Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 955 records · Page 53

STRUCTURAL ANNOTATION OF EM IMAGES BY GRAPH CUT

Biological images have the potential to reveal complex signatures that may not be amenable to morphological modeling in terms of shape, location, texture, and color. An effective analytical method is to characterize the composition of a specimen based on user-defined patterns of texture and contrast formation. However, such a simple requirement demands an improved model for stability and robustness. Here, an interactive computational model is introduced for learning patterns of interest by example. The learned patterns bound an active contour model in which the traditional gradient descent optimization is replaced by the more efficient optimization of the graph cut methods. First, the energy function is defined according to the curve evolution. Next, a graph is constructed with weighted edges on the energy function and is optimized with the graph cut algorithm. As a result, the method combines the advantages of the level set method and graph cut algorithm, i.e.,"topological" invariance and computational efficiency. The technique is extended to the multi-phase segmentation problem; the method is validated on synthetic images and then applied to specimens imaged by transmission electron microscopy(TEM).

60 APPLIED LIFE SCIENCES↗

Assessment of dedicated low-dose cardiac micro-CT reconstruction algorithms using the left ventricular volume of small rodents as a performance measure

Purpose: Phase-correlated microcomputed tomography (micro-CT) imaging plays an important role in the assessment of mouse models of cardiovascular diseases and the determination of functional parameters as the left ventricular volume. As the current gold standard, the phase-correlated Feldkamp reconstruction (PCF), shows poor performance in case of low dose scans, more sophisticated reconstruction algorithms have been proposed to enable low-dose imaging. In this study, the authors focus on the McKinnon-Bates (MKB) algorithm, the low dose phase-correlated (LDPC) reconstruction, and the high-dimensional total variation minimization reconstruction (HDTV) and investigate their potential to accurately determine the left ventricular volume at different dose levels from 50 to 500 mGy. The results were verified in phantom studies of a five-dimensional (5D) mathematical mouse phantom. Methods: Micro-CT data of eight mice, each administered with an x-ray dose of 500 mGy, were acquired, retrospectively gated for cardiac and respiratory motion and reconstructed using PCF, MKB, LDPC, and HDTV. Dose levels down to 50 mGy were simulated by using only a fraction of the projections. Contrast-to-noise ratio (CNR) was evaluated as a measure of image quality. Left ventricular volume was determined using different segmentation algorithms (Otsu, level sets, region growing). Forward projections of the 5D mouse phantom were performed to simulate a micro-CT scan. The simulated data were processed the same way as the real mouse data sets. Results: Compared to the conventional PCF reconstruction, the MKB, LDPC, and HDTV algorithm yield images of increased quality in terms of CNR. While the MKB reconstruction only provides small improvements, a significant increase of the CNR is observed in LDPC and HDTV reconstructions. The phantom studies demonstrate that left ventricular volumes can be determined accurately at 500 mGy. For lower dose levels which were simulated for real mouse data sets, the HDTV algorithm shows the best performance. At 50 mGy, the deviation from the reference obtained at 500 mGy were less than 4%. Also the LDPC algorithm provides reasonable results with deviation less than 10% at 50 mGy while PCF and MKB reconstruction show larger deviations even at higher dose levels. Conclusions: LDPC and HDTV increase CNR and allow for quantitative evaluations even at dose levels as low as 50 mGy. The left ventricular volumes exemplarily illustrate that cardiac parameters can be accurately estimated at lowest dose levels if sophisticated algorithms are used. This allows to reduce dose by a factor of 10 compared to today's gold standard and opens new options for longitudinal studies of the heart.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Evaluation of Functional Marrow Irradiation Based on Skeletal Marrow Composition Obtained Using Dual-Energy Computed Tomography

Purpose: To develop an imaging method to characterize and map marrow composition in the entire skeletal system, and to simulate differential targeted marrow irradiation based on marrow composition. Methods and Materials: Whole-body dual energy computed tomography (DECT) images of cadavers and leukemia patients were acquired, segmented to separate bone marrow components, namely, bone, red marrow (RM), and yellow marrow (YM). DECT-derived marrow fat fraction was validated using histology of lumbar vertebrae obtained from cadavers. The fractions of RM (RMF = RM/total marrow) and YMF were calculated in each skeletal region to assess the correlation of marrow composition with sites and ages. Treatment planning was simulated to target irradiation differentially at a higher dose (18 Gy) to either RM or YM and a lower dose (12 Gy) to the rest of the skeleton. Results: A significant correlation between fat fractions obtained from DECT and cadaver histology samples was observed (r=0.861, P<.0001, Pearson). The RMF decreased in the head, neck, and chest was significantly inversely correlated with age but did not show any significant age-related changes in the abdomen and pelvis regions. Conformity of radiation to targets (RM, YM) was significantly dependent on skeletal sites. The radiation exposure was significantly reduced (P<.05, t test) to organs at risk (OARs) in RM and YM irradiation compared with standard total marrow irradiation (TMI). Conclusions: Whole-body DECT offers a new imaging technique to visualize and measure skeletal-wide marrow composition. The DECT-based treatment planning offers volumetric and site-specific precise radiation dosimetry of RM and YM, which varies with aging. Our proposed method could be used as a functional compartment of TMI for further targeted radiation to specific bone marrow environment, dose escalation, reduction of doses to OARs, or a combination of these factors.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Quantitative Assessment of Heterogeneity in Tumor Metabolism Using FDG-PET

Purpose: [{sup 18}F]-fluorodeoxyglucose-positron emission tomography (FDG-PET) images are usually quantitatively analyzed in 'whole-tumor' volumes of interest. Also parameters determined with dynamic PET acquisitions, such as the Patlak glucose metabolic rate (MR{sub glc}) and pharmacokinetic rate constants of two-tissue compartment modeling, are most often derived per lesion. We propose segmentation of tumors to determine tumor heterogeneity, potentially useful for dose-painting in radiotherapy and elucidating mechanisms of FDG uptake. Methods and Materials: In 41 patients with 104 lesions, dynamic FDG-PET was performed. On MR{sub glc} images, tumors were segmented in quartiles of background subtracted maximum MR{sub glc} (0%-25%, 25%-50%, 50%-75%, and 75%-100%). Pharmacokinetic analysis was performed using an irreversible two-tissue compartment model in the three segments with highest MR{sub glc} to determine the rate constants of FDG metabolism. Results: From the highest to the lowest quartile, significant decreases of uptake (K{sub 1}), washout (k{sub 2}), and phosphorylation (k{sub 3}) rate constants were seen with significant increases in tissue blood volume fraction (V{sub b}). Conclusions: Tumor regions with highest MR{sub glc} are characterized by high cellular uptake and phosphorylation rate constants with relatively low blood volume fractions. In regions with less metabolic activity, the blood volume fraction increases and cellular uptake, washout, and phosphorylation rate constants decrease. These results support the hypothesis that regional tumor glucose phosphorylation rate is not dependent on the transport of nutrients (i.e., FDG) to the tumor.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Automating the detection of hydrological barriers and fragmentation in wetlands using deep learning and InSAR

The loss of hydrological connectivity and fragmentation of natural wetlands is a widespread driver of wetland degradation. Understanding where and how natural connectivity is impaired is essential for managing, protecting and remediating these ecosystems. Wetland Interferometric Synthetic Aperture Radar (Wetland InSAR) can provide information on surface flow orientation in wetlands at a high spatial resolution, which can be used for barrier detection. However, the broad application of this approach is constrained by the labour-intensive manual delineation of barriers based on mapped water levels. This study presents the first deep learning-based methodology for the automated detection of hydrological barriers. We trained a deep convolutional network to segment edge features of hydrological barriers in 25 image pairs captured by ALOS PALSAR-1 L-Band InSAR between 2006 and 2011. The training dataset consists of manually labelled and delineated barriers showing abrupt changes in water surface elevation and wrapped interferograms with high coherence. We tested this method across three wetland sites: the Everglades and southern Louisiana wetlands (United States) and the Cienaga de Zapata (Cuba). Across these sites, the convolutional network detected hydrological barriers with up to 84% accuracy. The model performed particularly well for linear hydrological barriers such as roads, dikes, and channels. Notably, some barriers impede flow only seasonally, appearing during low water levels and disappearing when water levels rise. Our automated approach to detecting and assessing wetland hydrologic connectivity can be applied more broadly to support the effective management of fragmented wetland ecosystems.

54 ENVIRONMENTAL SCIENCES↗

High-Resolution Phase-Contrast Imaging of Submicron Particles in Unstained Lung Tissue

To access the risks and chances of deposition of submicron particles in the gas-exchange area of the lung, a precise three-dimensional (3D)-localization of the sites of deposition is essential--especially because local peaks of deposition are expected in the acinar tree and in individual alveoli. In this study we developed the workflow for such an investigation. We administered 200-nm gold particles to young adult rats by intratracheal instillation. After fixation and paraffin embedding, their lungs were imaged unstained using synchrotron radiation x-ray tomographic microscopy (SRXTM) at the beamline TOMCAT (Swiss Light Source, Villigen, Switzerland) at sample detector distances of 2.5 mm (absorption contrast) and of 52.5 mm (phase contrast). A segmentation based on a global threshold of grey levels was successfully done on absorption-contrast images for the gold and on the phase-contrast images for the tissue. The smallest spots containing gold possessed a size of 1-2 voxels of 370-nm side length. We conclude that a combination of phase and absorption contrast SRXTM imaging is necessary to obtain the correct segmentation of both tissue and gold particles. This method will be used for the 3D localization of deposited particles in the gas-exchange area of the lung.

60 APPLIED LIFE SCIENCES↗

TU-H-CAMPUS-IeP2-03: Development of 3D Printed Coronary Phantoms for In-Vitro CT-FFR Validation Using Data from 320- Detector Row Coronary CT Angiography

Purpose: To validate Computed Tomography Fractional Flow Reserve (CT-FFR) measurements with accurate 3D printed coronary phantoms. Methods: DICOM data from four phases in two patients imaged with a standard 320 × 0.5mm coronary CT acquisition (70–80% cardiac cycle) underwent semi-automated segmentation using a research workstation. Both patients had a >50% stenosis from the clinical image interpretation. Each volume was saved as a Stereo Lithographic (STL) file with 250 micron resolution. The 3D geometries were qualitatively assessed; the best of the four phases was 3D printed using a Stratasys Eden260V printer in Tango+, a rubber-like material that roughly emulates mechanical properties of human vasculature. We connected the model to a programmable pump and measured the pressure drop using pressure sensors embedded proximal and distal to the arterial stenosis. Next, the STL files used for the 3D printed models were uploaded in the ANSYS meshing tool (ICEM CFD 16.1). A standard meshing process was applied and the meshed geometry was directly imported in the ANSYS Fluent for Computational Flow Dynamics simulations. The CFD simulations were used to calculate the CT-FFR and compared to the bench top FFR measured in the 3D printed phantoms. Results: FFR-CT measurements and phantoms were completed in within an hour after the segmentation. Patient 1 had a 60% stenosis that resulted in a CT-FFR of 0.68. The second case had a 50% stenosis and a CT-FFR of 0.75. The average bench top FFR measurements were 0.72 and 0.80, respectively. Conclusion: This pilot investigation demonstrated the use of a bench-top coronary model for CT-FFR validation. The measurements and the CFD simulations agreed within 6%. Project supported by Support: Toshiba America Medical Systems Corp.and NIH grant R01-EB002873. Project supported by Toshiba America Medical Systems Corp.and partial support from NIH grant R01-EB002873.

60 APPLIED LIFE SCIENCES↗

SU-E-J-220: Evaluation of Atlas-Based Auto-Segmentation (ABAS) in Head-And-Neck Adaptive Radiotherapy

Purpose: Evaluate the accuracy of atlas-based auto segmentation of organs at risk (OARs) on both helical CT (HCT) and cone beam CT (CBCT) images in head and neck (HN) cancer adaptive radiotherapy (ART). Methods: Six HN patients treated in the ART process were included in this study. For each patient, three images were selected: pretreatment planning CT (PreTx-HCT), in treatment CT for replanning (InTx-HCT) and a CBCT acquired in the same day of the InTx-HCT. Three clinical procedures of auto segmentation and deformable registration performed in the ART process were evaluated: a) auto segmentation on PreTx-HCT using multi-subject atlases, b) intra-patient propagation of OARs from PreTx-HCT to InTx-HCT using deformable HCT-to-HCT image registration, and c) intra-patient propagation of OARs from PreTx-HCT to CBCT using deformable CBCT-to-HCT image registration. Seven OARs (brainstem, cord, L/R parotid, L/R submandibular gland and mandible) were manually contoured on PreTx-HCT and InTx-HCT for comparison. In addition, manual contours on InTx-CT were copied on the same day CBCT, and a local region rigid body registration was performed accordingly for each individual OAR. For procedures a) and b), auto contours were compared to manual contours, and for c) auto contours were compared to those rigidly transferred contours on CBCT. Dice similarity coefficients (DSC) and mean surface distances of agreement (MSDA) were calculated for evaluation. Results: For procedure a), the mean DSC/MSDA of most OARs are >80%/±2mm. For intra-patient HCT-to-HCT propagation, the Resultimproved to >85%/±1.5mm. Compared to HCT-to-HCT, the mean DSC for HCT-to-CBCT propagation drops ∼2–3% and MSDA increases ∼0.2mm. This Resultindicates that the inferior imaging quality of CBCT seems only degrade auto propagation performance slightly. Conclusion: Auto segmentation and deformable propagation can generate OAR structures on HCT and CBCT images with clinically acceptable accuracy. Therefore, they can be reliably implemented in the clinical HN ART process.

60 APPLIED LIFE SCIENCES↗

Automated and Semiautomated Segmentation of Rectal Tumor Volumes on Diffusion-Weighted MRI: Can It Replace Manual Volumetry?

Purpose: Diffusion-weighted imaging (DWI) tumor volumetry is promising for rectal cancer response assessment, but an important drawback is that manual per-slice tumor delineation can be highly time consuming. This study investigated whether manual DWI-volumetry can be reproduced using a (semi)automated segmentation approach. Methods and Materials: Seventy-nine patients underwent magnetic resonance imaging (MRI) that included DWI (highest b value [b1000 or b1100]) before and after chemoradiation therapy (CRT). Tumor volumes were assessed on b1000 (or b1100) DWI before and after CRT by means of (1) automated segmentation (by 2 inexperienced readers), (2) semiautomated segmentation (manual adjustment of the volumes obtained by method 1 by 2 radiologists), and (3) manual segmentation (by 2 radiologists); this last assessment served as the reference standard. Intraclass correlation coefficients (ICC) and Dice similarity indices (DSI) were calculated to evaluate agreement between different methods and observers. Measurement times (from a radiologist's perspective) were recorded for each method. Results: Tumor volumes were not significantly different among the 3 methods, either before or after CRT (P=.08 to .92). ICCs compared to manual segmentation were 0.80 to 0.91 and 0.53 to 0.66 before and after CRT, respectively, for the automated segmentation and 0.91 to 0.97 and 0.61 to 0.75, respectively, for the semiautomated method. Interobserver agreement (ICC) pre and post CRT was 0.82 and 0.59 for automated segmentation, 0.91 and 0.73 for semiautomated segmentation, and 0.91 and 0.75 for manual segmentation, respectively. Mean DSI between the automated and semiautomated method were 0.83 and 0.58 pre-CRT and post-CRT, respectively; DSI between the automated and manual segmentation were 0.68 and 0.42 and 0.70 and 0.41 between the semiautomated and manual segmentation, respectively. Median measurement time for the radiologists was 0 seconds (pre- and post-CRT) for the automated method, 41 to 69 seconds (pre-CRT) and 60 to 67 seconds (post-CRT) for the semiautomated method, and 180 to 296 seconds (pre-CRT) and 84 to 91 seconds (post-CRT) for the manual method. Conclusions: DWI volumetry using a semiautomated segmentation approach is promising and a potentially time-saving alternative to manual tumor delineation, particularly for primary tumor volumetry. Once further optimized, it could be a helpful tool for tumor response assessment in rectal cancer.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Uncertainty-aware particle segmentation for electron microscopy at varied length scales

Electron microscopy is indispensable for examining the morphology and composition of solid materials at the sub-micron scale. To study the powder samples that are widely used in materials development, scanning electron microscopes (SEMs) are increasingly used at the laboratory scale to generate large datasets with hundreds of images. Parsing these images to identify distinct particles and determine their morphology requires careful analysis, and automating this process remains challenging. In this work, we enhance the Mask R-CNN architecture to develop a method for automated segmentation of particles in SEM images. We address several challenges inherent to measurements, such as image blur and particle agglomeration. Moreover, our method accounts for prediction uncertainty when such issues prevent accurate segmentation of a particle. Recognizing that disparate length scales are often present in large datasets, we use this framework to create two models that are separately trained to handle images obtained at low or high magnification. By testing these models on a variety of inorganic samples, our approach to particle segmentation surpasses an established automated segmentation method and yields comparable results to the predictions of three domain experts, revealing comparable accuracy while requiring a fraction of the time. These findings highlight the potential of deep learning in advancing autonomous workflows for materials characterization.

36 MATERIALS SCIENCE↗

Understanding the Influence of Receptive Field and Network Complexity in Neural Network-Guided TEM Image Analysis

Abstract Trained neural networks are promising tools to analyze the ever-increasing amount of scientific image data, but it is unclear how to best customize these networks for the unique features in transmission electron micrographs. Here, we systematically examine how neural network architecture choices affect how neural networks segment, or pixel-wise separate, crystalline nanoparticles from amorphous background in transmission electron microscopy (TEM) images. We focus on decoupling the influence of receptive field, or the area of the input image that contributes to the output decision, from network complexity, which dictates the number of trainable parameters. For low-resolution TEM images which rely on amplitude contrast to distinguish nanoparticles from background, we find that the receptive field does not significantly influence segmentation performance. On the other hand, for high-resolution TEM images which rely on both amplitude and phase-contrast changes to identify nanoparticles, receptive field is an important parameter for increased performance, especially in images with minimal amplitude contrast. Rather than depending on atom or nanoparticle size, the ideal receptive field seems to be inversely correlated to the degree of nanoparticle contrast in the image. Our results provide insight and guidance as to how to adapt neural networks for applications with TEM datasets.

42 ENGINEERING↗

Open Data and Deep Semantic Segmentation for Automated Extraction of Building Footprints

Advances in machine learning and computer vision, combined with increased access to unstructured data (e.g., images and text), have created an opportunity for automated extraction of building characteristics, cost-effectively, and at scale. These characteristics are relevant to a variety of urban and energy applications, yet are time consuming and costly to acquire with today’s manual methods. Several recent research studies have shown that in comparison to more traditional methods that are based on features engineering approach, an end-to-end learning approach based on deep learning algorithms significantly improved the accuracy of automatic building footprint extraction from remote sensing images. However, these studies used limited benchmark datasets that have been carefully curated and labeled. How the accuracy of these deep learning-based approach holds when using less curated training data has not received enough attention. The aim of this work is to leverage the openly available data to automatically generate a larger training dataset with more variability in term of regions and type of cities, which can be used to build more accurate deep learning models. In contrast to most benchmark datasets, the gathered data have not been manually curated. Thus, the training dataset is not perfectly clean in terms of remote sensing images exactly matching the ground truth building’s foot-print. A workflow that includes data pre-processing, deep learning semantic segmentation modeling, and results post-processing is introduced and applied to a dataset that include remote sensing images from 15 cities and five counties from various region of the USA, which include 8,607,677 buildings. The accuracy of the proposed approach was measured on an out of sample testing dataset corresponding to 364,000 buildings from three USA cities. The results favorably compared to those obtained from Microsoft’s recently released US building footprint dataset.

97 MATHEMATICS AND COMPUTING↗

SU-E-J-67: Evaluation of Adaptive MLC Morphing for Online Correction of Prostate Cancer Radiotherapy

Purpose: Online adaptive MLC morphing is desirable over translational couch shifts to accommodate target position as well as anatomic changes. A reliable method of adaptive MLC segment to target during prostate cancer IMRT treatment is proposed and evaluated by comparison with daily online-image guidance (IGRT) correction and online-IMRT planning. Methods: The MLC adaptive algorithm involves following steps; move the MLC segments according to target translational shifts, and then morph the segment shape to maintain the spatial relationship between the planning-target contour and MLC segment. Efficacy of this method was evaluated retrospectively using daily-CBCT images on seven prostate patients treated with seven-beam IMRT treatment to deliver 64Gy in 20 fractions. Daily modification was simulated with three approaches; daily-IGRT correction based on implanted radio-markers, adaptive MLC morphing, and online-IMRT planning, with no-residual variation. The selected dosimetric endpoints and nEUD (normalized equivalent uniform dose to online-IMRT planning) of each organ of interest were determined for evaluation and comparison. Results: For target(prostate), bladder and rectal-wall, the mean±sd of nEUD were 97.6%+3.2%, 103.9%±4.9% and 97.4%±1.1% for daily-IGRT correction; and 100.2%+0.2%, 108.9%±5.1% and 99.8%±1.2% for adaptive MLC morphing, respectively. For daily-IGRT correction, adaptive MLC morphing and online-IMRT planning, target D99 was <95% of the prescription dose in 30%, 0% and 0% of 140 fractions, respectively. For the rectal-wall, D5 exceeded 105% of the planned-D5 in 2.8%, 11.4% and 0% of 140 fractions, respectively. For the bladder, Dmax exceeded 105% of the planned-D5 in 2.8%, 5.6% and 0% of 140 fractions, respectively. D30 of bladder and rectal-wall were well within the planned-D30 for all three approaches. Conclusion: The proposed method of adaptive MLC morphing can be beneficial for the prostate patient population with large deformation and rotation. It is superior to the daily-IGRT correction, and comparable to the online-IMRT planning for dose to the target and rectal-wall.

60 APPLIED LIFE SCIENCES↗

NanoPSD: A software for automatic detection of Nano-Particle Shape Distribution in electron microscopy images

Accurate quantification of the size and morphology of nanoparticles from electron microscopy (EM) images is essential to understand growth mechanisms, surface reactivity, and functional behavior in nanoscale materials. Manual analysis remains slow, subjective, and difficult to reproduce in large datasets. We introduce NanoPSD (Nano-Particle Shape Distribution), an open-source and fully automated framework for quantitative particle detection and morphology analysis from EM images. NanoPSD integrates adaptive contrast enhancement, polarity-agnostic scale-bar detection, Optical Character Recognition (OCR)-based calibration, and classical segmentation via Otsu thresholding with morphological refinement. Particle contours are used to extract geometric descriptors, including equivalent circular diameter, aspect ratio, circularity, and solidity, enabling automated classification into spherical, rod-like, and aggregate morphologies. The framework supports both single-image and batch processing, generating publication-quality visualizations, LaTeX-ready tables, and structured comma-separated values (CSV) datasets. As a demonstration, we applied NanoPSD to plasma-synthesized nanoparticle samples diagnosed via transmission electron microscopy (TEM). The code produced statistically robust size and morphology distributions spanning a few to tens of nanometers with minimal user supervision. The pipeline demonstrates high reproducibility and scalability, processing large image collections with consistent calibration and output formatting. Its modular design enables seamless integration of future deep-learning-based segmentation models, providing a pathway toward intelligent, data-driven electron microscopy analysis.

36 MATERIALS SCIENCE↗

Leveraging unlabeled SEM datasets with self-supervised learning for enhanced particle segmentation

Scanning Electron Microscopes (SEMs) are widely used in experimental science laboratories, often requiring cumbersome and repetitive user analysis. Automating SEM image analysis processes is highly desirable to address this challenge. In particle sample analysis, Machine Learning (ML) has emerged as the most effective approach for particle segmentation. However, the time-intensive process of manually annotating thousands of SEM images limits the applicability of supervised learning approaches. Self-Supervised Learning (SSL) offers a promising alternative by enabling knowledge extraction from raw, unlabeled data. This study presents a framework for evaluating SSL techniques in SEM image analysis, focusing on novel methods leveraging the ConvNeXtV2 architecture for particle detection. A dataset comprising 25,000 SEM images is curated to benchmark these proposed SSL methods. The results demonstrate that ConvNeXtV2 models, with varying parameter counts, consistently outperform other techniques in particle detection across different length scales, achieving up to a 34% reduction in relative error compared to established SSL methods. Furthermore, an ablation study explores the relationship between dataset size and SSL performance, providing actionable insights for practitioners regarding model selection and resource efficiency. This research advances the integration of SSL into autonomous analysis pipelines and supports its application in accelerating materials science discovery.

Rettenberger, Luca↗

SU-F-T-41: 3D MTP-TRUS for Prostate Implant

Purpose: Prostate brachytherapy is an effective treatment for early prostate cancer. The current prostate implant is limited to using 2D transrectal ultrassound (TRUS) or machenical motor driven 2D array either in the end or on the side. Real-time 3D images can improve the accuracy of the guidance of prostate implant. The concept of our system is to allow realtime full visualization of the entire prostate with the multiple transverse scan. Methods: The prototype of 3D Multiple-Transverse-Plane Transrectal Ultrasound probe (MTP-TRUS) has been designed by us and manufactured by Blatek inc. It has 7 convex linear arrays and each array has 96 elements. It is connected to cQuest Fire bird research system (Cephasonics inc.) which is a flexible and configurable ultrasound-development platform. The size of cQuest Firebird system is compact and supports the real-time wireless image transferring. A relay based mux board is designed for the cQuest Firebird system to be able to connect 672 elements. Results: The center frequency of probe is 6MHz±10%. The diameter of probe is 3cm and the length is 20cm. The element pitch is 0.205 mm. Array focus is 30mm and spacing 1.6cm. The beam data for each array was measured and met our expectation. The interface board of MTP-TURS is made and able to connect to cQuest Firebird system. The image display interface is still under the development. Our real-time needle tracking algorithm will be implemented too. Conclusion: Our MTP-TRUS system for prostate implant will be able to acquire real-time 3D images of prostate and do the real-time needle segmentation and tracking. The system is compact and have wireless function.

60 APPLIED LIFE SCIENCES↗

A deep learning model for automatic analysis of cavities in irradiated materials

Transmission electron microscopy (TEM) is a commonly used technique in materials science for defect investigation. Quantitative analysis of defects is important for understanding the properties of a material, but manual analysis of TEM micrographs can be time-consuming and prone to error, especially when the defects have irregular shapes rather than spherical shapes. Many existing methods or deep learning models do not handle a wide range of sizes for the same object type within a single image. In this work, we present a framework that enables users to train an instance segmentation model called Mask R- CNN on any microstructure dataset, perform multi-detection on the same image at different scales, and obtain properties (e.g., size, area) of the objects based on the desired shape (e.g., circle, ellipse, rectangle). Additionally, we have developed a parallel detection module that uses multiple GPUs to increase the efficiency of the object detection process. We demonstrate the capabilities of our framework using a set of TEM images of cavities with different shapes, size distributions, and background contrasts. Finally, we show that the performance of our model in terms of density, size, and swelling of the cavities is comparable to the human average and that our model achieves the highest recall value compared to existing methods due to the use of image multi-rescaling.

36 MATERIALS SCIENCE↗

TH-CD-207B-06: Swank Factor of Segmented Scintillators in Multi-Slice CT Detectors: Pulse Height Spectra and Light Escape

Purpose: Pulse height spectra (PHS) have been used to determine the Swank factor of a scintillator by measuring fluctuations in its light output per x-ray interaction. The Swank factor and x-ray quantum efficiency of a scintillator define the upper limit to its imaging performance, i.e. DQE(0). The Swank factor below the K-edge is dominated by optical properties, i.e. variations in light escape efficiency from different depths of interaction, denoted e(z). These variations can be optimized to improve tradeoffs in x-ray absorption, light yield, and spatial resolution. This work develops a quantitative model for interpreting measured PHS, and estimating e(z) on an absolute scale. The method is used to investigate segmented ceramic GOS scintillators used in multi-slice CT detectors. Methods: PHS of a ceramic GOS plate (1 mm thickness) and segmented GOS array (1.4 mm thick) were measured at 46 keV. Signal and noise propagation through x-ray conversion gain, light escape, detection by a photomultiplier tube and dynode amplification were modeled using a cascade of stochastic gain stages. PHS were calculated with these expressions and compared to measurements. Light escape parameters were varied until modeled PHS agreed with measurements. The resulting estimates of e(z) were used to calculate PHS without measurement noise to determine the inherent Swank factor. Results: The variation in e(z) was 67.2–89.7% in the plate and 40.2–70.8% in the segmented sample, corresponding to conversion gains of 28.6–38.1 keV{sup −1} and 17.1–30.1 keV{sup −1}, respectively. The inherent Swank factors of the plate and segmented sample were 0.99 and 0.95, respectively. Conclusion: The high light escape efficiency in the ceramic GOS samples yields high Swank factors and DQE(0) in CT applications. The PHS model allows the intrinsic optical properties of scintillators to be deduced from PHS measurements, thus it provides new insights for evaluating the imaging performance of segmented ceramic GOS scintillators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗