Search NASA⌕ Search

SEARCH · Search NASA

Results for “Image segmentation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,747 records · Page 97

Normalized Noise Power Spectrum of Full Field Digital Mammography System

A method to measure noise power spectrum of a full field digital mammography system is presented. The effect of X-ray radiation dose, size and configuration of region of interest on normalized noise power spectrum (NNPS) was investigated. Flat field images were acquired using RQA-M2 beam quality technique (Mo/Mo anode-filter, 28 kV, 2 mm Al) with different clinical radiation doses. The images were cropped at about 4 cm from the edge of the breast wall and then divided into different size of non-overlapping or overlapping segments. NNPS was determined through detrending, 2-D fast Fourier transformation and normalization. Our measurement shows that high radiation dose gave lower NNPS at a specific beam quality.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Panel-Segmentation: A Python Package for Automated Solar Array Metadata Extraction Using Satellite Imagery

The NREL Python Panel-Segmentation package is a toolkit that automates the process of extracting accurate and valuable metadata related to solar array installations, using publicly available Google Maps satellite imagery. Previously published work includes automated azimuth estimation for individual solar installations in satellite images. Our continued research focuses on automated detection and classification of solar installation mounting configuration (tracking or fixed-tilt; rooftop, ground, or carport). Specifically, a Faster-RCNN Resnet-50 feature pyramid network (FPN) model was trained and validated on 862 manually labeled satellite images. This model was used to perform object detection on satellite imagery, locating and classifying individual solar installations' mounting configuration and type. Model results showed a mean average precision score (mAP) of 77.79%, with the model strongest at detecting fixed-tilt ground mount and fixed-tilt carport installations. The object detection model and its outputs have been incorporated into the Panel-Segmentation package's automated metadata extraction pipeline, which returns the mounting configuration and azimuth for individual solar arrays in satellite imagery. The complete image data set with labels has been released on the U.S. Department of Energy (DOE) DuraMAT DataHub, to encourage further research in this area.

deep learning↗

Characterization of tissue magnetic susceptibility-induced distortions for MRIgRT

Purpose: MR image geometric integrity is one of the building blocks of MRI-guided radiotherapy. In particular, tissue magnetic susceptibility-induced effects are patient-dependent and their behavior is difficult to assess and predict. In this study, the authors investigated in detail the characteristics of susceptibility ({chi}) distortions in the context of MRIgRT, including the case of two common MR-linac system configurations. Methods: The magnetic field distortions were numerically simulated for several imaging parameters and anatomical sites, i.e., brain, lung, pelvis (with air pockets), and prostate. The simulation process consisted of (a) segmentation of patient CT data into susceptibility relevant anatomical volumes (i.e., soft-tissue, bone and air/lung), (b) conversion of CT data into susceptibility masks by assigning bulk {chi} values to the structures defined at (a), (c) numerical computations of the local magnetic fields by using a finite difference algorithm, and (d) generation of the geometric distortion maps from the magnetic field distributions. For each patient anatomy, the distortions were quantified at the interfaces of anatomical structures with significantly different {chi} values. The analysis was performed for two specific orientations of the external main magnetic field (B{sub 0}) characteristic to the MR-linac systems, specifically along the z-axis for a bore MR scanner and in the (x,y)-plane for a biplanner magnet. The magnetic field local perturbations were reported in ppm. The metrics used to quantify the geometric distortions were the maximum, mean, and range of distortions. The numerical simulation algorithm was validated using phantom data measurements. Results: Susceptibility-induced distortions were determined for both quadratic and patient specific geometries. The numerical simulations showed a good agreement with the experimental data. The measurements were acquired at 1.5 and 3 T and with an encoding gradient varying between 3 and 20 mT/m by using an annular phantom mimicking the water-air and water-oil {chi} interfaces. For quadratic geometries, the magnitude of field distortion increased rapidly with the size of the inhomogeneity up to about 10 mm and then tended to plateau. This trend became more evident for materials with a larger {Delta}{chi} relative to water. The simulations showed only a slight increase in the maximum distortion values when the B{sub 0} orientation was varied with regard to the shape of the {chi} inhomogeneity. In the case of patient anatomy, the largest distortion values arose at the air-soft-tissue interface. Considering the two MR-linac system configurations and comparing the field distortion values corresponding to all organ structures, the distortions tended to be larger for the biplanar magnet. The authors provide a reference table with ppm values which can be used to easily evaluate the geometric distortions for patient data as a function of B{sub 0} and the strength of the encoding gradient. Conclusions: The susceptibility distortions were quantified as a function of multiple parameters such as the {chi} inhomogeneity size and shape, the magnitude of B{sub 0} and the readout gradient, and the orientation of B{sub 0} with respect to the sample geometry. The analysis was performed for several anatomical sites and corresponding to two B{sub 0} orientations as featured by MR-linac systems.

60 APPLIED LIFE SCIENCES↗

An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel

Abstract Gaseous fission products from nuclear fission reactions tend to form fission gas bubbles of various shapes and sizes inside nuclear fuel. The behavior of fission gas bubbles dictates nuclear fuel performances, such as fission gas release, grain growth, swelling, and fuel cladding mechanical interaction. Although mechanical understanding of the overall evolution behavior of fission gas bubbles is well known, lacking the quantitative data and high-level correlation between burnup/temperature and microstructure evolution blocks the development of predictive models and reduces the possibility of accelerating the qualification for new fuel forms. Historical characterization of fission gas bubbles in irradiated nuclear fuel relied on a simple threshold method working on low-resolution optical microscopy images. Advanced characterization of fission gas bubbles using scanning electron microscopic images reveals unprecedented details and extensive morphological data, which strains the effectiveness of conventional methods. This paper proposes a hybrid framework, based on digital image processing and deep learning models, to efficiently detect and classify fission gas bubbles from scanning electron microscopic images. The developed bubble annotation tool used a multitask deep learning network that integrates U-Net and ResNet to accomplish instance-level bubble segmentation. With limited annotated data, the model achieves a recall ratio of more than 90%, a leap forward compared to the threshold method. The model has the capability to identify fission gas bubbles with and without lanthanides to better understand the movement of lanthanide fission products and fuel cladding chemical interaction. Lastly, the deep learning model is versatile and applicable to the micro-structure segmentation of similar materials.

36 MATERIALS SCIENCE↗

WE-AB-204-03: A Novel 3D Printed Phantom for 4D PET/CT Imaging and SIB Radiotherapy Verification

Purpose: To construct and test a 3D printed phantom designed to mimic variable PET tracer uptake seen in lung tumor volumes. To assess segmentation accuracy of sub-volumes of the phantom following 4D PET/CT scanning with ideal and patient-specific respiratory motion. To plan, deliver and verify delivery of PET-driven, gated, simultaneous integrated boost (SIB) radiotherapy plans. Methods: A set of phantoms and inserts were designed and manufactured for a realistic representation of lung cancer gated radiotherapy steps from 4D PET/CT scanning to dose delivery. A cylindrical phantom (40x 120 mm) holds inserts for PET/CT scanning. The novel 3D printed insert dedicated to 4D PET/CT mimics high PET tracer uptake in the core and lower uptake in the periphery. This insert is a variable density porous cylinder (22.12×70 mm), ABS-P430 thermoplastic, 3D printed by uPrint SE Plus with inner void volume (5.5×42 mm). The square pores (1.8×1.8 mm2 each) fill 50% of outer volume, resulting in a 2:1 SUV ratio of PET-tracer in the void volume with respect to porous volume. A matching in size cylindrical phantom is dedicated to validate gated radiotherapy. It contains eight peripheral holes matching the location of the porous part of the 3D printed insert, and one central hole. These holes accommodate adaptors for Farmer-type ion chamber and cells vials. Results: End-to-end test were performed from 4D PET/CT scanning to transferring data to the planning system and target volume delineation. 4D PET/CT scans were acquired of the phantom with different respiratory motion patterns and gating windows. A measured 2:1 18F-FDG SUV ratio between inner void and outer volume matched the 3D printed design. Conclusion: The novel 3D printed phantom mimics variable PET tracer uptake typical of tumors. Obtained 4D PET/CT scans are suitable for segmentation, treatment planning and delivery in SIB gated treatments of NSCLC.

60 APPLIED LIFE SCIENCES↗

Exudate-based diabetic macular edema detection in fundus images using publicly available datasets

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy. In a large scale screening environment DME can be assessed by detecting exudates (a type of bright lesions) in fundus images. In this work, we introduce a new methodology for diagnosis of DME using a novel set of features based on colour, wavelet decomposition and automatic lesion segmentation. These features are employed to train a classifier able to automatically diagnose DME through the presence of exudation. We present a new publicly available dataset with ground-truth data containing 169 patients from various ethnic groups and levels of DME. This and other two publicly available datasets are employed to evaluate our algorithm. We are able to achieve diagnosis performance comparable to retina experts on the MESSIDOR (an independently labelled dataset with 1200 images) with cross-dataset testing (e.g., the classifier was trained on an independent dataset and tested on MESSIDOR). Our algorithm obtained an AUC between 0.88 and 0.94 depending on the dataset/features used. Additionally, it does not need ground truth at lesion level to reject false positives and is computationally efficient, as it generates a diagnosis on an average of 4.4 s (9.3 s, considering the optic nerve localization) per image on an 2.6 GHz platform with an unoptimized Matlab implementation.

59 BASIC BIOLOGICAL SCIENCES↗

BioSig3D: High Content Screening of Three-Dimensional Cell Culture Models

BioSig3D is a computational platform for high-content screening of three-dimensional (3D) cell culture models that are imaged in full 3D volume. It provides an end-to-end solution for designing high content screening assays, based on colony organization that is derived from segmentation of nuclei in each colony. BioSig3D also enables visualization of raw and processed 3D volumetric data for quality control, and integrates advanced bioinformatics analysis. The system consists of multiple computational and annotation modules that are coupled together with a strong use of controlled vocabularies to reduce ambiguities between different users. It is a web-based system that allows users to: design an experiment by defining experimental variables, upload a large set of volumetric images into the system, analyze and visualize the dataset, and either display computed indices as a heatmap, or phenotypic subtypes for heterogeneity analysis, or download computed indices for statistical analysis or integrative biology. BioSig3D has been used to profile baseline colony formations with two experiments: (i) morphogenesis of a panel of human mammary epithelial cell lines (HMEC), and (ii) heterogeneity in colony formation using an immortalized non-transformed cell line. These experiments reveal intrinsic growth properties of well-characterized cell lines that are routinely used for biological studies. BioSig3D is being released with seed datasets and video-based documentation.

Science & Technology - Other Topics↗

Development of High Resolution Mirrors and Cd-Zn-Te Detectors for Hard X-ray Astronomy

We describe the fabrication and implementation of a high-resolution conical, grazing- incidence, hard X-ray (20-70 keV) telescope. When flown aboard stratospheric balloons, these mirrors are used to image cosmic sources such as supernovae, neutron stars, and quasars. The fabrication process involves generating super-polished mandrels, mirror shell electroforming, and mirror testing. The cylindrical mandrels consist of two conical segments; each segment is approximately 305 mm long. These mandrels are first, precision ground to within approx. 1.0 micron straightness along each conical segment and then lapped and polished to less than 0.5 micron straightness. Each mandrel segment is the super-polished to an average surface roughness of approx. 3.25 angstrom rms. By mirror shell replication, this combination of good figure and low surface roughness has enabled us to achieve 15 arcsec, confirmed by X-ray measurements in the Marshall Space Flight Center 102 meter test facility. To image the focused X-rays requires a focal plane detector with appropriate spatial resolution. For 15 arcsec optics of 6 meter focal length, this resolution must be around 200 microns. In addition, the detector must have a high efficiency, relatively high energy resolution, and low background. We are currently developing Cadmium-Zinc-Telluride fine-pixel detectors for this purpose. The detectors under study consist of a 16x16 pixel array with a pixel pitch of 300 microns and are 1 mm and 2 mm thick. At 60 keV, the measured energy resolution is around 2%.

Ramsey, Brian D.↗

STATISTICAL PROPERTIES OF SOLAR ACTIVE REGIONS OBTAINED FROM AN AUTOMATIC DETECTION SYSTEM AND THE COMPUTATIONAL BIASES

We have developed a computational software system to automate the process of identifying solar active regions (ARs) and quantifying their physical properties based on high-resolution synoptic magnetograms constructed from Michelson Doppler Imager (MDI; on board the SOHO spacecraft) images from 1996 to 2008. The system, based on morphological analysis and intensity thresholding, has four functional modules: (1) intensity segmentation to obtain kernel pixels, (2) a morphological opening operation to erase small kernels, which effectively remove ephemeral regions and magnetic fragments in decayed ARs, (3) region growing to extend kernels to full AR size, and (4) the morphological closing operation to merge/group regions with a small spatial gap. We calculate the basic physical parameters of the 1730 ARs identified by the auto system. The mean and maximum magnetic flux of individual ARs are 1.67 x 10{sup 22} Mx and 1.97 x 10{sup 23} Mx, while that per Carrington rotation are 1.83 x 10{sup 23} Mx and 6.96 x 10{sup 23} Mx, respectively. The frequency distributions of ARs with respect to both area size and magnetic flux follow a log-normal function. However, when we decrease the detection thresholds and thus increase the number of detected ARs, the frequency distribution largely follows a power-law function. We also find that the equatorward drifting motion of the AR bands with solar cycle can be described by a linear function superposed with intermittent reverse driftings. The average drifting speed over one solar cycle is 1{sup o}.83{+-}0{sup o}.04 yr{sup -1} or 0.708 {+-} 0.015 m s{sup -1}.

79 ASTRONOMY AND ASTROPHYSICS↗

The role of MatP, ZapA and ZapB in chromosomal organization and dynamics in Escherichia coli

Despite extensive research over several decades, a comprehensive view of how the Escherichia coli chromosome is organized within the nucleoid, and how two daughter chromosomes segregate has yet to emerge. Here we investigate the role of the MatP, ZapA and ZapB proteins in organizing the replication terminus (Ter) region and in the chromosomal segregation process. Quantitative image analysis of the fluorescently labeled Ter region shows that the replication terminus attaches to the divisome in a single segment along the perimeter of the cell in a MatP, ZapA and ZapB-dependent manner. The attachment does not significantly affect the bulk chromosome segregation in slow growth conditions. With or without the attachment, two chromosomal masses separate from each other at a speed comparable to the cell growth. The separation starts even before the replication terminus region positions itself at the center of the nucleoid. Modeling of the segregation based on conformational entropy correctly predicts the positioning of the replication terminus region within the nucleoid. Furthermore, the model produces a distinctly different chromosomal density distribution than the experiment, indicating that the conformational entropy plays a limited role in segregating the chromosomes in the late stages of replication.

59 BASIC BIOLOGICAL SCIENCES↗

Automated aortic calcium scoring on low-dose chest computed tomography

Purpose: Thoracic computed tomography (CT) scans provide information about cardiovascular risk status. These scans are non-ECG synchronized, thus precise quantification of coronary calcifications is difficult. Aortic calcium scoring is less sensitive to cardiac motion, so it is an alternative to coronary calcium scoring as an indicator of cardiovascular risk. The authors developed and evaluated a computer-aided system for automatic detection and quantification of aortic calcifications in low-dose noncontrast-enhanced chest CT. Methods: The system was trained and tested on scans from participants of a lung cancer screening trial. A total of 433 low-dose, non-ECG-synchronized, noncontrast-enhanced 16 detector row examinations of the chest was randomly divided into 340 training and 93 test data sets. A first observer manually identified aortic calcifications on training and test scans. A second observer did the same on the test scans only. First, a multiatlas-based segmentation method was developed to delineate the aorta. Segmented volume was thresholded and potential calcifications (candidate objects) were extracted by three-dimensional connected component labeling. Due to image resolution and noise, in rare cases extracted candidate objects were connected to the spine. They were separated into a part outside and parts inside the aorta, and only the latter was further analyzed. All candidate objects were represented by 63 features describing their size, position, and texture. Subsequently, a two-stage classification with a selection of features and k-nearest neighbor classifiers was performed. Based on the detected aortic calcifications, total calcium volume score was determined for each subject. Results: The computer system correctly detected, on the average, 945 mm{sup 3} out of 965 mm{sup 3} (97.9%) calcified plaque volume in the aorta with an average of 64 mm{sup 3} of false positive volume per scan. Spearman rank correlation coefficient was {rho}=0.960 between the system and the first observer compared to {rho}=0.961 between the two observers. Conclusions: Automatic calcium scoring in the aorta thus appears feasible with good correlation between manual and automatic scoring.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

RhizoNet: semantic segmentation of plant roots using CNN (RhizoNet) v0.0.1

RhizoNet is designed for the semantic segmentation of plant root scans, utilizing a sophisticated deep learning network known as Residual Unet. It specializes in processing color images of plants cultivated in a hydroponic EcoFAB system, captured using an Epson scanner. The core of the algorithm is based on Residual U-nets, which significantly improve prediction accuracy. This is achieved through the implementation of a convex hull operation, which effectively delineates the primary root component by leveraging spatio-temporal image data. This enables researchers to accurately assess predicted biomass and monitor plant growth over time.

Ushizima, Daniela↗

Automated Progress Monitoring in Modular Construction Factories Using Computer Vision and Building Information Modeling

Modular construction methods have recently gained interest due to the advantages offered in terms of safety, quality, and productivity for projects. In this method, a significant portion of the construction is performed off-site in factories where modular components are built in different workstations, assembled on the production line, and shipped to the site for installation. Due to the labor-intensive nature of tasks, cycle times in modular construction factories are highly variable, which commonly leads to major bottlenecks and delays in construction projects. To remedy this effect, recent methods rely on sensors such as RFID to monitor the production process, which is reportedly expensive, and intrusive to the work process. Recently, computer vision-based methods have been proposed to track the production process in modular construction factories. However, these methods overlook monitoring the assembly process on the production line. Therefore, this paper presents a method to monitor the assembly process by integrating computer vision-based methods with Building Information Modeling (BIM). The proposed method detects the modular units using object segmentation; superimposes the installation area with the corresponding 2D region using BIM, and identifies the installation of the components using image processing techniques. The proposed method has been validated using surveillance videos captured from a modular construction factory in the US. Successful implementation of the proposed method can lead to timely identification of delays during the assembly process and reduce delays in modular integrated construction projects.

building information modeling↗

Automatic Rural Road Centerline Detection and Extraction from Aerial Images for a Forest Fire Decision Support System

To effectively manage the terrestrial firefighting fleet in a forest fire scenario, namely, to optimize its displacement in the field, it is crucial to have a well-structured and accurate mapping of rural roads. The landscape’s complexity, mainly due to severe shadows cast by the wild vegetation and trees, makes it challenging to extract rural roads based on processing aerial or satellite images, leading to heterogeneous results. This article proposes a method to improve the automatic detection of rural roads and the extraction of their centerlines from aerial images. This method has two main stages: (i) the use of a deep learning model (DeepLabV3+) for predicting rural road segments; (ii) an optimization strategy to improve the connections between predicted rural road segments, followed by a morphological approach to extract the rural road centerlines using thinning algorithms, such as those proposed by Zhang–Suen and Guo–Hall. After completing these two stages, the proposed method automatically detected and extracted rural road centerlines from complex rural environments. This is useful for developing real-time mapping applications.

Lourenço, Miguel (ORCID:0000000157673394)↗

Conversion of raster coded images to polygonal data structures

A method is presented for converting polygons coded in raster data structures into conventional vector structures to allow the output of scanner-based data collection systems to be input directly to conventional geographic information systems. The method relies on topological principles to (1) uniquely label each polygon in the image and produce an output image in which each pixel is described by the label of the polygon to which it belongs; (2) create line segment components of polygon boundaries, with nodes labeled and the two adjacent polygons identified; and (3) traverse the polygon boundaries by connecting the appropriate adjacent line segments. The conversion capability makes it possible to design systems which automatically convert to the data structure most appropriate for a particular application.

Nichols, D. A.↗

Measurements of Ocean Features With AIRSAR

Here we discuss an indirect approach for measuring ocean features from synthetic aperture radar (SAR) imagery. The approach is based on the refraction of swell that can be seen in the SAR imagery. Locally, swell refraction is due only to changes in bathymetry and surface current shear and it is easy to separate these two effects. It has been shown that linear energetic shears can be detected and measured from high resolution images of the ocean. A simple approach to measuring surface velocity and shear is to divide the imagery into smaller segments where the shear in each segment is approximately linear. The known linear algorithm would then be applied to each segment and the velocity/shear distribution can then be determined by assembling the segments with linear shear into an estimate of the actual shear/velocity distribution.

Sheres, David↗

Construction of Prototype Lightweight Mirrors

This contract and the work described was in support of a Seven Segment Demonstrator (SSD) and demonstration of a different technology for construction of lightweight mirrors. The objectives of the SSD were to demonstrate functionality and performance of a seven segment prototype array of hexagonal mirrors and supporting electromechanical components which address design issues critical to space optics deployed in large space based telescopes for astronomy and for optics used in spaced based optical communications systems. The SSD was intended to demonstrate technologies which can support the following capabilities; Transportation in dense packaging to existing launcher payload envelopes, then deployable on orbit to form space telescope with large aperture. Provide very large (less than 10 meters) primary reflectors of low mass and cost. Demonstrate the capability to form a segmented primary or quaternary mirror into a quasi-continuous surface with individual subapertures phased so that near diffraction limited imaging in the visible wavelength region is achieved. Continuous compensation of optical wavefront due to perturbations caused by imperfections, natural disturbances, and equipment induced vibrations/deflections to provide near diffraction limited imaging performance in the visible wavelength region. Demonstrate the feasibility of fabricating such systems with reduced mass and cost compared to past approaches. While the SSD could not be expected to satisfy all of the above capabilities, the intent was to start identifying and understanding new technologies that might be applicable to these goals.

Robinson, William G.↗

Adaptive Full Aperture Wavefront Sensor Study

This grant and the work described was in support of a Seven Segment Demonstrator (SSD) and review of wavefront sensing techniques proposed by the Government and Contractors for the Next Generation Space Telescope (NGST) Program. A team developed the SSD concept. For completeness, some of the information included in this report has also been included in the final report of a follow-on contract (H-27657D) entitled "Construction of Prototype Lightweight Mirrors". The original purpose of this GTRI study was to investigate how various wavefront sensing techniques might be most effectively employed with large (greater than 10 meter) aperture space based telescopes used for commercial and scientific purposes. However, due to changes in the scope of the work performed on this grant and in light of the initial studies completed for the NGST program, only a portion of this report addresses wavefront sensing techniques. The wavefront sensing techniques proposed by the Government and Contractors for the NGST were summarized in proposals and briefing materials developed by three study teams including NASA Goddard Space Flight Center, TRW, and Lockheed-Martin. In this report, GTRI reviews these approaches and makes recommendations concerning the approaches. The objectives of the SSD were to demonstrate functionality and performance of a seven segment prototype array of hexagonal mirrors and supporting electromechanical components which address design issues critical to space optics deployed in large space based telescopes for astronomy and for optics used in spaced based optical communications systems. The SSD was intended to demonstrate technologies which can support the following capabilities: Transportation in dense packaging to existing launcher payload envelopes, then deployable on orbit to form a space telescope with large aperture. Provide very large (greater than 10 meters) primary reflectors of low mass and cost. Demonstrate the capability to form a segmented primary or quaternary mirror into a quasi-continuous surface with individual subapertures phased so that near diffraction limited imaging in the visible wavelength region is achieved. Continuous compensation of optical wavefront due to perturbations caused by imperfections, natural disturbances, and equipment induced vibrations/deflections to provide near diffraction limited imaging performance in the visible wavelength region. Demonstrate the feasibility of fabricating such systems with reduced mass and cost compared to past approaches.

Robinson, William G.↗