Shenoy, Ajit

1987-01-01

This paper summarizes the results of a design study of the mobile transceiver, base station, and gateway station for NASA's proposed Mobile Satellite Experiment (MSAT-X). Major ground segment system design issues such as frequency stability control, modulation method, linear predictive coding vocoder algorithm, and error control technique are addressed. The modular and flexible transceiver design is described in detail, including the core, RF/IF, modem, vocoder, forward error correction codec, amplitude-companded single sideband, and input/output modules, as well as the flexible interface. Designs for a three-carrier base station and a 10-carrier gateway station are also discussed, including the interface with the controllers and with the public-switched telephone networks at the gateway station. Functional specifications are given for the transceiver, the base station, and the gateway station.

The Kinematic and Microphysical Control of Storm Integrated Lightning Flash Extent

NASA Technical Reports Server (NTRS)

Carey, Lawrence D.; Peterson, Harold S.; Schultz, Elise V.; Matthee, Retha; Schultz, Christopher J.; Petersen, Walter A,; Bain, Lamont

2012-01-01

Objective: To investigate the kinematic and microphysical control of lightning properties, particularly those that may govern the production of nitrogen oxides (NOx) in thunderstorms, such as flash rate, type (intracloud [IC] vs. cloud-to-ground [CG] ) and extent. Data and Methodology: a) NASA MSFC Lightning Nitrogen Oxides Model (LNOM) is applied to North Alabama Lightning Mapping Array (NALMA) and Vaisala National Lightning Detection Network(TradeMark) (NLDN) observations following ordinary convective cells through their lifecycle. b) LNOM provides estimates of flash type, channel length distributions, lightning segment altitude distributions (SADs) and lightning NOx production profiles (Koshak et al. 2012). c) LNOM lightning characteristics are compared to the evolution of updraft and precipitation properties inferred from dual-Doppler (DD) and polarimetric radar analyses of UAHuntsville Advanced Radar for Meteorological and Operational Research (ARMOR, Cband, polarimetric) and KHTX (S-band, Doppler).

Design of an MSAT-X mobile transceiver and related base and gateway stations

NASA Astrophysics Data System (ADS)

Fang, Russell J. F.; Bhaskar, Udaya; Hemmati, Farhad; Mackenthun, Kenneth M.; Shenoy, Ajit

This paper summarizes the results of a design study of the mobile transceiver, base station, and gateway station for NASA's proposed Mobile Satellite Experiment (MSAT-X). Major ground segment system design issues such as frequency stability control, modulation method, linear predictive coding vocoder algorithm, and error control technique are addressed. The modular and flexible transceiver design is described in detail, including the core, RF/IF, modem, vocoder, forward error correction codec, amplitude-companded single sideband, and input/output modules, as well as the flexible interface. Designs for a three-carrier base station and a 10-carrier gateway station are also discussed, including the interface with the controllers and with the public-switched telephone networks at the gateway station. Functional specifications are given for the transceiver, the base station, and the gateway station.

Clinical evaluation of semi-automatic open-source algorithmic software segmentation of the mandibular bone: Practical feasibility and assessment of a new course of action.

PubMed

Wallner, Jürgen; Hochegger, Kerstin; Chen, Xiaojun; Mischak, Irene; Reinbacher, Knut; Pau, Mauro; Zrnc, Tomislav; Schwenzer-Zimmerer, Katja; Zemann, Wolfgang; Schmalstieg, Dieter; Egger, Jan

2018-01-01

Computer assisted technologies based on algorithmic software segmentation are an increasing topic of interest in complex surgical cases. However-due to functional instability, time consuming software processes, personnel resources or licensed-based financial costs many segmentation processes are often outsourced from clinical centers to third parties and the industry. Therefore, the aim of this trial was to assess the practical feasibility of an easy available, functional stable and licensed-free segmentation approach to be used in the clinical practice. In this retrospective, randomized, controlled trail the accuracy and accordance of the open-source based segmentation algorithm GrowCut was assessed through the comparison to the manually generated ground truth of the same anatomy using 10 CT lower jaw data-sets from the clinical routine. Assessment parameters were the segmentation time, the volume, the voxel number, the Dice Score and the Hausdorff distance. Overall semi-automatic GrowCut segmentation times were about one minute. Mean Dice Score values of over 85% and Hausdorff Distances below 33.5 voxel could be achieved between the algorithmic GrowCut-based segmentations and the manual generated ground truth schemes. Statistical differences between the assessment parameters were not significant (p<0.05) and correlation coefficients were close to the value one (r > 0.94) for any of the comparison made between the two groups. Complete functional stable and time saving segmentations with high accuracy and high positive correlation could be performed by the presented interactive open-source based approach. In the cranio-maxillofacial complex the used method could represent an algorithmic alternative for image-based segmentation in the clinical practice for e.g. surgical treatment planning or visualization of postoperative results and offers several advantages. Due to an open-source basis the used method could be further developed by other groups or specialists. Systematic comparisons to other segmentation approaches or with a greater data amount are areas of future works.

NPOESS C3S Expandability: SafetyNet(TM) and McMurdo Improvements

NASA Astrophysics Data System (ADS)

Paciaroni, J.; Jamilkowski, M. L.

2009-12-01

The National Oceanic & Atmospheric Administration (NOAA), Department of Defense (DoD), and National Aeronautics and Space Administration (NASA) are jointly acquiring the next-generation weather and environmental satellite system; the National Polar-orbiting Operational Environmental Satellite System (NPOESS). NPOESS replaces the current Polar-orbiting Operational Environmental Satellites (POES) managed by NOAA and the Defense Meteorological Satellite Program (DMSP) managed by the DoD. The NPOESS satellites carry a suite of sensors that collect meteorological, oceanographic, climatological, and solar-geophysical observations of the earth, atmosphere, and space. The command and telemetry portion of NPOESS is the Command, Control and Communications Segment (C3S), developed by Raytheon Intelligence & Information Systems. C3S is responsible for managing the overall NPOESS mission from control and status of the space and ground assets to ensuring delivery of timely, high quality data from the Space Segment (SS) to the Interface Data Processing Segment (IDPS) for processing. In addition, the C3S provides the globally distributed ground assets necessary to collect and transport mission, telemetry, and command data between the satellites and the processing locations. The C3S provides all functions required for day-to-day commanding and state-of-health monitoring of the NPP and NPOESS satellites, and delivery of Stored Mission Data (SMD) to each U.S. Weather Central Interface Data Processor (IDP) for data products development and transfer to System subscribers. The C3S also monitors and reports system-wide health and status and data communications with external systems and between the NPOESS segments. Two crucial elements of NPOESS C3S expandability are SafetyNet(TM) and communications improvements to McMurdo Station, Antarctica. ‘SafetyNet(TM)’ is a key feature of the National Polar-orbiting Operational Environmental Satellite System (NPOESS), vital element of the C3S and Northrop Grumman Space Technology patented data collection architecture. The centerpiece of SafetyNet(TM) is the system of fifteen globally-distributed ground receptors developed by Raytheon Company. These receptors or antennae will collect up to five times as much environmental data approximately four times faster than current polar-orbiting weather satellites. Once collected, these data will be forwarded near-instantaneously to U.S. weather centrals via global fiber optic network for processing and production of data records for use in environmental prediction models. In January 2008, Raytheon Company achieved a significant milestone for the NPOESS program by successfully completing the first phase of a major communications upgrade for Antarctica. The upgrade of the off-continent satellite communications link at McMurdo Station more than tripled the bandwidth available for scientific research, weather prediction, and health and safety of those stationed at McMurdo. The project is part of the company’s C3S under development for NPOESS. This upgrade paves the way for a second major communications upgrade planned for 2012 in preparation for the use of McMurdo Station as one of the 15 NPOESS ground stations worldwide that will be receiving environmental data collected by the NPOESS satellites.

Edge-assignment and figure-ground segmentation in short-term visual matching.

PubMed

Driver, J; Baylis, G C

1996-12-01

Eight experiments examined the role of edge-assignment in a contour matching task. Subjects judged whether the jagged vertical edge of a probe shape matched the jagged edge that divided two adjoining shapes in an immediately preceding figure-ground display. Segmentation factors biased assignment of this dividing edge toward a figural shape on just one of its sides. Subjects were faster and more accurate at matching when the probe edge had a corresponding assignment. The rapid emergence of this effect provides an on-line analog of the long-term memory advantage for figures over grounds which Rubin (1915/1958) reported. The present on-line advantage was found when figures were defined by relative contrast and size, or by symmetry, and could not be explained solely by the automatic drawing of attention toward the location of the figural region. However, deliberate attention to one region of an otherwise ambiguous figure-ground display did produce the advantage. We propose that one-sided assignment of dividing edges may be obligatory in vision.

How human resource organization can enhance space information acquisition and processing: the experience of the VENESAT-1 ground segment

NASA Astrophysics Data System (ADS)

Acevedo, Romina; Orihuela, Nuris; Blanco, Rafael; Varela, Francisco; Camacho, Enrique; Urbina, Marianela; Aponte, Luis Gabriel; Vallenilla, Leopoldo; Acuña, Liana; Becerra, Roberto; Tabare, Terepaima; Recaredo, Erica

2009-12-01

Built in cooperation with the P.R of China, in October 29th of 2008, the Bolivarian Republic of Venezuela launched its first Telecommunication Satellite, the so called VENESAT-1 (Simón Bolívar Satellite), which operates in C (covering Center America, The Caribbean Region and most of South America), Ku (Bolivia, Cuba, Dominican Republic, Haiti, Paraguay, Uruguay, Venezuela) and Ka bands (Venezuela). The launch of VENESAT-1 represents the starting point for Venezuela as an active player in the field of space science and technology. In order to fulfill mission requirements and to guarantee the satellite's health, local professionals must provide continuous monitoring, orbit calculation, maneuvers preparation and execution, data preparation and processing, as well as data base management at the VENESAT-1 Ground Segment, which includes both a primary and backup site. In summary, data processing and real time data management are part of the daily activities performed by the personnel at the ground segment. Using published and unpublished information, this paper presents how human resource organization can enhance space information acquisition and processing, by analyzing the proposed organizational structure for the VENESAT-1 Ground Segment. We have found that the proposed units within the organizational structure reflect 3 key issues for mission management: Satellite Operations, Ground Operations, and Site Maintenance. The proposed organization is simple (3 hierarchical levels and 7 units), and communication channels seem efficient in terms of facilitating information acquisition, processing, storage, flow and exchange. Furthermore, the proposal includes a manual containing the full description of personnel responsibilities and profile, which efficiently allocates the management and operation of key software for satellite operation such as the Real-time Data Transaction Software (RDTS), Data Management Software (DMS), and Carrier Spectrum Monitoring Software (CSM) within the different organizational units. In all this process, the international cooperation has played a key role for the consolidation of its space capabilities, especially through the continuous and arduous exchange of information, documentation and expertise between Chinese and Venezuelan personnel at the ground stations. Based on the principles of technology transfer and human training, since 1999 the Bolivarian Republic of Venezuela has shown an increasing interest in developing local space capabilities for peaceful purposes. According to the analysis we have performed, the proposed organizational structure of the VENESAT-1 ground segment will allow the country to face the challenges imposed by the operation of complex technologies. By enhancing human resource organization, this proposal will help to fulfill mission requirements, and to facilitate the safe access, processing and storage of satellite data across the organization, during both nominal and potential contingency situations.

Latency of TCP applications over the ATM-WAN using the GFR service category

NASA Astrophysics Data System (ADS)

Chen, Kuo-Hsien; Siliquini, John F.; Budrikis, Zigmantas

1998-10-01

The GFR service category has been proposed for data services in ATM networks. Since users are ultimately interested in data service that provide high efficiency and low latency, it is important to study the latency performance for data traffic of the GFR service category in an ATM network. Today much of the data traffic utilizes the TCP/IP protocol suite and in this paper we study through simulation the latency of TCP applications running over a wide-area ATM network utilizing the GFR service category using a realistic TCP traffic model. From this study, we find that during congestion periods the reserved bandwidth in GFR can improve the latency performance for TCP applications. However, due to TCP 'Slow Start' data segment generation dynamics, we show that a large proportion of TCP segments are discarded under network congestion even when the reserved bandwidth is equal to the average generated rate of user data. Therefore, a user experiences worse than expected latency performance when the network is congested. In this study we also examine the effects of segment size on the latency performance of TCP applications using the GFR service category.

Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models.

PubMed

Karimi, Davood; Samei, Golnoosh; Kesch, Claudia; Nir, Guy; Salcudean, Septimiu E

2018-05-15

Most of the existing convolutional neural network (CNN)-based medical image segmentation methods are based on methods that have originally been developed for segmentation of natural images. Therefore, they largely ignore the differences between the two domains, such as the smaller degree of variability in the shape and appearance of the target volume and the smaller amounts of training data in medical applications. We propose a CNN-based method for prostate segmentation in MRI that employs statistical shape models to address these issues. Our CNN predicts the location of the prostate center and the parameters of the shape model, which determine the position of prostate surface keypoints. To train such a large model for segmentation of 3D images using small data (1) we adopt a stage-wise training strategy by first training the network to predict the prostate center and subsequently adding modules for predicting the parameters of the shape model and prostate rotation, (2) we propose a data augmentation method whereby the training images and their prostate surface keypoints are deformed according to the displacements computed based on the shape model, and (3) we employ various regularization techniques. Our proposed method achieves a Dice score of 0.88, which is obtained by using both elastic-net and spectral dropout for regularization. Compared with a standard CNN-based method, our method shows significantly better segmentation performance on the prostate base and apex. Our experiments also show that data augmentation using the shape model significantly improves the segmentation results. Prior knowledge about the shape of the target organ can improve the performance of CNN-based segmentation methods, especially where image features are not sufficient for a precise segmentation. Statistical shape models can also be employed to synthesize additional training data that can ease the training of large CNNs.

S-net project: Construction of large scale seafloor observatory network for tsunamis and earthquakes in Japan

NASA Astrophysics Data System (ADS)

Mochizuki, M.; Kanazawa, T.; Uehira, K.; Shimbo, T.; Shiomi, K.; Kunugi, T.; Aoi, S.; Matsumoto, T.; Sekiguchi, S.; Yamamoto, N.; Takahashi, N.; Shinohara, M.; Yamada, T.

2016-12-01

National Research Institute for Earth Science and Disaster Resilience ( NIED ) has launched the project of constructing an observatory network for tsunamis and earthquakes on the seafloor. The observatory network was named "S-net, Seafloor Observation Network for Earthquakes and Tsunamis along the Japan Trench". The S-net consists of 150 seafloor observatories which are connected in line with submarine optical cables. The total length of submarine optical cable is about 5,700 km. The S-net system extends along Kuril and Japan trenches around Japan islands from north to south covering the area between southeast off island of Hokkaido and off the Boso Peninsula, Chiba Prefecture. The project has been financially supported by MEXT Japan. An observatory package is 34cm in diameter and 226cm long. Each observatory equips two units of a high sensitive water-depth sensor as a tsunami meter and four sets of three-component seismometers. The water-depth sensor has measurement resolution of sub-centimeter level. Combination of multiple seismometers secures wide dynamic range and robustness of the observation that are needed for early earthquake warning. The S-net is composed of six segment networks that consists of about 25 observatories and 800-1,600km length submarine optical cable. Five of six segment networks except the one covering the outer rise area of the Japan Trench has been already installed. The data from the observatories on those five segment networks are being transferred to the data center at NIED on a real-time basis, and then verification of data integrity are being carried out at the present moment. Installation of the last segment network of the S-net, that is, the outer rise one is scheduled to be finished within FY2016. Full-scale operation of the S-net will start at FY2017. We will report construction and operation of the S-net submarine cable system as well as the outline of the obtained data in this presentation.

Intelligent model-based OPC

NASA Astrophysics Data System (ADS)

Huang, W. C.; Lai, C. M.; Luo, B.; Tsai, C. K.; Chih, M. H.; Lai, C. W.; Kuo, C. C.; Liu, R. G.; Lin, H. T.

2006-03-01

Optical proximity correction is the technique of pre-distorting mask layouts so that the printed patterns are as close to the desired shapes as possible. For model-based optical proximity correction, a lithographic model to predict the edge position (contour) of patterns on the wafer after lithographic processing is needed. Generally, segmentation of edges is performed prior to the correction. Pattern edges are dissected into several small segments with corresponding target points. During the correction, the edges are moved back and forth from the initial drawn position, assisted by the lithographic model, to finally settle on the proper positions. When the correction converges, the intensity predicted by the model in every target points hits the model-specific threshold value. Several iterations are required to achieve the convergence and the computation time increases with the increase of the required iterations. An artificial neural network is an information-processing paradigm inspired by biological nervous systems, such as how the brain processes information. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. A neural network can be a powerful data-modeling tool that is able to capture and represent complex input/output relationships. The network can accurately predict the behavior of a system via the learning procedure. A radial basis function network, a variant of artificial neural network, is an efficient function approximator. In this paper, a radial basis function network was used to build a mapping from the segment characteristics to the edge shift from the drawn position. This network can provide a good initial guess for each segment that OPC has carried out. The good initial guess reduces the required iterations. Consequently, cycle time can be shortened effectively. The optimization of the radial basis function network for this system was practiced by genetic algorithm, which is an artificially intelligent optimization method with a high probability to obtain global optimization. From preliminary results, the required iterations were reduced from 5 to 2 for a simple dumbbell-shape layout.

Image texture segmentation using a neural network

NASA Astrophysics Data System (ADS)

Sayeh, Mohammed R.; Athinarayanan, Ragu; Dhali, Pushpuak

1992-09-01

In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes are represented by the stable equilibrium states of the system. Design of the system is based on synthesizing two local energy functions, namely, the learning and recall energy functions. Before the implementation of the segmentation process, a Gauss-Markov random field (GMRF) model is applied to the raw image. This application suitably reduces the image data and prepares the texture information for the neural network process. We give a simple image example illustrating the capability of the technique. The GMRF-generated features are also used for a clustering, based on the Euclidean distance.

Pattern Recognition Of Blood Vessel Networks In Ocular Fundus Images

NASA Astrophysics Data System (ADS)

Akita, K.; Kuga, H.

1982-11-01

We propose a computer method of recognizing blood vessel networks in color ocular fundus images which are used in the mass diagnosis of adult diseases such as hypertension and diabetes. A line detection algorithm is applied to extract the blood vessels, and the skeleton patterns of them are made to analyze and describe their structures. The recognition of line segments of arteries and/or veins in the vessel networks consists of three stages. First, a few segments which satisfy a certain constraint are picked up and discriminated as arteries or veins. This is the initial labeling. Then the remaining unknown ones are labeled by utilizing the physical level knowledge. We propose two schemes for this stage : a deterministic labeling and a probabilistic relaxation labeling. Finally the label of each line segment is checked so as to minimize the total number of labeling contradictions. Some experimental results are also presented.

Ground target recognition using rectangle estimation.

PubMed

Grönwall, Christina; Gustafsson, Fredrik; Millnert, Mille

2006-11-01

We propose a ground target recognition method based on 3-D laser radar data. The method handles general 3-D scattered data. It is based on the fact that man-made objects of complex shape can be decomposed to a set of rectangles. The ground target recognition method consists of four steps; 3-D size and orientation estimation, target segmentation into parts of approximately rectangular shape, identification of segments that represent the target's functional/main parts, and target matching with CAD models. The core in this approach is rectangle estimation. The performance of the rectangle estimation method is evaluated statistically using Monte Carlo simulations. A case study on tank recognition is shown, where 3-D data from four fundamentally different types of laser radar systems are used. Although the approach is tested on rather few examples, we believe that the approach is promising.

The automated ground network system

NASA Technical Reports Server (NTRS)

Smith, Miles T.; Militch, Peter N.

1993-01-01

The primary goal of the Automated Ground Network System (AGNS) project is to reduce Ground Network (GN) station life-cycle costs. To accomplish this goal, the AGNS project will employ an object-oriented approach to develop a new infrastructure that will permit continuous application of new technologies and methodologies to the Ground Network's class of problems. The AGNS project is a Total Quality (TQ) project. Through use of an open collaborative development environment, developers and users will have equal input into the end-to-end design and development process. This will permit direct user input and feedback and will enable rapid prototyping for requirements clarification. This paper describes the AGNS objectives, operations concept, and proposed design.

Space Operations

DTIC Science & Technology

2009-01-06

enabling precise blue force tracking (BFT), enhancing joint force situational awareness, maneuverability, and command and control (C2... spacecraft , transmits the status of those systems to the control segment on the ground, and receives and processes instructions from the control segment...missions include the tracking , telemetry, and control operations of: (1) Ultrahigh frequency (UHF) follow-on satellite system and fleet

Extraction of Capillary Non-perfusion from Fundus Fluorescein Angiogram

NASA Astrophysics Data System (ADS)

Sivaswamy, Jayanthi; Agarwal, Amit; Chawla, Mayank; Rani, Alka; Das, Taraprasad

Capillary Non-Perfusion (CNP) is a condition in diabetic retinopathy where blood ceases to flow to certain parts of the retina, potentially leading to blindness. This paper presents a solution for automatically detecting and segmenting CNP regions from fundus fluorescein angiograms (FFAs). CNPs are modelled as valleys, and a novel technique based on extrema pyramid is presented for trough-based valley detection. The obtained valley points are used to segment the desired CNP regions by employing a variance-based region growing scheme. The proposed algorithm has been tested on 40 images and validated against expert-marked ground truth. In this paper, we present results of testing and validation of our algorithm against ground truth and compare the segmentation performance against two others methods.The performance of the proposed algorithm is presented as a receiver operating characteristic (ROC) curve. The area under this curve is 0.842 and the distance of ROC from the ideal point (0,1) is 0.31. The proposed method for CNP segmentation was found to outperform the watershed [1] and heat-flow [2] based methods.

Component-Level Electronic-Assembly Repair (CLEAR) System Architecture

NASA Technical Reports Server (NTRS)

Oeftering, Richard C.; Bradish, Martin A.; Juergens, Jeffrey R.; Lewis, Michael J.; Vrnak, Daniel R.

2011-01-01

This document captures the system architecture for a Component-Level Electronic-Assembly Repair (CLEAR) capability needed for electronics maintenance and repair of the Constellation Program (CxP). CLEAR is intended to improve flight system supportability and reduce the mass of spares required to maintain the electronics of human rated spacecraft on long duration missions. By necessity it allows the crew to make repairs that would otherwise be performed by Earth based repair depots. Because of practical knowledge and skill limitations of small spaceflight crews they must be augmented by Earth based support crews and automated repair equipment. This system architecture covers the complete system from ground-user to flight hardware and flight crew and defines an Earth segment and a Space segment. The Earth Segment involves database management, operational planning, and remote equipment programming and validation processes. The Space Segment involves the automated diagnostic, test and repair equipment required for a complete repair process. This document defines three major subsystems including, tele-operations that links the flight hardware to ground support, highly reconfigurable diagnostics and test instruments, and a CLEAR Repair Apparatus that automates the physical repair process.

Space Geodetic Technique Co-location in Space: Simulation Results for the GRASP Mission

NASA Astrophysics Data System (ADS)

Kuzmicz-Cieslak, M.; Pavlis, E. C.

2011-12-01

The Global Geodetic Observing System-GGOS, places very stringent requirements in the accuracy and stability of future realizations of the International Terrestrial Reference Frame (ITRF): an origin definition at 1 mm or better at epoch and a temporal stability on the order of 0.1 mm/y, with similar numbers for the scale (0.1 ppb) and orientation components. These goals were derived from the requirements of Earth science problems that are currently the international community's highest priority. None of the geodetic positioning techniques can achieve this goal alone. This is due in part to the non-observability of certain attributes from a single technique. Another limitation is imposed from the extent and uniformity of the tracking network and the schedule of observational availability and number of suitable targets. The final limitation derives from the difficulty to "tie" the reference points of each technique at the same site, to an accuracy that will support the GGOS goals. The future GGOS network will address decisively the ground segment and to certain extent the space segment requirements. The JPL-proposed multi-technique mission GRASP (Geodetic Reference Antenna in Space) attempts to resolve the accurate tie between techniques, using their co-location in space, onboard a well-designed spacecraft equipped with GNSS receivers, a SLR retroreflector array, a VLBI beacon and a DORIS system. Using the anticipated system performance for all four techniques at the time the GGOS network is completed (ca 2020), we generated a number of simulated data sets for the development of a TRF. Our simulation studies examine the degree to which GRASP can improve the inter-technique "tie" issue compared to the classical approach, and the likely modus operandi for such a mission. The success of the examined scenarios is judged by the quality of the origin and scale definition of the resulting TRF.

Lightning NOx Statistics Derived by NASA Lightning Nitrogen Oxides Model (LNOM) Data Analyses

NASA Technical Reports Server (NTRS)

Koshak, William; Peterson, Harold

2013-01-01

What is the LNOM? The NASA Marshall Space Flight Center (MSFC) Lightning Nitrogen Oxides Model (LNOM) [Koshak et al., 2009, 2010, 2011; Koshak and Peterson 2011, 2013] analyzes VHF Lightning Mapping Array (LMA) and National Lightning Detection Network(TradeMark) (NLDN) data to estimate the lightning nitrogen oxides (LNOx) produced by individual flashes. Figure 1 provides an overview of LNOM functionality. Benefits of LNOM: (1) Does away with unrealistic "vertical stick" lightning channel models for estimating LNOx; (2) Uses ground-based VHF data that maps out the true channel in space and time to < 100 m accuracy; (3) Therefore, true channel segment height (ambient air density) is used to compute LNOx; (4) True channel length is used! (typically tens of kilometers since channel has many branches and "wiggles"); (5) Distinction between ground and cloud flashes are made; (6) For ground flashes, actual peak current from NLDN used to compute NOx from lightning return stroke; (7) NOx computed for several other lightning discharge processes (based on Cooray et al., 2009 theory): (a) Hot core of stepped leaders and dart leaders, (b) Corona sheath of stepped leader, (c) K-change, (d) Continuing Currents, and (e) M-components; and (8) LNOM statistics (see later) can be used to parameterize LNOx production for regional air quality models (like CMAQ), and for global chemical transport models (like GEOS-Chem).

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery.

PubMed

Liu, Yan; Stojadinovic, Strahinja; Hrycushko, Brian; Wardak, Zabi; Lau, Steven; Lu, Weiguo; Yan, Yulong; Jiang, Steve B; Zhen, Xin; Timmerman, Robert; Nedzi, Lucien; Gu, Xuejun

2017-01-01

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

Russian Earth Science Research Program on ISS

DOE Office of Scientific and Technical Information (OSTI.GOV)

Armand, N. A.; Tishchenko, Yu. G.

1999-01-22

Version of the Russian Earth Science Research Program on the Russian segment of ISS is proposed. The favorite tasks are selected, which may be solved with the use of space remote sensing methods and tools and which are worthwhile for realization. For solving these tasks the specialized device sets (submodules), corresponding to the specific of solved tasks, are working out. They would be specialized modules, transported to the ISS. Earth remote sensing research and ecological monitoring (high rates and large bodies transmitted from spaceborne information, comparatively stringent requirements to the period of its processing, etc.) cause rather high requirements tomore » the ground segment of receiving, processing, storing, and distribution of space information in the interests of the Earth natural resources investigation. Creation of the ground segment has required the development of the interdepartmental data receiving and processing center. Main directions of works within the framework of the ISS program are determined.« less

A Framework for Dimensioning VDL-2 Air-Ground Networks

NASA Technical Reports Server (NTRS)

Ribeiro, Leila Z.; Monticone, Leone C.; Snow, Richard E.; Box, Frank; Apaza, Rafel; Bretmersky, Steven

2014-01-01

This paper describes a framework developed at MITRE for dimensioning a Very High Frequency (VHF) Digital Link Mode 2 (VDL-2) Air-to-Ground network. This framework was developed to support the FAA's Data Communications (Data Comm) program by providing estimates of expected capacity required for the air-ground network services that will support Controller-Pilot-Data-Link Communications (CPDLC), as well as the spectrum needed to operate the system at required levels of performance. The Data Comm program is part of the FAA's NextGen initiative to implement advanced communication capabilities in the National Airspace System (NAS). The first component of the framework is the radio-frequency (RF) coverage design for the network ground stations. Then we proceed to describe the approach used to assess the aircraft geographical distribution and the data traffic demand expected in the network. The next step is the resource allocation utilizing optimization algorithms developed in MITRE's Spectrum ProspectorTM tool to propose frequency assignment solutions, and a NASA-developed VDL-2 tool to perform simulations and determine whether a proposed plan meets the desired performance requirements. The framework presented is capable of providing quantitative estimates of multiple variables related to the air-ground network, in order to satisfy established coverage, capacity and latency performance requirements. Outputs include: coverage provided at different altitudes; data capacity required in the network, aggregated or on a per ground station basis; spectrum (pool of frequencies) needed for the system to meet a target performance; optimized frequency plan for a given scenario; expected performance given spectrum available; and, estimates of throughput distributions for a given scenario. We conclude with a discussion aimed at providing insight into the tradeoffs and challenges identified with respect to radio resource management for VDL-2 air-ground networks.

The 2014 Mw6.1 South Napa Earthquake: A unilateral rupture with shallow asperity and rapid afterslip

USGS Publications Warehouse

Wei, Shengji; Barbot, Sylvain; Graves, Robert; Lienkaemper, James J.; Wang, Teng; Hudnut, Kenneth W.; Fu, Yuning; Helmberger, Don

2015-01-01

The Mw6.1 South Napa earthquake occurred near Napa, California on August 24, 2014 (UTC), and was the largest inland earthquake in Northern California since the 1989 Mw6.9 Loma Prieta earthquake. The first report of the earthquake from the Northern California Earthquake Data Center (NCEDC) indicates a hypocentral depth of 11.0km with longitude and latitude of (122.3105°W, 38.217°N). Surface rupture was documented by field observations and Lidar imaging (Brooks et al. 2014; Hudnut et al. 2014; Brocher et al., 2015), with about 12 km of continuous rupture starting near the epicenter and extending to the northwest. The southern part of the rupture is relatively straight, but the strike changes by about 15° at the northern end over a 6-km segment. The peak dextral offset was observed near the Buhman residence with right-.‐lateral motion of 46 cm, near the location where the strike of fault begins to rotate clock-.‐wise (Hudnut et al., 2014). The earthquake was well recorded by the strong motion network operated by the NCEDC, the California Geological Survey and the U.S. Geological Survey (USGS). There are about 12 sites within an epicentral distance of 15km, with relatively good azimuthal coverage (Fig.1). The largest peak-ground-velocity (PGV) of nearly 100 cm/s was observed on station 1765, which is the closest station to the rupture and lies about 3 km east of the northern segment (Fig. 1). The ground deformation associated with the earthquake was also well recorded by the high-resolution COSMO-SkyMed satellite and Sentinel-1A satellite, providing independent static observations.

Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging.

PubMed

Fu, J C; Chen, C C; Chai, J W; Wong, S T C; Li, I C

2010-06-01

We propose an automatic hybrid image segmentation model that integrates the statistical expectation maximization (EM) model and the spatial pulse coupled neural network (PCNN) for brain magnetic resonance imaging (MRI) segmentation. In addition, an adaptive mechanism is developed to fine tune the PCNN parameters. The EM model serves two functions: evaluation of the PCNN image segmentation and adaptive adjustment of the PCNN parameters for optimal segmentation. To evaluate the performance of the adaptive EM-PCNN, we use it to segment MR brain image into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). The performance of the adaptive EM-PCNN is compared with that of the non-adaptive EM-PCNN, EM, and Bias Corrected Fuzzy C-Means (BCFCM) algorithms. The result is four sets of boundaries for the GM and the brain parenchyma (GM+WM), the two regions of most interest in medical research and clinical applications. Each set of boundaries is compared with the golden standard to evaluate the segmentation performance. The adaptive EM-PCNN significantly outperforms the non-adaptive EM-PCNN, EM, and BCFCM algorithms in gray mater segmentation. In brain parenchyma segmentation, the adaptive EM-PCNN significantly outperforms the BCFCM only. However, the adaptive EM-PCNN is better than the non-adaptive EM-PCNN and EM on average. We conclude that of the three approaches, the adaptive EM-PCNN yields the best results for gray matter and brain parenchyma segmentation. Copyright 2009 Elsevier Ltd. All rights reserved.

A deep learning model integrating FCNNs and CRFs for brain tumor segmentation.

PubMed

Zhao, Xiaomei; Wu, Yihong; Song, Guidong; Li, Zhenye; Zhang, Yazhuo; Fan, Yong

2018-01-01

Accurate and reliable brain tumor segmentation is a critical component in cancer diagnosis, treatment planning, and treatment outcome evaluation. Build upon successful deep learning techniques, a novel brain tumor segmentation method is developed by integrating fully convolutional neural networks (FCNNs) and Conditional Random Fields (CRFs) in a unified framework to obtain segmentation results with appearance and spatial consistency. We train a deep learning based segmentation model using 2D image patches and image slices in following steps: 1) training FCNNs using image patches; 2) training CRFs as Recurrent Neural Networks (CRF-RNN) using image slices with parameters of FCNNs fixed; and 3) fine-tuning the FCNNs and the CRF-RNN using image slices. Particularly, we train 3 segmentation models using 2D image patches and slices obtained in axial, coronal and sagittal views respectively, and combine them to segment brain tumors using a voting based fusion strategy. Our method could segment brain images slice-by-slice, much faster than those based on image patches. We have evaluated our method based on imaging data provided by the Multimodal Brain Tumor Image Segmentation Challenge (BRATS) 2013, BRATS 2015 and BRATS 2016. The experimental results have demonstrated that our method could build a segmentation model with Flair, T1c, and T2 scans and achieve competitive performance as those built with Flair, T1, T1c, and T2 scans. Copyright © 2017 Elsevier B.V. All rights reserved.

Effects of the addition of functional electrical stimulation to ground level gait training with body weight support after chronic stroke.

PubMed

Prado-Medeiros, Christiane L; Sousa, Catarina O; Souza, Andréa S; Soares, Márcio R; Barela, Ana M F; Salvini, Tania F

2011-01-01

The addition of functional electrical stimulation (FES) to treadmill gait training with partial body weight support (BWS) has been proposed as a strategy to facilitate gait training in people with hemiparesis. However, there is a lack of studies that evaluate the effectiveness of FES addition on ground level gait training with BWS, which is the most common locomotion surface. To investigate the additional effects of commum peroneal nerve FES combined with gait training and BWS on ground level, on spatial-temporal gait parameters, segmental angles, and motor function. Twelve people with chronic hemiparesis participated in the study. An A1-B-A2 design was applied. A1 and A2 corresponded to ground level gait training using BWS, and B corresponded to the same training with the addition of FES. The assessments were performed using the Modified Ashworth Scale (MAS), Functional Ambulation Category (FAC), Rivermead Motor Assessment (RMA), and filming. The kinematics analyzed variables were mean walking speed of locomotion; step length; stride length, speed and duration; initial and final double support duration; single-limb support duration; swing period; range of motion (ROM), maximum and minimum angles of foot, leg, thigh, and trunk segments. There were not changes between phases for the functional assessment of RMA, for the spatial-temporal gait variables and segmental angles, no changes were observed after the addition of FES. The use of FES on ground level gait training with BWS did not provide additional benefits for all assessed parameters.

Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging.

PubMed

Liu, Fang; Zhou, Zhaoye; Jang, Hyungseok; Samsonov, Alexey; Zhao, Gengyan; Kijowski, Richard

2018-04-01

To describe and evaluate a new fully automated musculoskeletal tissue segmentation method using deep convolutional neural network (CNN) and three-dimensional (3D) simplex deformable modeling to improve the accuracy and efficiency of cartilage and bone segmentation within the knee joint. A fully automated segmentation pipeline was built by combining a semantic segmentation CNN and 3D simplex deformable modeling. A CNN technique called SegNet was applied as the core of the segmentation method to perform high resolution pixel-wise multi-class tissue classification. The 3D simplex deformable modeling refined the output from SegNet to preserve the overall shape and maintain a desirable smooth surface for musculoskeletal structure. The fully automated segmentation method was tested using a publicly available knee image data set to compare with currently used state-of-the-art segmentation methods. The fully automated method was also evaluated on two different data sets, which include morphological and quantitative MR images with different tissue contrasts. The proposed fully automated segmentation method provided good segmentation performance with segmentation accuracy superior to most of state-of-the-art methods in the publicly available knee image data set. The method also demonstrated versatile segmentation performance on both morphological and quantitative musculoskeletal MR images with different tissue contrasts and spatial resolutions. The study demonstrates that the combined CNN and 3D deformable modeling approach is useful for performing rapid and accurate cartilage and bone segmentation within the knee joint. The CNN has promising potential applications in musculoskeletal imaging. Magn Reson Med 79:2379-2391, 2018. © 2017 International Society for Magnetic Resonance in Medicine. © 2017 International Society for Magnetic Resonance in Medicine.

ASM Based Synthesis of Handwritten Arabic Text Pages

PubMed Central

Al-Hamadi, Ayoub; Elzobi, Moftah; El-etriby, Sherif; Ghoneim, Ahmed

2015-01-01

Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available. PMID:26295059

ASM Based Synthesis of Handwritten Arabic Text Pages.

PubMed

Dinges, Laslo; Al-Hamadi, Ayoub; Elzobi, Moftah; El-Etriby, Sherif; Ghoneim, Ahmed

2015-01-01

Document analysis tasks, as text recognition, word spotting, or segmentation, are highly dependent on comprehensive and suitable databases for training and validation. However their generation is expensive in sense of labor and time. As a matter of fact, there is a lack of such databases, which complicates research and development. This is especially true for the case of Arabic handwriting recognition, that involves different preprocessing, segmentation, and recognition methods, which have individual demands on samples and ground truth. To bypass this problem, we present an efficient system that automatically turns Arabic Unicode text into synthetic images of handwritten documents and detailed ground truth. Active Shape Models (ASMs) based on 28046 online samples were used for character synthesis and statistical properties were extracted from the IESK-arDB database to simulate baselines and word slant or skew. In the synthesis step ASM based representations are composed to words and text pages, smoothed by B-Spline interpolation and rendered considering writing speed and pen characteristics. Finally, we use the synthetic data to validate a segmentation method. An experimental comparison with the IESK-arDB database encourages to train and test document analysis related methods on synthetic samples, whenever no sufficient natural ground truthed data is available.

LANDSAT-D Investigations Workshop

NASA Technical Reports Server (NTRS)

1982-01-01

Viewgraphs are presented which highlight LANDSAT-D project status and ground segment; early access TM processing; LANDSAT-D data acquisition and availability; LANDSAT-D performance characterization; MSS pre-NOAA characterization; MSS radiometric sensor performance (spectral information, absolute calibration, and ground processing); MSS geometric sensor performance; and MSS geometric processing and calibration.

A deep learning approach for real time prostate segmentation in freehand ultrasound guided biopsy.

PubMed

Anas, Emran Mohammad Abu; Mousavi, Parvin; Abolmaesumi, Purang

2018-06-01

Targeted prostate biopsy, incorporating multi-parametric magnetic resonance imaging (mp-MRI) and its registration with ultrasound, is currently the state-of-the-art in prostate cancer diagnosis. The registration process in most targeted biopsy systems today relies heavily on accurate segmentation of ultrasound images. Automatic or semi-automatic segmentation is typically performed offline prior to the start of the biopsy procedure. In this paper, we present a deep neural network based real-time prostate segmentation technique during the biopsy procedure, hence paving the way for dynamic registration of mp-MRI and ultrasound data. In addition to using convolutional networks for extracting spatial features, the proposed approach employs recurrent networks to exploit the temporal information among a series of ultrasound images. One of the key contributions in the architecture is to use residual convolution in the recurrent networks to improve optimization. We also exploit recurrent connections within and across different layers of the deep networks to maximize the utilization of the temporal information. Furthermore, we perform dense and sparse sampling of the input ultrasound sequence to make the network robust to ultrasound artifacts. Our architecture is trained on 2,238 labeled transrectal ultrasound images, with an additional 637 and 1,017 unseen images used for validation and testing, respectively. We obtain a mean Dice similarity coefficient of 93%, a mean surface distance error of 1.10 mm and a mean Hausdorff distance error of 3.0 mm. A comparison of the reported results with those of a state-of-the-art technique indicates statistically significant improvement achieved by the proposed approach. Copyright © 2018 Elsevier B.V. All rights reserved.

LEO Download Capacity Analysis for a Network of Adaptive Array Ground Stations

NASA Technical Reports Server (NTRS)

Ingram, Mary Ann; Barott, William C.; Popovic, Zoya; Rondineau, Sebastien; Langley, John; Romanofsky, Robert; Lee, Richard Q.; Miranda, Felix; Steffes, Paul; Mandl, Dan

2005-01-01

To lower costs and reduce latency, a network of adaptive array ground stations, distributed across the United States, is considered for the downlink of a polar-orbiting low earth orbiting (LEO) satellite. Assuming the X-band 105 Mbps transmitter of NASA s Earth Observing 1 (EO-1) satellite with a simple line-of-sight propagation model, the average daily download capacity in bits for a network of adaptive array ground stations is compared to that of a single 11 m dish in Poker Flats, Alaska. Each adaptive array ground station is assumed to have multiple steerable antennas, either mechanically steered dishes or phased arrays that are mechanically steered in azimuth and electronically steered in elevation. Phased array technologies that are being developed for this application are the space-fed lens (SFL) and the reflectarray. Optimization of the different boresight directions of the phased arrays within a ground station is shown to significantly increase capacity; for example, this optimization quadruples the capacity for a ground station with eight SFLs. Several networks comprising only two to three ground stations are shown to meet or exceed the capacity of the big dish, Cutting the data rate by half, which saves modem costs and increases the coverage area of each ground station, is shown to increase the average daily capacity of the network for some configurations.

SU-C-207B-05: Tissue Segmentation of Computed Tomography Images Using a Random Forest Algorithm: A Feasibility Study

DOE Office of Scientific and Technical Information (OSTI.GOV)

Polan, D; Brady, S; Kaufman, R

2016-06-15

Purpose: Develop an automated Random Forest algorithm for tissue segmentation of CT examinations. Methods: Seven materials were classified for segmentation: background, lung/internal gas, fat, muscle, solid organ parenchyma, blood/contrast, and bone using Matlab and the Trainable Weka Segmentation (TWS) plugin of FIJI. The following classifier feature filters of TWS were investigated: minimum, maximum, mean, and variance each evaluated over a pixel radius of 2n, (n = 0–4). Also noise reduction and edge preserving filters, Gaussian, bilateral, Kuwahara, and anisotropic diffusion, were evaluated. The algorithm used 200 trees with 2 features per node. A training data set was established using anmore » anonymized patient’s (male, 20 yr, 72 kg) chest-abdomen-pelvis CT examination. To establish segmentation ground truth, the training data were manually segmented using Eclipse planning software, and an intra-observer reproducibility test was conducted. Six additional patient data sets were segmented based on classifier data generated from the training data. Accuracy of segmentation was determined by calculating the Dice similarity coefficient (DSC) between manual and auto segmented images. Results: The optimized autosegmentation algorithm resulted in 16 features calculated using maximum, mean, variance, and Gaussian blur filters with kernel radii of 1, 2, and 4 pixels, in addition to the original CT number, and Kuwahara filter (linear kernel of 19 pixels). Ground truth had a DSC of 0.94 (range: 0.90–0.99) for adult and 0.92 (range: 0.85–0.99) for pediatric data sets across all seven segmentation classes. The automated algorithm produced segmentation with an average DSC of 0.85 ± 0.04 (range: 0.81–1.00) for the adult patients, and 0.86 ± 0.03 (range: 0.80–0.99) for the pediatric patients. Conclusion: The TWS Random Forest auto-segmentation algorithm was optimized for CT environment, and able to segment seven material classes over a range of body habitus and CT protocol parameters with an average DSC of 0.86 ± 0.04 (range: 0.80–0.99).« less

Development of a Subject-Specific Foot-Ground Contact Model for Walking

PubMed Central

Jackson, Jennifer N.; Hass, Chris J.; Fregly, Benjamin J.

2016-01-01

Computational walking simulations could facilitate the development of improved treatments for clinical conditions affecting walking ability. Since an effective treatment is likely to change a patient's foot-ground contact pattern and timing, such simulations should ideally utilize deformable foot-ground contact models tailored to the patient's foot anatomy and footwear. However, no study has reported a deformable modeling approach that can reproduce all six ground reaction quantities (expressed as three reaction force components, two center of pressure (CoP) coordinates, and a free reaction moment) for an individual subject during walking. This study proposes such an approach for use in predictive optimizations of walking. To minimize complexity, we modeled each foot as two rigid segments—a hindfoot (HF) segment and a forefoot (FF) segment—connected by a pin joint representing the toes flexion–extension axis. Ground reaction forces (GRFs) and moments acting on each segment were generated by a grid of linear springs with nonlinear damping and Coulomb friction spread across the bottom of each segment. The stiffness and damping of each spring and common friction parameter values for all springs were calibrated for both feet simultaneously via a novel three-stage optimization process that used motion capture and ground reaction data collected from a single walking trial. The sequential three-stage process involved matching (1) the vertical force component, (2) all three force components, and finally (3) all six ground reaction quantities. The calibrated model was tested using four additional walking trials excluded from calibration. With only small changes in input kinematics, the calibrated model reproduced all six ground reaction quantities closely (root mean square (RMS) errors less than 13 N for all three forces, 25 mm for anterior–posterior (AP) CoP, 8 mm for medial–lateral (ML) CoP, and 2 N·m for the free moment) for both feet in all walking trials. The largest errors in AP CoP occurred at the beginning and end of stance phase when the vertical ground reaction force (vGRF) was small. Subject-specific deformable foot-ground contact models created using this approach should enable changes in foot-ground contact pattern to be predicted accurately by gait optimization studies, which may lead to improvements in personalized rehabilitation medicine. PMID:27379886

Self-organising mixture autoregressive model for non-stationary time series modelling.

PubMed

Ni, He; Yin, Hujun

2008-12-01

Modelling non-stationary time series has been a difficult task for both parametric and nonparametric methods. One promising solution is to combine the flexibility of nonparametric models with the simplicity of parametric models. In this paper, the self-organising mixture autoregressive (SOMAR) network is adopted as a such mixture model. It breaks time series into underlying segments and at the same time fits local linear regressive models to the clusters of segments. In such a way, a global non-stationary time series is represented by a dynamic set of local linear regressive models. Neural gas is used for a more flexible structure of the mixture model. Furthermore, a new similarity measure has been introduced in the self-organising network to better quantify the similarity of time series segments. The network can be used naturally in modelling and forecasting non-stationary time series. Experiments on artificial, benchmark time series (e.g. Mackey-Glass) and real-world data (e.g. numbers of sunspots and Forex rates) are presented and the results show that the proposed SOMAR network is effective and superior to other similar approaches.

Graph-based unsupervised segmentation algorithm for cultured neuronal networks' structure characterization and modeling.

PubMed

de Santos-Sierra, Daniel; Sendiña-Nadal, Irene; Leyva, Inmaculada; Almendral, Juan A; Ayali, Amir; Anava, Sarit; Sánchez-Ávila, Carmen; Boccaletti, Stefano

2015-06-01

Large scale phase-contrast images taken at high resolution through the life of a cultured neuronal network are analyzed by a graph-based unsupervised segmentation algorithm with a very low computational cost, scaling linearly with the image size. The processing automatically retrieves the whole network structure, an object whose mathematical representation is a matrix in which nodes are identified neurons or neurons' clusters, and links are the reconstructed connections between them. The algorithm is also able to extract any other relevant morphological information characterizing neurons and neurites. More importantly, and at variance with other segmentation methods that require fluorescence imaging from immunocytochemistry techniques, our non invasive measures entitle us to perform a longitudinal analysis during the maturation of a single culture. Such an analysis furnishes the way of individuating the main physical processes underlying the self-organization of the neurons' ensemble into a complex network, and drives the formulation of a phenomenological model yet able to describe qualitatively the overall scenario observed during the culture growth. © 2014 International Society for Advancement of Cytometry.

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities.

PubMed

Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; van Uden, Inge W M; Sanchez, Clara I; Litjens, Geert; de Leeuw, Frank-Erik; van Ginneken, Bram; Marchiori, Elena; Platel, Bram

2017-07-11

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

Simultaneous Scalp Electroencephalography (EEG), Electromyography (EMG), and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

PubMed Central

Bulea, Thomas C.; Kilicarslan, Atilla; Ozdemir, Recep; Paloski, William H.; Contreras-Vidal, Jose L.

2013-01-01

Recent studies support the involvement of supraspinal networks in control of bipedal human walking. Part of this evidence encompasses studies, including our previous work, demonstrating that gait kinematics and limb coordination during treadmill walking can be inferred from the scalp electroencephalogram (EEG) with reasonably high decoding accuracies. These results provide impetus for development of non-invasive brain-machine-interface (BMI) systems for use in restoration and/or augmentation of gait- a primary goal of rehabilitation research. To date, studies examining EEG decoding of activity during gait have been limited to treadmill walking in a controlled environment. However, to be practically viable a BMI system must be applicable for use in everyday locomotor tasks such as over ground walking and turning. Here, we present a novel protocol for non-invasive collection of brain activity (EEG), muscle activity (electromyography (EMG)), and whole-body kinematic data (head, torso, and limb trajectories) during both treadmill and over ground walking tasks. By collecting these data in the uncontrolled environment insight can be gained regarding the feasibility of decoding unconstrained gait and surface EMG from scalp EEG. PMID:23912203

The Telecommunications and Data Acquisition Report

NASA Technical Reports Server (NTRS)

Posner, E. C. (Editor)

1984-01-01

Tracking and ground-based navigation; communications, spacecraft-ground; station control and system technology; capabilities for new projects; networks consolidation program; and network sustaining are described.

Off-lexicon online Arabic handwriting recognition using neural network

NASA Astrophysics Data System (ADS)

Yahia, Hamdi; Chaabouni, Aymen; Boubaker, Houcine; Alimi, Adel M.

2017-03-01

This paper highlights a new method for online Arabic handwriting recognition based on graphemes segmentation. The main contribution of our work is to explore the utility of Beta-elliptic model in segmentation and features extraction for online handwriting recognition. Indeed, our method consists in decomposing the input signal into continuous part called graphemes based on Beta-Elliptical model, and classify them according to their position in the pseudo-word. The segmented graphemes are then described by the combination of geometric features and trajectory shape modeling. The efficiency of the considered features has been evaluated using feed forward neural network classifier. Experimental results using the benchmarking ADAB Database show the performance of the proposed method.

Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation.

PubMed

Bobo, Meg F; Bao, Shunxing; Huo, Yuankai; Yao, Yuang; Virostko, Jack; Plassard, Andrew J; Lyu, Ilwoo; Assad, Albert; Abramson, Richard G; Hilmes, Melissa A; Landman, Bennett A

2018-03-01

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities.

Fully convolutional neural networks improve abdominal organ segmentation

NASA Astrophysics Data System (ADS)

Bobo, Meg F.; Bao, Shunxing; Huo, Yuankai; Yao, Yuang; Virostko, Jack; Plassard, Andrew J.; Lyu, Ilwoo; Assad, Albert; Abramson, Richard G.; Hilmes, Melissa A.; Landman, Bennett A.

2018-03-01

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities. 1

Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features.

PubMed

Kushibar, Kaisar; Valverde, Sergi; González-Villà, Sandra; Bernal, Jose; Cabezas, Mariano; Oliver, Arnau; Lladó, Xavier

2018-06-15

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

The Out of Service Guest Pilot Evaluation of the Two-segment Noise Abatement Approach in the Boeing B727-200

NASA Technical Reports Server (NTRS)

Nylen, W. E.

1974-01-01

Guest pilot evaluation results of an approach profile modification for reducing ground level noise under the approach of jet aircraft runways are reported. Evaluation results were used to develop a two segmented landing approach procedure and equipment necessary to obtain pilot, airline, and FAA acceptance of the two segmented flight as a routine way of operating aircraft on approach and landing. Data are given on pilot workload and acceptance of the procedure.

Systems Architecture for Fully Autonomous Space Missions

NASA Technical Reports Server (NTRS)

Esper, Jamie; Schnurr, R.; VanSteenberg, M.; Brumfield, Mark (Technical Monitor)

2002-01-01

The NASA Goddard Space Flight Center is working to develop a revolutionary new system architecture concept in support of fully autonomous missions. As part of GSFC's contribution to the New Millenium Program (NMP) Space Technology 7 Autonomy and on-Board Processing (ST7-A) Concept Definition Study, the system incorporates the latest commercial Internet and software development ideas and extends them into NASA ground and space segment architectures. The unique challenges facing the exploration of remote and inaccessible locales and the need to incorporate corresponding autonomy technologies within reasonable cost necessitate the re-thinking of traditional mission architectures. A measure of the resiliency of this architecture in its application to a broad range of future autonomy missions will depend on its effectiveness in leveraging from commercial tools developed for the personal computer and Internet markets. Specialized test stations and supporting software come to past as spacecraft take advantage of the extensive tools and research investments of billion-dollar commercial ventures. The projected improvements of the Internet and supporting infrastructure go hand-in-hand with market pressures that provide continuity in research. By taking advantage of consumer-oriented methods and processes, space-flight missions will continue to leverage on investments tailored to provide better services at reduced cost. The application of ground and space segment architectures each based on Local Area Networks (LAN), the use of personal computer-based operating systems, and the execution of activities and operations through a Wide Area Network (Internet) enable a revolution in spacecraft mission formulation, implementation, and flight operations. Hardware and software design, development, integration, test, and flight operations are all tied-in closely to a common thread that enables the smooth transitioning between program phases. The application of commercial software development techniques lays the foundation for delivery of product-oriented flight software modules and models. Software can then be readily applied to support the on-board autonomy required for mission self-management. An on-board intelligent system, based on advanced scripting languages, facilitates the mission autonomy required to offload ground system resources, and enables the spacecraft to manage itself safely through an efficient and effective process of reactive planning, science data acquisition, synthesis, and transmission to the ground. Autonomous ground systems in turn coordinate and support schedule contact times with the spacecraft. Specific autonomy software modules on-board include mission and science planners, instrument and subsystem control, and fault tolerance response software, all residing within a distributed computing environment supported through the flight LAN. Autonomy also requires the minimization of human intervention between users on the ground and the spacecraft, and hence calls for the elimination of the traditional operations control center as a funnel for data manipulation. Basic goal-oriented commands are sent directly from the user to the spacecraft through a distributed internet-based payload operations "center". The ensuing architecture calls for the use of spacecraft as point extensions on the Internet. This paper will detail the system architecture implementation chosen to enable cost-effective autonomous missions with applicability to a broad range of conditions. It will define the structure needed for implementation of such missions, including software and hardware infrastructures. The overall architecture is then laid out as a common thread in the mission life cycle from formulation through implementation and flight operations.

Ground Water Atlas of the United States: Segment 12, Connecticut, Maine, Massachusetts, New Hampshire, New York, Rhode Island, Vermont

USGS Publications Warehouse

Olcott, Perry G.

1995-01-01

The State of New York and the six New England States of Maine, Vermont, New Hampshire, Massachusetts, Connecticut, and Rhode Island compose Segment 12 of this Atlas (fig. 1). The seven States have a total land area of about 116,000 square miles (table 1); all but a small area in southwestern New York has been glaciated. Population in the States of Segment 12 totals about 30,408,000 (table 1) and is concentrated in southern and eastern Massachusetts, Connecticut, Rhode Island, and especially New York (fig. 1). The northern part of the segment and the mountainous areas of New York and much of New Hampshire, Vermont, and Maine are sparsely populated. The percentage of population supplied from ground-water sources during 1980 was 54 to 60 percent in Maine, New Hampshire, and Vermont (table 1). Nearly all rural, domestic, and small-community water systems obtain water from wells that are, in comparison with other sources, the safest and the least expensive to install and maintain. Where water demand is great-in the urban areas of New York, Connecticut, Massachusetts, and Rhode Island-sophisticated reservoir, pipeline, and purification systems are economically feasible and are needed to meet demands. Surface water is the principal source of supply in these four States, and ground water was used to supply only 24 to 35 percent of their population during 1980 (table 1).

The use of zeolites to generate PET phantoms for the validation of quantification strategies in oncology.

PubMed

Zito, Felicia; De Bernardi, Elisabetta; Soffientini, Chiara; Canzi, Cristina; Casati, Rosangela; Gerundini, Paolo; Baselli, Giuseppe

2012-09-01

In recent years, segmentation algorithms and activity quantification methods have been proposed for oncological (18)F-fluorodeoxyglucose (FDG) PET. A full assessment of these algorithms, necessary for a clinical transfer, requires a validation on data sets provided with a reliable ground truth as to the imaged activity distribution, which must be as realistic as possible. The aim of this work is to propose a strategy to simulate lesions of uniform uptake and irregular shape in an anthropomorphic phantom, with the possibility to easily obtain a ground truth as to lesion activity and borders. Lesions were simulated with samples of clinoptilolite, a family of natural zeolites of irregular shape, able to absorb aqueous solutions of (18)F-FDG, available in a wide size range, and nontoxic. Zeolites were soaked in solutions of (18)F-FDG for increasing times up to 120 min and their absorptive properties were characterized as function of soaking duration, solution concentration, and zeolite dry weight. Saturated zeolites were wrapped in Parafilm, positioned inside an Alderson thorax-abdomen phantom and imaged with a PET-CT scanner. The ground truth for the activity distribution of each zeolite was obtained by segmenting high-resolution finely aligned CT images, on the basis of independently obtained volume measurements. The fine alignment between CT and PET was validated by comparing the CT-derived ground truth to a set of zeolites' PET threshold segmentations in terms of Dice index and volume error. The soaking time necessary to achieve saturation increases with zeolite dry weight, with a maximum of about 90 min for the largest sample. At saturation, a linear dependence of the uptake normalized to the solution concentration on zeolite dry weight (R(2) = 0.988), as well as a uniform distribution of the activity over the entire zeolite volume from PET imaging were demonstrated. These findings indicate that the (18)F-FDG solution is able to saturate the zeolite pores and that the concentration does not influence the distribution uniformity of both solution and solute, at least at the trace concentrations used for zeolite activation. An additional proof of uniformity of zeolite saturation was obtained observing a correspondence between uptake and adsorbed volume of solution, corresponding to about 27.8% of zeolite volume. As to the ground truth for zeolites positioned inside the phantom, the segmentation of finely aligned CT images provided reliable borders, as demonstrated by a mean absolute volume error of 2.8% with respect to the PET threshold segmentation corresponding to the maximum Dice. The proposed methodology allowed obtaining an experimental phantom data set that can be used as a feasible tool to test and validate quantification and segmentation algorithms for PET in oncology. The phantom is currently under consideration for being included in a benchmark designed by AAPM TG211, which will be available to the community to evaluate PET automatic segmentation methods.

Quality assurance using outlier detection on an automatic segmentation method for the cerebellar peduncles

NASA Astrophysics Data System (ADS)

Li, Ke; Ye, Chuyang; Yang, Zhen; Carass, Aaron; Ying, Sarah H.; Prince, Jerry L.

2016-03-01

Cerebellar peduncles (CPs) are white matter tracts connecting the cerebellum to other brain regions. Automatic segmentation methods of the CPs have been proposed for studying their structure and function. Usually the performance of these methods is evaluated by comparing segmentation results with manual delineations (ground truth). However, when a segmentation method is run on new data (for which no ground truth exists) it is highly desirable to efficiently detect and assess algorithm failures so that these cases can be excluded from scientific analysis. In this work, two outlier detection methods aimed to assess the performance of an automatic CP segmentation algorithm are presented. The first one is a univariate non-parametric method using a box-whisker plot. We first categorize automatic segmentation results of a dataset of diffusion tensor imaging (DTI) scans from 48 subjects as either a success or a failure. We then design three groups of features from the image data of nine categorized failures for failure detection. Results show that most of these features can efficiently detect the true failures. The second method—supervised classification—was employed on a larger DTI dataset of 249 manually categorized subjects. Four classifiers—linear discriminant analysis (LDA), logistic regression (LR), support vector machine (SVM), and random forest classification (RFC)—were trained using the designed features and evaluated using a leave-one-out cross validation. Results show that the LR performs worst among the four classifiers and the other three perform comparably, which demonstrates the feasibility of automatically detecting segmentation failures using classification methods.

Saliency U-Net: A regional saliency map-driven hybrid deep learning network for anomaly segmentation

NASA Astrophysics Data System (ADS)

Karargyros, Alex; Syeda-Mahmood, Tanveer

2018-02-01

Deep learning networks are gaining popularity in many medical image analysis tasks due to their generalized ability to automatically extract relevant features from raw images. However, this can make the learning problem unnecessarily harder requiring network architectures of high complexity. In case of anomaly detection, in particular, there is often sufficient regional difference between the anomaly and the surrounding parenchyma that could be easily highlighted through bottom-up saliency operators. In this paper we propose a new hybrid deep learning network using a combination of raw image and such regional maps to more accurately learn the anomalies using simpler network architectures. Specifically, we modify a deep learning network called U-Net using both the raw and pre-segmented images as input to produce joint encoding (contraction) and expansion paths (decoding) in the U-Net. We present results of successfully delineating subdural and epidural hematomas in brain CT imaging and liver hemangioma in abdominal CT images using such network.

Boundary segmentation for fluorescence microscopy using steerable filters

NASA Astrophysics Data System (ADS)

Ho, David Joon; Salama, Paul; Dunn, Kenneth W.; Delp, Edward J.

2017-02-01

Fluorescence microscopy is used to image multiple subcellular structures in living cells which are not readily observed using conventional optical microscopy. Moreover, two-photon microscopy is widely used to image structures deeper in tissue. Recent advancement in fluorescence microscopy has enabled the generation of large data sets of images at different depths, times, and spectral channels. Thus, automatic object segmentation is necessary since manual segmentation would be inefficient and biased. However, automatic segmentation is still a challenging problem as regions of interest may not have well defined boundaries as well as non-uniform pixel intensities. This paper describes a method for segmenting tubular structures in fluorescence microscopy images of rat kidney and liver samples using adaptive histogram equalization, foreground/background segmentation, steerable filters to capture directional tendencies, and connected-component analysis. The results from several data sets demonstrate that our method can segment tubular boundaries successfully. Moreover, our method has better performance when compared to other popular image segmentation methods when using ground truth data obtained via manual segmentation.

Modifications to the accuracy assessment analysis routine SPATL to produce an output file

NASA Technical Reports Server (NTRS)

Carnes, J. G.

1978-01-01

The SPATL is an analysis program in the Accuracy Assessment Software System which makes comparisons between ground truth information and dot labeling for an individual segment. In order to facilitate the aggregation cf this information, SPATL was modified to produce a disk output file containing the necessary information about each segment.

High Quality Facade Segmentation Based on Structured Random Forest, Region Proposal Network and Rectangular Fitting

NASA Astrophysics Data System (ADS)

Rahmani, K.; Mayer, H.

2018-05-01

In this paper we present a pipeline for high quality semantic segmentation of building facades using Structured Random Forest (SRF), Region Proposal Network (RPN) based on a Convolutional Neural Network (CNN) as well as rectangular fitting optimization. Our main contribution is that we employ features created by the RPN as channels in the SRF.We empirically show that this is very effective especially for doors and windows. Our pipeline is evaluated on two datasets where we outperform current state-of-the-art methods. Additionally, we quantify the contribution of the RPN and the rectangular fitting optimization on the accuracy of the result.

Practical Aspects of Access Network Indoor Extensions Using Multimode Glass and Plastic Optical Fibers

NASA Astrophysics Data System (ADS)

Keiser, Gerd; Liu, Hao-Yu; Lu, Shao-Hsi; Devi Pukhrambam, Puspa

2012-07-01

Low-cost multimode glass and plastic optical fibers are attractive for high-capacity indoor telecom networks. Many existing buildings already have glass multimode fibers installed for local area network applications. Future indoor applications will use combinations of glass multimode fibers with plastic optical fibers that have low losses in the 850-nm-1,310-nm range. This article examines real-world link losses when randomly interconnecting glass and plastic fiber segments having factory-installed connectors. Potential interconnection issues include large variations in connector losses among randomly selected fiber segments, asymmetric link losses in bidirectional links, and variations in bandwidths among different types of fibers.

Brain Tumor Segmentation Using Deep Belief Networks and Pathological Knowledge.

PubMed

Zhan, Tianming; Chen, Yi; Hong, Xunning; Lu, Zhenyu; Chen, Yunjie

2017-01-01

In this paper, we propose an automatic brain tumor segmentation method based on Deep Belief Networks (DBNs) and pathological knowledge. The proposed method is targeted against gliomas (both low and high grade) obtained in multi-sequence magnetic resonance images (MRIs). Firstly, a novel deep architecture is proposed to combine the multi-sequences intensities feature extraction with classification to get the classification probabilities of each voxel. Then, graph cut based optimization is executed on the classification probabilities to strengthen the spatial relationships of voxels. At last, pathological knowledge of gliomas is applied to remove some false positives. Our method was validated in the Brain Tumor Segmentation Challenge 2012 and 2013 databases (BRATS 2012, 2013). The performance of segmentation results demonstrates our proposal providing a competitive solution with stateof- the-art methods. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Linear-regression convolutional neural network for fully automated coronary lumen segmentation in intravascular optical coherence tomography

NASA Astrophysics Data System (ADS)

Yong, Yan Ling; Tan, Li Kuo; McLaughlin, Robert A.; Chee, Kok Han; Liew, Yih Miin

2017-12-01

Intravascular optical coherence tomography (OCT) is an optical imaging modality commonly used in the assessment of coronary artery diseases during percutaneous coronary intervention. Manual segmentation to assess luminal stenosis from OCT pullback scans is challenging and time consuming. We propose a linear-regression convolutional neural network to automatically perform vessel lumen segmentation, parameterized in terms of radial distances from the catheter centroid in polar space. Benchmarked against gold-standard manual segmentation, our proposed algorithm achieves average locational accuracy of the vessel wall of 22 microns, and 0.985 and 0.970 in Dice coefficient and Jaccard similarity index, respectively. The average absolute error of luminal area estimation is 1.38%. The processing rate is 40.6 ms per image, suggesting the potential to be incorporated into a clinical workflow and to provide quantitative assessment of vessel lumen in an intraoperative time frame.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments.

PubMed

Van Valen, David A; Kudo, Takamasa; Lane, Keara M; Macklin, Derek N; Quach, Nicolas T; DeFelice, Mialy M; Maayan, Inbal; Tanouchi, Yu; Ashley, Euan A; Covert, Markus W

2016-11-01

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

DOE PAGES

Van Valen, David A.; Kudo, Takamasa; Lane, Keara M.; ...

2016-11-04

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domainsmore » of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.« less

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

DOE Office of Scientific and Technical Information (OSTI.GOV)

Van Valen, David A.; Kudo, Takamasa; Lane, Keara M.

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domainsmore » of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems.« less

Deep Learning Automates the Quantitative Analysis of Individual Cells in Live-Cell Imaging Experiments

PubMed Central

Van Valen, David A.; Lane, Keara M.; Quach, Nicolas T.; Maayan, Inbal

2016-01-01

Live-cell imaging has opened an exciting window into the role cellular heterogeneity plays in dynamic, living systems. A major critical challenge for this class of experiments is the problem of image segmentation, or determining which parts of a microscope image correspond to which individual cells. Current approaches require many hours of manual curation and depend on approaches that are difficult to share between labs. They are also unable to robustly segment the cytoplasms of mammalian cells. Here, we show that deep convolutional neural networks, a supervised machine learning method, can solve this challenge for multiple cell types across the domains of life. We demonstrate that this approach can robustly segment fluorescent images of cell nuclei as well as phase images of the cytoplasms of individual bacterial and mammalian cells from phase contrast images without the need for a fluorescent cytoplasmic marker. These networks also enable the simultaneous segmentation and identification of different mammalian cell types grown in co-culture. A quantitative comparison with prior methods demonstrates that convolutional neural networks have improved accuracy and lead to a significant reduction in curation time. We relay our experience in designing and optimizing deep convolutional neural networks for this task and outline several design rules that we found led to robust performance. We conclude that deep convolutional neural networks are an accurate method that require less curation time, are generalizable to a multiplicity of cell types, from bacteria to mammalian cells, and expand live-cell imaging capabilities to include multi-cell type systems. PMID:27814364

Effects of Nerve Injury and Segmental Regeneration on the Cellular Correlates of Neural Morphallaxis

PubMed Central

Martinez, Veronica G.; Manson, Josiah M.B.; Zoran, Mark J.

2009-01-01

Functional recovery of neural networks after injury requires a series of signaling events similar to the embryonic processes that governed initial network construction. Neural morphallaxis, a form of nervous system regeneration, involves reorganization of adult neural connectivity patterns. Neural morphallaxis in the worm, Lumbriculus variegatus, occurs during asexual reproduction and segmental regeneration, as body fragments acquire new positional identities along the anterior–posterior axis. Ectopic head (EH) formation, induced by ventral nerve cord lesion, generated morphallactic plasticity including the reorganization of interneuronal sensory fields and the induction of a molecular marker of neural morphallaxis. Morphallactic changes occurred only in segments posterior to an EH. Neither EH formation, nor neural morphallaxis was observed after dorsal body lesions, indicating a role for nerve cord injury in morphallaxis induction. Furthermore, a hierarchical system of neurobehavioral control was observed, where anterior heads were dominant and an EH controlled body movements only in the absence of the anterior head. Both suppression of segmental regeneration and blockade of asexual fission, after treatment with boric acid, disrupted the maintenance of neural morphallaxis, but did not block its induction. Therefore, segmental regeneration (i.e., epimorphosis) may not be required for the induction of morphallactic remodeling of neural networks. However, on-going epimorphosis appears necessary for the long-term consolidation of cellular and molecular mechanisms underlying the morphallaxis of neural circuitry. PMID:18561185

Segmentation of histological images and fibrosis identification with a convolutional neural network.

PubMed

Fu, Xiaohang; Liu, Tong; Xiong, Zhaohan; Smaill, Bruce H; Stiles, Martin K; Zhao, Jichao

2018-07-01

Segmentation of histological images is one of the most crucial tasks for many biomedical analyses involving quantification of certain tissue types, such as fibrosis via Masson's trichrome staining. However, challenges are posed by the high variability and complexity of structural features in such images, in addition to imaging artifacts. Further, the conventional approach of manual thresholding is labor-intensive, and highly sensitive to inter- and intra-image intensity variations. An accurate and robust automated segmentation method is of high interest. We propose and evaluate an elegant convolutional neural network (CNN) designed for segmentation of histological images, particularly those with Masson's trichrome stain. The network comprises 11 successive convolutional - rectified linear unit - batch normalization layers. It outperformed state-of-the-art CNNs on a dataset of cardiac histological images (labeling fibrosis, myocytes, and background) with a Dice similarity coefficient of 0.947. With 100 times fewer (only 300,000) trainable parameters than the state-of-the-art, our CNN is less susceptible to overfitting, and is efficient. Additionally, it retains image resolution from input to output, captures fine-grained details, and can be trained end-to-end smoothly. To the best of our knowledge, this is the first deep CNN tailored to the problem of concern, and may potentially be extended to solve similar segmentation tasks to facilitate investigations into pathology and clinical treatment. Copyright © 2018 Elsevier Ltd. All rights reserved.

Foldable Instrumented Bits for Ultrasonic/Sonic Penetrators

NASA Technical Reports Server (NTRS)

Bar-Cohen, Yoseph; Badescu, Mircea; Iskenderian, Theodore; Sherrit, Stewart; Bao, Xiaoqi; Linderman, Randel

2010-01-01

Long tool bits are undergoing development that can be stowed compactly until used as rock- or ground-penetrating probes actuated by ultrasonic/sonic mechanisms. These bits are designed to be folded or rolled into compact form for transport to exploration sites, where they are to be connected to their ultrasonic/ sonic actuation mechanisms and unfolded or unrolled to their full lengths for penetrating ground or rock to relatively large depths. These bits can be designed to acquire rock or soil samples and/or to be equipped with sensors for measuring properties of rock or soil in situ. These bits can also be designed to be withdrawn from the ground, restowed, and transported for reuse at different exploration sites. Apparatuses based on the concept of a probe actuated by an ultrasonic/sonic mechanism have been described in numerous prior NASA Tech Briefs articles, the most recent and relevant being "Ultrasonic/ Sonic Impacting Penetrators" (NPO-41666) NASA Tech Briefs, Vol. 32, No. 4 (April 2008), page 58. All of those apparatuses are variations on the basic theme of the earliest ones, denoted ultrasonic/sonic drill corers (USDCs). To recapitulate: An apparatus of this type includes a lightweight, low-power, piezoelectrically driven actuator in which ultrasonic and sonic vibrations are generated and coupled to a tool bit. The combination of ultrasonic and sonic vibrations gives rise to a hammering action (and a resulting chiseling action at the tip of the tool bit) that is more effective for drilling than is the microhammering action of ultrasonic vibrations alone. The hammering and chiseling actions are so effective that the size of the axial force needed to make the tool bit advance into soil, rock, or another material of interest is much smaller than in ordinary twist drilling, ordinary hammering, or ordinary steady pushing. Examples of properties that could be measured by use of an instrumented tool bit include electrical conductivity, permittivity, magnetic field, magnetic permeability, temperature, and any other properties that can be measured by fiber-optic sensors. The problem of instrumenting a probe of this type is simplified, relative to the problem of attaching electrodes in a rotating drill bit, in two ways: (1) Unlike a rotating drill bit, a bit of this type does not have flutes, which would compound the problem of ensuring contact between sensors and the side wall of a hole; and (2) there is no need for slip rings for electrical contact between sensor electronic circuitry and external circuitry because, unlike a rotating drill, a tool bit of this type is not rotated continuously during operation. One design for a tool bit of the present type is a segmented bit with a segmented, hinged support structure (see figure). The bit and its ultrasonic/sonic actuator are supported by a slider/guiding fixture, and its displacement and preload are controlled by a motor. For deployment from the folded configuration, a spring-loaded mechanism rotates the lower segment about the hinges, causing the lower segment to become axially aligned with the upper segment. A latching mechanism then locks the segments of the bit and the corresponding segments of the slider/guiding fixture. Then the entire resulting assembly is maneuvered into position for drilling into the ground. Another design provides for a bit comprising multiple tubular segments with an inner alignment string, similar to a foldable tent pole comprising multiple tubular segments with an inner elastic cable connecting the two ends. At the beginning of deployment, all segments except the first (lowermost) one remain folded, and the ultrasonic/sonic actuator is clamped to the top of the lowermost segment and used to drive this segment into the ground. When the first segment has penetrated to a specified depth, the second segment is connected to the upper end of the first segment to form a longer rigid tubular bit and the actuator is moved to the upper end of the second segnt. The process as described thus far is repeated, adding segments until the desired depth of penetration has been attained. Yet other designs provide for bits in the form of bistable circular- or rectangular- cross-section tubes that can be stowed compactly like rolls of flat tape and become rigidified upon extension to full length, in a manner partly similar to that of a common steel tape measure. Albeit not marketed for use in tool bits, a bistable reeled composite product that transforms itself from a flat coil to a rigid tube of circular cross section when unrolled, is commercially available under the trade name RolaTube(TradeMark) and serves as a model for the further development of tool bits of this subtype.

Swallow segmentation with artificial neural networks and multi-sensor fusion.

PubMed

Lee, Joon; Steele, Catriona M; Chau, Tom

2009-11-01

Swallow segmentation is a critical precursory step to the analysis of swallowing signal characteristics. In an effort to automatically segment swallows, we investigated artificial neural networks (ANN) with information from cervical dual-axis accelerometry, submental MMG, and nasal airflow. Our objectives were (1) to investigate the relationship between segmentation performance and the number of signal sources and (2) to identify the signals or signal combinations most useful for swallow segmentation. Signals were acquired from 17 healthy adults in both discrete and continuous swallowing tasks using five stimuli. Training and test feature vectors were constructed with variances from single or multiple signals, estimated within 200 ms moving windows with 50% overlap. Corresponding binary target labels (swallow or non-swallow) were derived by manual segmentation. A separate 3-layer ANN was trained for each participant-signal combination, and all possible signal combinations were investigated. As more signal sources were included, segmentation performance improved in terms of sensitivity, specificity, accuracy, and adjusted accuracy. The combination of all four signal sources achieved the highest mean accuracy and adjusted accuracy of 88.5% and 89.6%, respectively. A-P accelerometry proved to be the most discriminatory source, while the inclusion of MMG or nasal airflow resulted in the least performance improvement. These findings suggest that an ANN, multi-sensor fusion approach to segmentation is worthy of further investigation in swallowing studies.

An automatic segmentation method of a parameter-adaptive PCNN for medical images.

PubMed

Lian, Jing; Shi, Bin; Li, Mingcong; Nan, Ziwei; Ma, Yide

2017-09-01

Since pre-processing and initial segmentation steps in medical images directly affect the final segmentation results of the regions of interesting, an automatic segmentation method of a parameter-adaptive pulse-coupled neural network is proposed to integrate the above-mentioned two segmentation steps into one. This method has a low computational complexity for different kinds of medical images and has a high segmentation precision. The method comprises four steps. Firstly, an optimal histogram threshold is used to determine the parameter [Formula: see text] for different kinds of images. Secondly, we acquire the parameter [Formula: see text] according to a simplified pulse-coupled neural network (SPCNN). Thirdly, we redefine the parameter V of the SPCNN model by sub-intensity distribution range of firing pixels. Fourthly, we add an offset [Formula: see text] to improve initial segmentation precision. Compared with the state-of-the-art algorithms, the new method achieves a comparable performance by the experimental results from ultrasound images of the gallbladder and gallstones, magnetic resonance images of the left ventricle, and mammogram images of the left and the right breast, presenting the overall metric UM of 0.9845, CM of 0.8142, TM of 0.0726. The algorithm has a great potential to achieve the pre-processing and initial segmentation steps in various medical images. This is a premise for assisting physicians to detect and diagnose clinical cases.

Flexible methods for segmentation evaluation: results from CT-based luggage screening.

PubMed

Karimi, Seemeen; Jiang, Xiaoqian; Cosman, Pamela; Martz, Harry

2014-01-01

Imaging systems used in aviation security include segmentation algorithms in an automatic threat recognition pipeline. The segmentation algorithms evolve in response to emerging threats and changing performance requirements. Analysis of segmentation algorithms' behavior, including the nature of errors and feature recovery, facilitates their development. However, evaluation methods from the literature provide limited characterization of the segmentation algorithms. To develop segmentation evaluation methods that measure systematic errors such as oversegmentation and undersegmentation, outliers, and overall errors. The methods must measure feature recovery and allow us to prioritize segments. We developed two complementary evaluation methods using statistical techniques and information theory. We also created a semi-automatic method to define ground truth from 3D images. We applied our methods to evaluate five segmentation algorithms developed for CT luggage screening. We validated our methods with synthetic problems and an observer evaluation. Both methods selected the same best segmentation algorithm. Human evaluation confirmed the findings. The measurement of systematic errors and prioritization helped in understanding the behavior of each segmentation algorithm. Our evaluation methods allow us to measure and explain the accuracy of segmentation algorithms.

Residual Shuffling Convolutional Neural Networks for Deep Semantic Image Segmentation Using Multi-Modal Data

NASA Astrophysics Data System (ADS)

Chen, K.; Weinmann, M.; Gao, X.; Yan, M.; Hinz, S.; Jutzi, B.; Weinmann, M.

2018-05-01

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation.

Squeeze-SegNet: a new fast deep convolutional neural network for semantic segmentation

NASA Astrophysics Data System (ADS)

Nanfack, Geraldin; Elhassouny, Azeddine; Oulad Haj Thami, Rachid

2018-04-01

The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmentation. Thus, brilliant ideas in the field of semantic segmentation with deep learning have completed the state of the art of accuracy, however this architectures become very difficult to apply in embedded systems as is the case for autonomous driving. We present a new Deep fully Convolutional Neural Network for pixel-wise semantic segmentation which we call Squeeze-SegNet. The architecture is based on Encoder-Decoder style. We use a SqueezeNet-like encoder and a decoder formed by our proposed squeeze-decoder module and upsample layer using downsample indices like in SegNet and we add a deconvolution layer to provide final multi-channel feature map. On datasets like Camvid or City-states, our net gets SegNet-level accuracy with less than 10 times fewer parameters than SegNet.

An approach to analyze the breast tissues in infrared images using nonlinear adaptive level sets and Riesz transform features.

PubMed

Prabha, S; Suganthi, S S; Sujatha, C M

2015-01-01

Breast thermography is a potential imaging method for the early detection of breast cancer. The pathological conditions can be determined by measuring temperature variations in the abnormal breast regions. Accurate delineation of breast tissues is reported as a challenging task due to inherent limitations of infrared images such as low contrast, low signal to noise ratio and absence of clear edges. Segmentation technique is attempted to delineate the breast tissues by detecting proper lower breast boundaries and inframammary folds. Characteristic features are extracted to analyze the asymmetrical thermal variations in normal and abnormal breast tissues. An automated analysis of thermal variations of breast tissues is attempted using nonlinear adaptive level sets and Riesz transform. Breast thermal images are initially subjected to Stein's unbiased risk estimate based orthonormal wavelet denoising. These denoised images are enhanced using contrast-limited adaptive histogram equalization method. The breast tissues are then segmented using non-linear adaptive level set method. The phase map of enhanced image is integrated into the level set framework for final boundary estimation. The segmented results are validated against the corresponding ground truth images using overlap and regional similarity metrics. The segmented images are further processed with Riesz transform and structural texture features are derived from the transformed coefficients to analyze pathological conditions of breast tissues. Results show that the estimated average signal to noise ratio of denoised images and average sharpness of enhanced images are improved by 38% and 6% respectively. The interscale consideration adopted in the denoising algorithm is able to improve signal to noise ratio by preserving edges. The proposed segmentation framework could delineate the breast tissues with high degree of correlation (97%) between the segmented and ground truth areas. Also, the average segmentation accuracy and sensitivity are found to be 98%. Similarly, the maximum regional overlap between segmented and ground truth images obtained using volume similarity measure is observed to be 99%. Directionality as a feature, showed a considerable difference between normal and abnormal tissues which is found to be 11%. The proposed framework for breast thermal image analysis that is aided with necessary preprocessing is found to be useful in assisting the early diagnosis of breast abnormalities.

ExoMars Trace Gas Orbiter (TGO) Science Ground Segment (SGS)

NASA Astrophysics Data System (ADS)

Metcalfe, L.; Aberasturi, M.; Alonso, E.; Álvarez, R.; Ashman, M.; Barbarisi, I.; Brumfitt, J.; Cardesín, A.; Coia, D.; Costa, M.; Fernández, R.; Frew, D.; Gallegos, J.; García Beteta, J. J.; Geiger, B.; Heather, D.; Lim, T.; Martin, P.; Muñoz Crego, C.; Muñoz Fernandez, M.; Villacorta, A.; Svedhem, H.

2018-06-01

The ExoMars Trace Gas Orbiter (TGO) Science Ground Segment (SGS), comprised of payload Instrument Team, ESA and Russian operational centres, is responsible for planning the science operations of the TGO mission and for the generation and archiving of the scientific data products to levels meeting the scientific aims and criteria specified by the ESA Project Scientist as advised by the Science Working Team (SWT). The ExoMars SGS builds extensively upon tools and experience acquired through earlier ESA planetary missions like Mars and Venus Express, and Rosetta, but also is breaking ground in various respects toward the science operations of future missions like BepiColombo or JUICE. A productive interaction with the Russian partners in the mission facilitates broad and effective collaboration. This paper describes the global organisation and operation of the SGS, with reference to its principal systems, interfaces and operational processes.

A proposal of optimal sampling design using a modularity strategy

NASA Astrophysics Data System (ADS)

Simone, A.; Giustolisi, O.; Laucelli, D. B.

2016-08-01

In real water distribution networks (WDNs) are present thousands nodes and optimal placement of pressure and flow observations is a relevant issue for different management tasks. The planning of pressure observations in terms of spatial distribution and number is named sampling design and it was faced considering model calibration. Nowadays, the design of system monitoring is a relevant issue for water utilities e.g., in order to manage background leakages, to detect anomalies and bursts, to guarantee service quality, etc. In recent years, the optimal location of flow observations related to design of optimal district metering areas (DMAs) and leakage management purposes has been faced considering optimal network segmentation and the modularity index using a multiobjective strategy. Optimal network segmentation is the basis to identify network modules by means of optimal conceptual cuts, which are the candidate locations of closed gates or flow meters creating the DMAs. Starting from the WDN-oriented modularity index, as a metric for WDN segmentation, this paper proposes a new way to perform the sampling design, i.e., the optimal location of pressure meters, using newly developed sampling-oriented modularity index. The strategy optimizes the pressure monitoring system mainly based on network topology and weights assigned to pipes according to the specific technical tasks. A multiobjective optimization minimizes the cost of pressure meters while maximizing the sampling-oriented modularity index. The methodology is presented and discussed using the Apulian and Exnet networks.

Dynamic patterning by the Drosophila pair-rule network reconciles long-germ and short-germ segmentation

PubMed Central

2017-01-01

Drosophila segmentation is a well-established paradigm for developmental pattern formation. However, the later stages of segment patterning, regulated by the “pair-rule” genes, are still not well understood at the system level. Building on established genetic interactions, I construct a logical model of the Drosophila pair-rule system that takes into account the demonstrated stage-specific architecture of the pair-rule gene network. Simulation of this model can accurately recapitulate the observed spatiotemporal expression of the pair-rule genes, but only when the system is provided with dynamic “gap” inputs. This result suggests that dynamic shifts of pair-rule stripes are essential for segment patterning in the trunk and provides a functional role for observed posterior-to-anterior gap domain shifts that occur during cellularisation. The model also suggests revised patterning mechanisms for the parasegment boundaries and explains the aetiology of the even-skipped null mutant phenotype. Strikingly, a slightly modified version of the model is able to pattern segments in either simultaneous or sequential modes, depending only on initial conditions. This suggests that fundamentally similar mechanisms may underlie segmentation in short-germ and long-germ arthropods. PMID:28953896

Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks.

PubMed

Demirhan, Ayşe; Toru, Mustafa; Guler, Inan

2015-07-01

Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2, and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.

Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images

NASA Astrophysics Data System (ADS)

Alshehhi, Rasha; Marpu, Prashanth Reddy

2017-04-01

Extraction of road networks in urban areas from remotely sensed imagery plays an important role in many urban applications (e.g. road navigation, geometric correction of urban remote sensing images, updating geographic information systems, etc.). It is normally difficult to accurately differentiate road from its background due to the complex geometry of the buildings and the acquisition geometry of the sensor. In this paper, we present a new method for extracting roads from high-resolution imagery based on hierarchical graph-based image segmentation. The proposed method consists of: 1. Extracting features (e.g., using Gabor and morphological filtering) to enhance the contrast between road and non-road pixels, 2. Graph-based segmentation consisting of (i) Constructing a graph representation of the image based on initial segmentation and (ii) Hierarchical merging and splitting of image segments based on color and shape features, and 3. Post-processing to remove irregularities in the extracted road segments. Experiments are conducted on three challenging datasets of high-resolution images to demonstrate the proposed method and compare with other similar approaches. The results demonstrate the validity and superior performance of the proposed method for road extraction in urban areas.

Understanding the topological characteristics and flow complexity of urban traffic congestion

NASA Astrophysics Data System (ADS)

Wen, Tzai-Hung; Chin, Wei-Chien-Benny; Lai, Pei-Chun

2017-05-01

For a growing number of developing cities, the capacities of streets cannot meet the rapidly growing demand of cars, causing traffic congestion. Understanding the spatial-temporal process of traffic flow and detecting traffic congestion are important issues associated with developing sustainable urban policies to resolve congestion. Therefore, the objective of this study is to propose a flow-based ranking algorithm for investigating traffic demands in terms of the attractiveness of street segments and flow complexity of the street network based on turning probability. Our results show that, by analyzing the topological characteristics of streets and volume data for a small fraction of street segments in Taipei City, the most congested segments of the city were identified successfully. The identified congested segments are significantly close to the potential congestion zones, including the officially announced most congested streets, the segments with slow moving speeds at rush hours, and the areas near significant landmarks. The identified congested segments also captured congestion-prone areas concentrated in the business districts and industrial areas of the city. Identifying the topological characteristics and flow complexity of traffic congestion provides network topological insights for sustainable urban planning, and these characteristics can be used to further understand congestion propagation.

Evaluating the role of river-floodplain connectivity in providing beneficial hydrologic services in mountain landscapes

NASA Astrophysics Data System (ADS)

Covino, T. P.; Wegener, P.; Weiss, T.; Wohl, E.; Rhoades, C.

2017-12-01

River networks of mountain landscapes tend to be dominated by steep, valley-confined channels that have limited floodplain area and low hydrologic buffering capacity. Interspersed between the narrow segments are wide, low-gradient segments where extensive floodplains, wetlands, and riparian areas can develop. Although they tend to be limited in their frequency relative to the narrow valley segments, the low-gradient, wide portions of mountain channel networks can be particularly important to hydrologic buffering and can be sites of high nutrient retention and ecosystem productivity. Hydrologic buffering along the wide valley segments is dependent on lateral hydrologic connectivity between the river and floodplain, however these connections have been increasingly severed as a result of various land and water management practices. We evaluated the role of river-floodplain connectivity in influencing water, dissolved organic carbon (DOC), and nutrient flux in river networks of the Colorado Rockies. We found that disconnected segments with limited floodplain/riparian area had limited buffering capacity, while connected segments exhibited variable source-sink dynamics as a function of flow. Specifically, connected segments were typically a sink for water, DOC, and nutrients during high flows, and subsequently became a source as flows decreased. Shifts in river-floodplain hydrologic connectivity across flows related to higher and more variable aquatic ecosystem metabolism rates along connected relative to disconnected segments. Our data suggest that lateral hydrologic connectivity in wide valleys can enhance hydrologic and biogeochemical buffering, and promote high rates of aquatic ecosystem metabolism. While hydrologic disconnection in one river-floodplain system is unlikely to influence water resources at larger scales, the cumulative effects of widespread disconnection may be substantial. Because intact river-floodplain (i.e., connected) systems provide numerous hydrologic and ecologic benefits, understanding the dynamics and cumulative effects of disconnection is an important step toward improved water resource and ecosystem management.

Segmentation of skin lesions in chronic graft versus host disease photographs with fully convolutional networks

NASA Astrophysics Data System (ADS)

Wang, Jianing; Chen, Fuyao; Dellalana, Laura E.; Jagasia, Madan H.; Tkaczyk, Eric R.; Dawant, Benoit M.

2018-02-01

Chronic graft-versus-host disease (cGVHD) is a frequent and potentially life-threatening complication of allogeneic hematopoietic stem cell transplantation (HCT) and commonly affects the skin, resulting in distressing patient morbidity. The percentage of involved body surface area (BSA) is commonly used for diagnosing and scoring the severity of cGVHD. However, the segmentation of the involved BSA from patient whole body serial photography is challenging because (1) it is difficult to design traditional segmentation method that rely on hand crafted features as the appearance of cGVHD lesions can be drastically different from patient to patient; (2) to the best of our knowledge, currently there is no publicavailable labelled image set of cGVHD skin for training deep networks to segment the involved BSA. In this preliminary study we create a small labelled image set of skin cGVHD, and we explore the possibility to use a fully convolutional neural network (FCN) to segment the skin lesion in the images. We use a commercial stereoscopic Vectra H1 camera (Canfield Scientific) to acquire 400 3D photographs of 17 cGVHD patients aged between 22 and 72. A rotational data augmentation process is then applied, which rotates the 3D photos through 10 predefined angles, producing one 2D projection image at each position. This results in 4000 2D images that constitute our cGVHD image set. A FCN model is trained and tested using our images. We show that our method achieves encouraging results for segmenting cGVHD skin lesion in photographic images.

Deep residual networks for automatic segmentation of laparoscopic videos of the liver

NASA Astrophysics Data System (ADS)

Gibson, Eli; Robu, Maria R.; Thompson, Stephen; Edwards, P. Eddie; Schneider, Crispin; Gurusamy, Kurinchi; Davidson, Brian; Hawkes, David J.; Barratt, Dean C.; Clarkson, Matthew J.

2017-03-01

Motivation: For primary and metastatic liver cancer patients undergoing liver resection, a laparoscopic approach can reduce recovery times and morbidity while offering equivalent curative results; however, only about 10% of tumours reside in anatomical locations that are currently accessible for laparoscopic resection. Augmenting laparoscopic video with registered vascular anatomical models from pre-procedure imaging could support using laparoscopy in a wider population. Segmentation of liver tissue on laparoscopic video supports the robust registration of anatomical liver models by filtering out false anatomical correspondences between pre-procedure and intra-procedure images. In this paper, we present a convolutional neural network (CNN) approach to liver segmentation in laparoscopic liver procedure videos. Method: We defined a CNN architecture comprising fully-convolutional deep residual networks with multi-resolution loss functions. The CNN was trained in a leave-one-patient-out cross-validation on 2050 video frames from 6 liver resections and 7 laparoscopic staging procedures, and evaluated using the Dice score. Results: The CNN yielded segmentations with Dice scores >=0.95 for the majority of images; however, the inter-patient variability in median Dice score was substantial. Four failure modes were identified from low scoring segmentations: minimal visible liver tissue, inter-patient variability in liver appearance, automatic exposure correction, and pathological liver tissue that mimics non-liver tissue appearance. Conclusion: CNNs offer a feasible approach for accurately segmenting liver from other anatomy on laparoscopic video, but additional data or computational advances are necessary to address challenges due to the high inter-patient variability in liver appearance.

Cognitive and Social Structure of the Elite Collaboration Network of Astrophysics: A Case Study on Shifting Network Structures

ERIC Educational Resources Information Center

Heidler, Richard

2011-01-01

Scientific collaboration can only be understood along the epistemic and cognitive grounding of scientific disciplines. New scientific discoveries in astrophysics led to a major restructuring of the elite network of astrophysics. To study the interplay of the epistemic grounding and the social network structure of a discipline, a mixed-methods…

Fully convolutional networks (FCNs)-based segmentation method for colorectal tumors on T2-weighted magnetic resonance images.

PubMed

Jian, Junming; Xiong, Fei; Xia, Wei; Zhang, Rui; Gu, Jinhui; Wu, Xiaodong; Meng, Xiaochun; Gao, Xin

2018-06-01

Segmentation of colorectal tumors is the basis of preoperative prediction, staging, and therapeutic response evaluation. Due to the blurred boundary between lesions and normal colorectal tissue, it is hard to realize accurate segmentation. Routinely manual or semi-manual segmentation methods are extremely tedious, time-consuming, and highly operator-dependent. In the framework of FCNs, a segmentation method for colorectal tumor was presented. Normalization was applied to reduce the differences among images. Borrowing from transfer learning, VGG-16 was employed to extract features from normalized images. We conducted five side-output blocks from the last convolutional layer of each block of VGG-16 along the network, these side-output blocks can deep dive multiscale features, and produced corresponding predictions. Finally, all of the predictions from side-output blocks were fused to determine the final boundaries of the tumors. A quantitative comparison of 2772 colorectal tumor manual segmentation results from T2-weighted magnetic resonance images shows that the average Dice similarity coefficient, positive predictive value, specificity, sensitivity, Hammoude distance, and Hausdorff distance were 83.56, 82.67, 96.75, 87.85%, 0.2694, and 8.20, respectively. The proposed method is superior to U-net in colorectal tumor segmentation (P < 0.05). There is no difference between cross-entropy loss and Dice-based loss in colorectal tumor segmentation (P > 0.05). The results indicate that the introduction of FCNs contributed to accurate segmentation of colorectal tumors. This method has the potential to replace the present time-consuming and nonreproducible manual segmentation method.

Automatic aortic root segmentation in CTA whole-body dataset

NASA Astrophysics Data System (ADS)

Gao, Xinpei; Kitslaar, Pieter H.; Scholte, Arthur J. H. A.; Lelieveldt, Boudewijn P. F.; Dijkstra, Jouke; Reiber, Johan H. C.

2016-03-01

Trans-catheter aortic valve replacement (TAVR) is an evolving technique for patients with serious aortic stenosis disease. Typically, in this application a CTA data set is obtained of the patient's arterial system from the subclavian artery to the femoral arteries, to evaluate the quality of the vascular access route and analyze the aortic root to determine if and which prosthesis should be used. In this paper, we concentrate on the automated segmentation of the aortic root. The purpose of this study was to automatically segment the aortic root in computed tomography angiography (CTA) datasets to support TAVR procedures. The method in this study includes 4 major steps. First, the patient's cardiac CTA image was resampled to reduce the computation time. Next, the cardiac CTA image was segmented using an atlas-based approach. The most similar atlas was selected from a total of 8 atlases based on its image similarity to the input CTA image. Third, the aortic root segmentation from the previous step was transferred to the patient's whole-body CTA image by affine registration and refined in the fourth step using a deformable subdivision surface model fitting procedure based on image intensity. The pipeline was applied to 20 patients. The ground truth was created by an analyst who semi-automatically corrected the contours of the automatic method, where necessary. The average Dice similarity index between the segmentations of the automatic method and the ground truth was found to be 0.965±0.024. In conclusion, the current results are very promising.

Application guide for AFINCH (Analysis of Flows in Networks of Channels) described by NHDPlus

USGS Publications Warehouse

Holtschlag, David J.

2009-01-01

AFINCH (Analysis of Flows in Networks of CHannels) is a computer application that can be used to generate a time series of monthly flows at stream segments (flowlines) and water yields for catchments defined in the National Hydrography Dataset Plus (NHDPlus) value-added attribute system. AFINCH provides a basis for integrating monthly flow data from streamgages, water-use data, monthly climatic data, and land-cover characteristics to estimate natural monthly water yields from catchments by user-defined regression equations. Images of monthly water yields for active streamgages are generated in AFINCH and provide a basis for detecting anomalies in water yields, which may be associated with undocumented flow diversions or augmentations. Water yields are multiplied by the drainage areas of the corresponding catchments to estimate monthly flows. Flows from catchments are accumulated downstream through the streamflow network described by the stream segments. For stream segments where streamgages are active, ratios of measured to accumulated flows are computed. These ratios are applied to upstream water yields to proportionally adjust estimated flows to match measured flows. Flow is conserved through the NHDPlus network. A time series of monthly flows can be generated for stream segments that average about 1-mile long, or monthly water yields from catchments that average about 1 square mile. Estimated monthly flows can be displayed within AFINCH, examined for nonstationarity, and tested for monotonic trends. Monthly flows also can be used to estimate flow-duration characteristics at stream segments. AFINCH generates output files of monthly flows and water yields that are compatible with ArcMap, a geographical information system analysis and display environment. Chloropleth maps of monthly water yield and flow can be generated and analyzed within ArcMap by joining NHDPlus data structures with AFINCH output. Matlab code for the AFINCH application is presented.

Need for denser geodetic network to get real constrain on the fault behavior along the Main Marmara Sea segments of the NAF, toward an optimized GPS network.

NASA Astrophysics Data System (ADS)

Klein, E.; Masson, F.; Duputel, Z.; Yavasoglu, H.; Agram, P. S.

2016-12-01

Over the last two decades, the densification of GPS networks and the development of new radar satellites offered an unprecedented opportunity to study crustal deformation due to faulting. Yet, submarine strike slip fault segments remain a major issue, especially when the landscape appears unfavorable to the use of SAR measurements. It is the case of the North Anatolian fault segments located in the Main Marmara Sea, that remain unbroken ever since the Mw7.4 earthquake of Izmit in 1999, which ended a eastward migrating seismic sequence of Mw > 7 earthquakes. Located directly offshore Istanbul, evaluation of seismic hazard appears capital. But a strong controversy remains over whether these segments are accumulating strain and are likely to experience a major earthquake, or are creeping, resulting both from the simplicity of current geodetic models and the scarcity of geodetic data. We indeed show that 2D infinite fault models cannot account for the complexity of the Marmara fault segments. But current geodetic data in the western region of Istanbul are also insufficient to invert for the coupling using a 3D geometry of the fault. Therefore, we implement a global optimization procedure aiming at identifying the most favorable distribution of GPS stations to explore the strain accumulation. We present here the results of this procedure that allows to determine both the optimal number and location of the new stations. We show that a denser terrestrial survey network can indeed locally improve the resolution on the shallower part of the fault, even more efficiently with permanent stations. But data closer from the fault, only possible by submarine measurements, remain necessary to properly constrain the fault behavior and its potential along strike coupling variations.

Signal processing for distributed sensor concept: DISCO

NASA Astrophysics Data System (ADS)

Rafailov, Michael K.

2007-04-01

Distributed Sensor concept - DISCO proposed for multiplication of individual sensor capabilities through cooperative target engagement. DISCO relies on ability of signal processing software to format, to process and to transmit and receive sensor data and to exploit those data in signal synthesis process. Each sensor data is synchronized formatted, Signal-to-Noise Ration (SNR) enhanced and distributed inside of the sensor network. Signal processing technique for DISCO is Recursive Adaptive Frame Integration of Limited data - RAFIL technique that was initially proposed [1] as a way to improve the SNR, reduce data rate and mitigate FPA correlated noise of an individual sensor digital video-signal processing. In Distributed Sensor Concept RAFIL technique is used in segmented way, when constituencies of the technique are spatially and/or temporally separated between transmitters and receivers. Those constituencies include though not limited to two thresholds - one is tuned for optimum probability of detection, the other - to manage required false alarm rate, and limited frame integration placed somewhere between the thresholds as well as formatters, conventional integrators and more. RAFIL allows a non-linear integration that, along with SNR gain, provides system designers more capability where cost, weight, or power considerations limit system data rate, processing, or memory capability [2]. DISCO architecture allows flexible optimization of SNR gain, data rates and noise suppression on sensor's side and limited integration, re-formatting and final threshold on node's side. DISCO with Recursive Adaptive Frame Integration of Limited data may have flexible architecture that allows segmenting the hardware and software to be best suitable for specific DISCO applications and sensing needs - whatever it is air-or-space platforms, ground terminals or integration of sensors network.

Automated assessment of breast tissue density in non-contrast 3D CT images without image segmentation based on a deep CNN

NASA Astrophysics Data System (ADS)

Zhou, Xiangrong; Kano, Takuya; Koyasu, Hiromi; Li, Shuo; Zhou, Xinxin; Hara, Takeshi; Matsuo, Masayuki; Fujita, Hiroshi

2017-03-01

This paper describes a novel approach for the automatic assessment of breast density in non-contrast three-dimensional computed tomography (3D CT) images. The proposed approach trains and uses a deep convolutional neural network (CNN) from scratch to classify breast tissue density directly from CT images without segmenting the anatomical structures, which creates a bottleneck in conventional approaches. Our scheme determines breast density in a 3D breast region by decomposing the 3D region into several radial 2D-sections from the nipple, and measuring the distribution of breast tissue densities on each 2D section from different orientations. The whole scheme is designed as a compact network without the need for post-processing and provides high robustness and computational efficiency in clinical settings. We applied this scheme to a dataset of 463 non-contrast CT scans obtained from 30- to 45-year-old-women in Japan. The density of breast tissue in each CT scan was assigned to one of four categories (glandular tissue within the breast <25%, 25%-50%, 50%-75%, and >75%) by a radiologist as ground truth. We used 405 CT scans for training a deep CNN and the remaining 58 CT scans for testing the performance. The experimental results demonstrated that the findings of the proposed approach and those of the radiologist were the same in 72% of the CT scans among the training samples and 76% among the testing samples. These results demonstrate the potential use of deep CNN for assessing breast tissue density in non-contrast 3D CT images.

Georgia's Ground-Water Resources and Monitoring Network, 2006

USGS Publications Warehouse

Nobles, Patricia L.

2006-01-01

The U.S. Geological Survey (USGS) ground-water network for Georgia currently consists of 170 wells in which ground-water levels are continuously monitored. Most of the wells are locatedin the Coastal Plain in the southern part of the State where ground-water pumping stress is high. In particular, there are large concentrations of wells in coastal and southwestern Georgia areas, where there are issues related to ground-water pumping, saltwater intrusion along the coast, and diminished streamflow in southwestern Georgia due to irrigation pumping. The map at right shows the USGS ground-water monitoring network for Georgia. Ground-water levels are monitored in 170 wells statewide, of which 19 transmit data in real time via satellite and posted on the World Wide Web at http://waterdata.usgs.gov/ga/nwis/current/?type=gw . A greater concentration of wells occurs in the Coastal Plain where there are several layers of aquifers and in coastal and southwestern Georgia areas, which are areas with specific ground-water issues.

An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture.

PubMed

Doulamis, A; Doulamis, N; Ntalianis, K; Kollias, S

2003-01-01

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

Regional co-location pattern scoping on a street network considering distance decay effects of spatial interaction

PubMed Central

Yu, Wenhao

2017-01-01

Regional co-location scoping intends to identify local regions where spatial features of interest are frequently located together. Most of the previous researches in this domain are conducted on a global scale and they assume that spatial objects are embedded in a 2-D space, but the movement in urban space is actually constrained by the street network. In this paper we refine the scope of co-location patterns to 1-D paths consisting of nodes and segments. Furthermore, since the relations between spatial events are usually inversely proportional to their separation distance, the proposed method introduces the “Distance Decay Effects” to improve the result. Specifically, our approach first subdivides the street edges into continuous small linear segments. Then a value representing the local distribution intensity of events is estimated for each linear segment using the distance-decay function. Each kind of geographic feature can lead to a tessellated network with density attribute, and the generated multiple networks for the pattern of interest will be finally combined into a composite network by calculating the co-location prevalence measure values, which are based on the density variation between different features. Our experiments verify that the proposed approach is effective in urban analysis. PMID:28763496

The Telecommunications and Data Acquisition Report

NASA Technical Reports Server (NTRS)

Posner, E. C. (Editor)

1988-01-01

Deep Space Network and Systems topics addressed include: tracking and ground-base navigation; communications, spacecraft-ground; station control and system technology; capabilities for existing projects; and network upgrading and sustaining.

A multi-layer steganographic method based on audio time domain segmented and network steganography

NASA Astrophysics Data System (ADS)

Xue, Pengfei; Liu, Hanlin; Hu, Jingsong; Hu, Ronggui

2018-05-01

Both audio steganography and network steganography are belong to modern steganography. Audio steganography has a large capacity. Network steganography is difficult to detect or track. In this paper, a multi-layer steganographic method based on the collaboration of them (MLS-ATDSS&NS) is proposed. MLS-ATDSS&NS is realized in two covert layers (audio steganography layer and network steganography layer) by two steps. A new audio time domain segmented steganography (ATDSS) method is proposed in step 1, and the collaboration method of ATDSS and NS is proposed in step 2. The experimental results showed that the advantage of MLS-ATDSS&NS over others is better trade-off between capacity, anti-detectability and robustness, that means higher steganographic capacity, better anti-detectability and stronger robustness.

Geological indications for active deformation along Fethiye and G

NASA Astrophysics Data System (ADS)

Pavlides, S.; Chatzipetros, Anastasia Michailidou (1), Alexandros; Yağmurlu, Nevzat Özgür, Züheyr Kamaci, Murat Şentürk, Fuzuli

2009-04-01

Geological indications for active deformation along Fethiye and Gökova faults, SW Turkey Alexandros Chatzipetros, Spyros Pavlides, Anastasia Michailidou (1) Fuzuli Yağmurlu, Nevzat Özgür, Züheyr Kamaci, Murat Şentürk (2) 1Department of Geology, Aristotle University, 54124, Thessaloniki, Greece 2Department of Geological Engineering, Süleyman Demirel University, Isparta, Turkey Fethiye and Gökova faults (FF and GF respectively) are two long fault zones in SW Turkey, associated with minor to moderate historical seismic activity; their geological and geomorphological characteristics however are indicative of active deformation. FF is part of the Fethiye - Burdur Fault Zone (FBFZ), the inferred mainland continuation of the eastern part of the Hellenic Arc. FF, as well as FBFZ, is an oblique-slip (normal with significant dextral component) fault of NE-SW strike, dipping to the NW, that forms the SE border of Fethiye basin and controls its extension to the NE, while it also controls the development of the drainage network. Its geomorphological signature is characterized by steep bedrock fault scarps that are accompanied by thick sequences of alluvial fans and colluviums. Although it does not appear to disrupt the most recent generation of alluvial fans, geophysical prospecting showed that the deformation reaches all the way up to almost the superficial layers. Palaeoseismological trenching in selected sites along the fault yielded indications of at least two large, ground rupturing, seismic events in Holocene, as indicated by the inferred age of the trenched material. Indications include surface ruptures, faulted colluvial wedges and palaeosoils and microstratigraphical correlations. GF forms is divided into two main segments, the partly submarine Gökova-Kos segment trending E-W to NE-SW and the mainland NE-SW trending main Gökova segment, both dipping to the SE to S. They are predominantly normal with dextral component. The first segment defines the northern shore of Gökova gulf, which is the longest fault-controlled shoreline in Turkey. Bathymetric data indicate that its continuation is submarine and continues up to the southern shores of Kos island (Greece), posing a relatively unknown up to now probable seismic source for this part of the Aegean Sea in the Greek territory. The second segment forms a very impressive and dominant scarp that almost totally controls the geomorphology (drainage, alluvial fans and colluviums). Although this fault is not associated with significant historical seismicity, there are some archaeological indications of recent activity. Microstratigraphical analysis of paleoseismological trenches showed that indeed there are no recent earthquakes in the area, at least not any that caused significant ground deformations. Quantitative results regarding the dating of specific seismic events will be extrapolated after the results of 14C dating of selected samples from palaeoseismological trenches,currently under way, become available.

Performance of an Artificial Multi-observer Deep Neural Network for Fully Automated Segmentation of Polycystic Kidneys.

PubMed

Kline, Timothy L; Korfiatis, Panagiotis; Edwards, Marie E; Blais, Jaime D; Czerwiec, Frank S; Harris, Peter C; King, Bernard F; Torres, Vicente E; Erickson, Bradley J

2017-08-01

Deep learning techniques are being rapidly applied to medical imaging tasks-from organ and lesion segmentation to tissue and tumor classification. These techniques are becoming the leading algorithmic approaches to solve inherently difficult image processing tasks. Currently, the most critical requirement for successful implementation lies in the need for relatively large datasets that can be used for training the deep learning networks. Based on our initial studies of MR imaging examinations of the kidneys of patients affected by polycystic kidney disease (PKD), we have generated a unique database of imaging data and corresponding reference standard segmentations of polycystic kidneys. In the study of PKD, segmentation of the kidneys is needed in order to measure total kidney volume (TKV). Automated methods to segment the kidneys and measure TKV are needed to increase measurement throughput and alleviate the inherent variability of human-derived measurements. We hypothesize that deep learning techniques can be leveraged to perform fast, accurate, reproducible, and fully automated segmentation of polycystic kidneys. Here, we describe a fully automated approach for segmenting PKD kidneys within MR images that simulates a multi-observer approach in order to create an accurate and robust method for the task of segmentation and computation of TKV for PKD patients. A total of 2000 cases were used for training and validation, and 400 cases were used for testing. The multi-observer ensemble method had mean ± SD percent volume difference of 0.68 ± 2.2% compared with the reference standard segmentations. The complete framework performs fully automated segmentation at a level comparable with interobserver variability and could be considered as a replacement for the task of segmentation of PKD kidneys by a human.

Reliability Block Diagram (RBD) Analysis of NASA Dryden Flight Research Center (DFRC) Flight Termination System and Power Supply

NASA Technical Reports Server (NTRS)

Morehouse, Dennis V.

2006-01-01

In order to perform public risk analyses for vehicles containing Flight Termination Systems (FTS), it is necessary for the analyst to know the reliability of each of the components of the FTS. These systems are typically divided into two segments; a transmitter system and associated equipment, typically in a ground station or on a support aircraft, and a receiver system and associated equipment on the target vehicle. This analysis attempts to analyze the reliability of the NASA DFRC flight termination system ground transmitter segment for use in the larger risk analysis and to compare the results against two established Department of Defense availability standards for such equipment.

Three-dimensional data-tracking dynamic optimization simulations of human locomotion generated by direct collocation.

PubMed

Lin, Yi-Chung; Pandy, Marcus G

2017-07-05

The aim of this study was to perform full-body three-dimensional (3D) dynamic optimization simulations of human locomotion by driving a neuromusculoskeletal model toward in vivo measurements of body-segmental kinematics and ground reaction forces. Gait data were recorded from 5 healthy participants who walked at their preferred speeds and ran at 2m/s. Participant-specific data-tracking dynamic optimization solutions were generated for one stride cycle using direct collocation in tandem with an OpenSim-MATLAB interface. The body was represented as a 12-segment, 21-degree-of-freedom skeleton actuated by 66 muscle-tendon units. Foot-ground interaction was simulated using six contact spheres under each foot. The dynamic optimization problem was to find the set of muscle excitations needed to reproduce 3D measurements of body-segmental motions and ground reaction forces while minimizing the time integral of muscle activations squared. Direct collocation took on average 2.7±1.0h and 2.2±1.6h of CPU time, respectively, to solve the optimization problems for walking and running. Model-computed kinematics and foot-ground forces were in good agreement with corresponding experimental data while the calculated muscle excitation patterns were consistent with measured EMG activity. The results demonstrate the feasibility of implementing direct collocation on a detailed neuromusculoskeletal model with foot-ground contact to accurately and efficiently generate 3D data-tracking dynamic optimization simulations of human locomotion. The proposed method offers a viable tool for creating feasible initial guesses needed to perform predictive simulations of movement using dynamic optimization theory. The source code for implementing the model and computational algorithm may be downloaded at http://simtk.org/home/datatracking. Copyright © 2017 Elsevier Ltd. All rights reserved.

Unmanned Ground Vehicle Navigation and Coverage Hole Patching in Wireless Sensor Networks

ERIC Educational Resources Information Center

Zhang, Guyu

2013-01-01

This dissertation presents a study of an Unmanned Ground Vehicle (UGV) navigation and coverage hole patching in coordinate-free and localization-free Wireless Sensor Networks (WSNs). Navigation and coverage maintenance are related problems since coverage hole patching requires effective navigation in the sensor network environment. A…

Validation of pore network simulations of ex-situ water distributions in a gas diffusion layer of proton exchange membrane fuel cells with X-ray tomographic images

NASA Astrophysics Data System (ADS)

Agaesse, Tristan; Lamibrac, Adrien; Büchi, Felix N.; Pauchet, Joel; Prat, Marc

2016-11-01

Understanding and modeling two-phase flows in the gas diffusion layer (GDL) of proton exchange membrane fuel cells are important in order to improve fuel cells performance. They are scientifically challenging because of the peculiarities of GDLs microstructures. In the present work, simulations on a pore network model are compared to X-ray tomographic images of water distributions during an ex-situ water invasion experiment. A method based on watershed segmentation was developed to extract a pore network from the 3D segmented image of the dry GDL. Pore network modeling and a full morphology model were then used to perform two-phase simulations and compared to the experimental data. The results show good agreement between experimental and simulated microscopic water distributions. Pore network extraction parameters were also benchmarked using the experimental data and results from full morphology simulations.

An experiment to enable commercial mobile satellite service

NASA Technical Reports Server (NTRS)

Lovell, R. R.; Knouse, G. H.; Weber, W. J.

1982-01-01

A Mobile Satellite Experiment (MSAT-X) is described, based on a planned cooperative U.S./Canadian program. The experiment would establish network architecture, develop system and ground-segment technology, and define the technical characteristics needed to help structure the regulatory/institutional framework needed to enable a first-generation commercial satellite service. A satellite of this type would augment terrestrial systems, both cellular and noncellular, in the thin-route/rural areas of the country where service is either unavailable or inadequate. Applications range from wide-area radio/dispatch (e.g., oil exploration and interstate trucking) to extension of the public mobile telephone service. Market estimates are provided and experiment objectives and requirements are delineated. The requirements are being developed in close coordination with the Department of Communications (DOC) of Canada and with industry and potential-user organizations. The paper closes with a development plan and milestone chart.

Experiments applications guide: Advanced Communications Technology Satellite (ACTS)

NASA Technical Reports Server (NTRS)

1988-01-01

This applications guide first surveys the capabilities of the Advanced Communication Technology Satellite (ACTS) system (both the flight and ground segments). This overview is followed by a description of the baseband processor (BBP) and microwave switch matrix (MSM) operating modes. Terminals operating with the baseband processor are referred to as low burst rate (LBR); and those operating with the microwave switch matrix, as high burst rate (HBR). Three very small-aperture terminals (VSATs), LBR-1, LBR-2, and HBR, are described for various ACTS operating modes. Also described is the NASA Lewis link evaluation terminal. A section on ACTS experiment opportunities introduces a wide spectrum of network control, telecommunications, system, and scientific experiments. The performance of the VSATs is discussed in detail. This guide is intended as a catalyst to encourage participation by the telecommunications, business, and science communities in a broad spectrum of experiments.

Dynamic detection of window starting positions and its implementation within an activity recognition framework.

PubMed

Ni, Qin; Patterson, Timothy; Cleland, Ian; Nugent, Chris

2016-08-01

Activity recognition is an intrinsic component of many pervasive computing and ambient intelligent solutions. This has been facilitated by an explosion of technological developments in the area of wireless sensor network, wearable and mobile computing. Yet, delivering robust activity recognition, which could be deployed at scale in a real world environment, still remains an active research challenge. Much of the existing literature to date has focused on applying machine learning techniques to pre-segmented data collected in controlled laboratory environments. Whilst this approach can provide valuable ground truth information from which to build recognition models, these techniques often do not function well when implemented in near real time applications. This paper presents the application of a multivariate online change detection algorithm to dynamically detect the starting position of windows for the purposes of activity recognition. Copyright © 2016 Elsevier Inc. All rights reserved.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery

PubMed Central

Stojadinovic, Strahinja; Hrycushko, Brian; Wardak, Zabi; Lau, Steven; Lu, Weiguo; Yan, Yulong; Jiang, Steve B.; Zhen, Xin; Timmerman, Robert; Nedzi, Lucien

2017-01-01

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases. PMID:28985229

Retinal blood vessel segmentation using fully convolutional network with transfer learning.

PubMed

Jiang, Zhexin; Zhang, Hao; Wang, Yi; Ko, Seok-Bum

2018-04-26

Since the retinal blood vessel has been acknowledged as an indispensable element in both ophthalmological and cardiovascular disease diagnosis, the accurate segmentation of the retinal vessel tree has become the prerequisite step for automated or computer-aided diagnosis systems. In this paper, a supervised method is presented based on a pre-trained fully convolutional network through transfer learning. This proposed method has simplified the typical retinal vessel segmentation problem from full-size image segmentation to regional vessel element recognition and result merging. Meanwhile, additional unsupervised image post-processing techniques are applied to this proposed method so as to refine the final result. Extensive experiments have been conducted on DRIVE, STARE, CHASE_DB1 and HRF databases, and the accuracy of the cross-database test on these four databases is state-of-the-art, which also presents the high robustness of the proposed approach. This successful result has not only contributed to the area of automated retinal blood vessel segmentation but also supports the effectiveness of transfer learning when applying deep learning technique to medical imaging. Copyright © 2018 Elsevier Ltd. All rights reserved.

Automated and real-time segmentation of suspicious breast masses using convolutional neural network

PubMed Central

Gregory, Adriana; Denis, Max; Meixner, Duane D.; Bayat, Mahdi; Whaley, Dana H.; Fatemi, Mostafa; Alizad, Azra

2018-01-01

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm. PMID:29768415

Automatic cerebrospinal fluid segmentation in non-contrast CT images using a 3D convolutional network

NASA Astrophysics Data System (ADS)

Patel, Ajay; van de Leemput, Sil C.; Prokop, Mathias; van Ginneken, Bram; Manniesing, Rashindra

2017-03-01

Segmentation of anatomical structures is fundamental in the development of computer aided diagnosis systems for cerebral pathologies. Manual annotations are laborious, time consuming and subject to human error and observer variability. Accurate quantification of cerebrospinal fluid (CSF) can be employed as a morphometric measure for diagnosis and patient outcome prediction. However, segmenting CSF in non-contrast CT images is complicated by low soft tissue contrast and image noise. In this paper we propose a state-of-the-art method using a multi-scale three-dimensional (3D) fully convolutional neural network (CNN) to automatically segment all CSF within the cranial cavity. The method is trained on a small dataset comprised of four manually annotated cerebral CT images. Quantitative evaluation of a separate test dataset of four images shows a mean Dice similarity coefficient of 0.87 +/- 0.01 and mean absolute volume difference of 4.77 +/- 2.70 %. The average prediction time was 68 seconds. Our method allows for fast and fully automated 3D segmentation of cerebral CSF in non-contrast CT, and shows promising results despite a limited amount of training data.

Delineation and geometric modeling of road networks

NASA Astrophysics Data System (ADS)

Poullis, Charalambos; You, Suya

In this work we present a novel vision-based system for automatic detection and extraction of complex road networks from various sensor resources such as aerial photographs, satellite images, and LiDAR. Uniquely, the proposed system is an integrated solution that merges the power of perceptual grouping theory (Gabor filtering, tensor voting) and optimized segmentation techniques (global optimization using graph-cuts) into a unified framework to address the challenging problems of geospatial feature detection and classification. Firstly, the local precision of the Gabor filters is combined with the global context of the tensor voting to produce accurate classification of the geospatial features. In addition, the tensorial representation used for the encoding of the data eliminates the need for any thresholds, therefore removing any data dependencies. Secondly, a novel orientation-based segmentation is presented which incorporates the classification of the perceptual grouping, and results in segmentations with better defined boundaries and continuous linear segments. Finally, a set of gaussian-based filters are applied to automatically extract centerline information (magnitude, width and orientation). This information is then used for creating road segments and transforming them to their polygonal representations.

Classification with an edge: Improving semantic image segmentation with boundary detection

NASA Astrophysics Data System (ADS)

Marmanis, D.; Schindler, K.; Wegner, J. D.; Galliani, S.; Datcu, M.; Stilla, U.

2018-01-01

We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large receptive fields. However, this success comes at a cost, since the associated loss of effective spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class boundaries explicit in the model. First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the SEGNET encoder-decoder architecture. Second, we also include boundary detection in FCN-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs in an end-to-end training scheme. Our best model achieves >90% overall accuracy on the ISPRS Vaihingen benchmark.

Hydrogeology of the northern segment of the Edwards aquifer, Austin region, Texas

DOE Office of Scientific and Technical Information (OSTI.GOV)

Senger, R.K.; Collins, E.W.; Kreitler, C.W.

1990-01-01

This book reports on geologic mapping and fracture analysis of Lower Cretaceous Edwards aquifer strata conducted to provide a better understanding of the geology of the Balcones Fault Zone as it relates to the hydrogeology of the aquifer's northern segment. Hydrochemical, water-level, and precipitation data were studied to evaluate ground-water flow characteristics, recharge and discharge mechanisms, and the hydrochemical evolution of ground water in the Edwards aquifer. The authors found that ground water generally flows eastward, and main discharge of the unconfined, fast-flowing system occurs along fractures through springs and seeps at the major creeks and rivers in the Georgetownmore » area. Some recharge water moves downdip past these springs into a confined section farther east, along a much reduced hydraulic gradient, and discharges by leaking through the confining units. Hydrochemistry of Edwards ground water indicates an evolution from a Ca-HCO{sub 3} and Ca-Mg-HCO{sub 3} to a mixed-cation-HCO{sub 3} farther downdip to a Na-HCO{sub 3}, and finally to a Na-mixed-anion-type water.« less

Segmental and Kinetic Contributions in Vertical Jumps Performed with and without an Arm Swing

ERIC Educational Resources Information Center

Feltner, Michael E.; Bishop, Elijah J.; Perez, Cassandra M.

2004-01-01

To determine the contributions of the motions of the body segments to the vertical ground reaction force ([F.sub.z]), the joint torques produced by the leg muscles, and the time course of vertical velocity generation during a vertical jump, 15 men were videotaped performing countermovement vertical jumps from a force plate with and without an arm…

Using multimodal information for the segmentation of fluorescent micrographs with application to virology and microbiology.

PubMed

Held, Christian; Wenzel, Jens; Webel, Rike; Marschall, Manfred; Lang, Roland; Palmisano, Ralf; Wittenberg, Thomas

2011-01-01

In order to improve reproducibility and objectivity of fluorescence microscopy based experiments and to enable the evaluation of large datasets, flexible segmentation methods are required which are able to adapt to different stainings and cell types. This adaption is usually achieved by the manual adjustment of the segmentation methods parameters, which is time consuming and challenging for biologists with no knowledge on image processing. To avoid this, parameters of the presented methods automatically adapt to user generated ground truth to determine the best method and the optimal parameter setup. These settings can then be used for segmentation of the remaining images. As robust segmentation methods form the core of such a system, the currently used watershed transform based segmentation routine is replaced by a fast marching level set based segmentation routine which incorporates knowledge on the cell nuclei. Our evaluations reveal that incorporation of multimodal information improves segmentation quality for the presented fluorescent datasets.

Spatial data for Eurycea salamander habitats associated With three aquifers in south-central Texas

USGS Publications Warehouse

Heitmuller, Franklin T.; Reece, Brian D.

2006-01-01

Eurycea salamander taxa comprise 12 known species that inhabit springs and caves in south-central Texas. Many of these are threatened or endangered species, and some are found only at one location. A number of the neotenic salamanders might be at risk from habitat loss associated with declines in ground-water levels. Eurycea salamander habitats are associated with three aquifers in south-central Texas: (1) the Edwards-Trinity (Plateau) aquifer, (2) the Edwards (Balcones Fault Zone) aquifer, and (3) the Trinity aquifer. The Edwards (Balcones fault zone) aquifer is commonly separated into three segments: from southwest to northeast, the San Antonio segment, the Barton Springs segment, and the northern segment. The Trinity aquifer south of the Colorado River can be divided into three permeable zones, the upper, middle, and lower zone. The U.S. Geological Survey, in cooperation with the U.S. Fish and Wildlife Service, developed this report (geodatabase) to aggregate the spatial data necessary to assess the potential effects of ground-water declines on known Eurycea habitat locations in south-central Texas. The geodatabase provides information about spring habitats, spring flow, cave habitats, aquifers, and projected water levels.

A KST framework for correlation network construction from time series signals

NASA Astrophysics Data System (ADS)

Qi, Jin-Peng; Gu, Quan; Zhu, Ying; Zhang, Ping

2018-04-01

A KST (Kolmogorov-Smirnov test and T statistic) method is used for construction of a correlation network based on the fluctuation of each time series within the multivariate time signals. In this method, each time series is divided equally into multiple segments, and the maximal data fluctuation in each segment is calculated by a KST change detection procedure. Connections between each time series are derived from the data fluctuation matrix, and are used for construction of the fluctuation correlation network (FCN). The method was tested with synthetic simulations and the result was compared with those from using KS or T only for detection of data fluctuation. The novelty of this study is that the correlation analyses was based on the data fluctuation in each segment of each time series rather than on the original time signals, which would be more meaningful for many real world applications and for analysis of large-scale time signals where prior knowledge is uncertain.

Localization of lung fields in HRCT images using a deep convolution neural network

NASA Astrophysics Data System (ADS)

Kumar, Abhishek; Agarwala, Sunita; Dhara, Ashis Kumar; Mukhopadhyay, Sudipta; Nandi, Debashis; Garg, Mandeep; Khandelwal, Niranjan; Kalra, Naveen

2018-02-01

Lung field segmentation is a prerequisite step for the development of a computer-aided diagnosis system for interstitial lung diseases observed in chest HRCT images. Conventional methods of lung field segmentation rely on a large gray value contrast between lung fields and surrounding tissues. These methods fail on lung HRCT images with dense and diffused pathology. An efficient prepro- cessing could improve the accuracy of segmentation of pathological lung field in HRCT images. In this paper, a convolution neural network is used for localization of lung fields in HRCT images. The proposed method provides an optimal bounding box enclosing the lung fields irrespective of the presence of diffuse pathology. The performance of the proposed algorithm is validated on 330 lung HRCT images obtained from MedGift database on ZF and VGG networks. The model achieves a mean average precision of 0.94 with ZF net and a slightly better performance giving a mean average precision of 0.95 in case of VGG net.

The deep space network, volume 13

NASA Technical Reports Server (NTRS)

1973-01-01

The objectives, functions, and organization of the Deep Space Network are summarized. The deep space instrumentation facility, the ground communications facility, and the network control system are described. Other areas reported include: Helios Mission support, DSN support of the Mariner Mars 1971 extended mission, Mariner Venus/Mercury 1973 mission support, Viking mission support, radio science, tracking and ground-based navigation, network control and data processing, and deep space stations.

U.S. Geological Survey Ground-Water Climate Response Network

USGS Publications Warehouse

,

2007-01-01

The U.S. Geological Survey serves the Nation by providing reliable hydrologic information used by others to manage the Nation's water resources. The U.S. Geological Survey (USGS) measures more than 20,000 wells each year for a variety of objectives as part of Federal programs and in cooperation with State and local agencies. Water-level data are collected using consistent data-collection and quality-control methods. A small subset of these wells meets the criteria necessary to be included in a 'Climate Response Network' of wells designed to illustrate the response of the ground-water system to climate variations nationwide. The primary purpose of the Climate Response Network is to portray the effect of climate on ground-water levels in unconfined aquifers or near-surface confined aquifers that are minimally affected by pumping or other anthropogenic stresses. The Climate Response Network Web site (http://groundwaterwatch.usgs.gov/) is the official USGS Web site for illustrating current ground-water conditions in the United States and Puerto Rico. The Climate Response Network Web pages provide information on ground-water conditions at a variety of scales. A national map provides a broad overview of water-table conditions across the Nation. State maps provide a more local picture of ground-water conditions. Site pages provide the details about a specific well.

Clinical evaluation of semi-automatic open-source algorithmic software segmentation of the mandibular bone: Practical feasibility and assessment of a new course of action

PubMed Central

Wallner, Jürgen; Hochegger, Kerstin; Chen, Xiaojun; Mischak, Irene; Reinbacher, Knut; Pau, Mauro; Zrnc, Tomislav; Schwenzer-Zimmerer, Katja; Zemann, Wolfgang; Schmalstieg, Dieter

2018-01-01

Introduction Computer assisted technologies based on algorithmic software segmentation are an increasing topic of interest in complex surgical cases. However—due to functional instability, time consuming software processes, personnel resources or licensed-based financial costs many segmentation processes are often outsourced from clinical centers to third parties and the industry. Therefore, the aim of this trial was to assess the practical feasibility of an easy available, functional stable and licensed-free segmentation approach to be used in the clinical practice. Material and methods In this retrospective, randomized, controlled trail the accuracy and accordance of the open-source based segmentation algorithm GrowCut was assessed through the comparison to the manually generated ground truth of the same anatomy using 10 CT lower jaw data-sets from the clinical routine. Assessment parameters were the segmentation time, the volume, the voxel number, the Dice Score and the Hausdorff distance. Results Overall semi-automatic GrowCut segmentation times were about one minute. Mean Dice Score values of over 85% and Hausdorff Distances below 33.5 voxel could be achieved between the algorithmic GrowCut-based segmentations and the manual generated ground truth schemes. Statistical differences between the assessment parameters were not significant (p<0.05) and correlation coefficients were close to the value one (r > 0.94) for any of the comparison made between the two groups. Discussion Complete functional stable and time saving segmentations with high accuracy and high positive correlation could be performed by the presented interactive open-source based approach. In the cranio-maxillofacial complex the used method could represent an algorithmic alternative for image-based segmentation in the clinical practice for e.g. surgical treatment planning or visualization of postoperative results and offers several advantages. Due to an open-source basis the used method could be further developed by other groups or specialists. Systematic comparisons to other segmentation approaches or with a greater data amount are areas of future works. PMID:29746490

Effective spreading from multiple leaders identified by percolation in the susceptible-infected-recovered (SIR) model

NASA Astrophysics Data System (ADS)

Ji, Shenggong; Lü, Linyuan; Yeung, Chi Ho; Hu, Yanqing

2017-07-01

Social networks constitute a new platform for information propagation, but its success is crucially dependent on the choice of spreaders who initiate the spreading of information. In this paper, we remove edges in a network at random and the network segments into isolated clusters. The most important nodes in each cluster then form a set of influential spreaders, such that news propagating from them would lead to extensive coverage and minimal redundancy. The method utilizes the similarities between the segmented networks before percolation and the coverage of information propagation in each social cluster to obtain a set of distributed and coordinated spreaders. Our tests of implementing the susceptible-infected-recovered model on Facebook and Enron email networks show that this method outperforms conventional centrality-based methods in terms of spreadability and coverage redundancy. The suggested way of identifying influential spreaders thus sheds light on a new paradigm of information propagation in social networks.