Search NASA⌕ Search

SEARCH · Search NASA

Results for “image based modeling”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2016

TU-AB-202-05: GPU-Based 4D Deformable Image Registration Using Adaptive Tetrahedral Mesh Modeling

Purpose: Deformable image registration (DIR) has been employed today as an automated and effective segmentation method to transfer tumor or organ contours from the planning image to daily images, instead of manual segmentation. However, the computational time and accuracy of current DIR approaches are still insufficient for online adaptive radiation therapy (ART), which requires real-time and high-quality image segmentation, especially in a large datasets of 4D-CT images. The objective of this work is to propose a new DIR algorithm, with fast computational speed and high accuracy, by using adaptive feature-based tetrahedral meshing and GPU-based parallelization. Methods: The first step is to generate the adaptive tetrahedral mesh based on the image features of a reference phase of 4D-CT, so that the deformation can be well captured and accurately diffused from the mesh vertices to voxels of the image volume. Subsequently, the deformation vector fields (DVF) and other phases of 4D-CT can be obtained by matching each phase of the target 4D-CT images with the corresponding deformed reference phase. The proposed 4D DIR method is implemented on GPU, resulting in significantly increasing the computational efficiency due to its parallel computing ability. Results: A 4D NCAT digital phantom was used to test the efficiency and accuracy of our method. Both the image and DVF results show that the fine structures and shapes of lung are well preserved, and the tumor position is well captured, i.e., 3D distance error is 1.14 mm. Compared to the previous voxel-based CPU implementation of DIR, such as demons, the proposed method is about 160x faster for registering a 10-phase 4D-CT with a phase dimension of 256×256×150. Conclusion: The proposed 4D DIR method uses feature-based mesh and GPU-based parallelism, which demonstrates the capability to compute both high-quality image and motion results, with significant improvement on the computational speed.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

Sci-Thur AM: YIS – 01: New technologies for astatine-211 targeted alpha therapy research

Purpose: The short-range, densely ionizing α-particles emitted by {sup 211}At (t{sub 1/2}=7.2h) are well suited for the treatment of diffuse microscopic disease, using cancer targeting biomolecules. {sup 211}At availability is limited by the rarity of α-cyclotrons required for standard production. Image-based dosimetry is also limited for {sup 211}At, which emits low intensity X-rays. Our goal was to leverage state-of-the-art infrastructure at TRIUMF to produce and evaluate two related isotopes, {sup 211}Rn (t{sub 1/2}=14.6h, 73% decay to {sup 211}At) as a generator for {sup 211}At, and {sup 209}At (t{sub 1/2}=5.4h, X-ray/gamma-ray emitter) as a novel 211At surrogate for preclinical imaging studies. Methods: Produced by spallation of uranium with 480 MeV protons, mass separated ion beams of short-lived francium isotopes were implanted into NaCl targets where {sup 211}Rn or {sup 209}At were produced by radioactive decay, in situ. {sup 211}Rn was transferred to dodecane from which {sup 211}At was efficiently extracted and evaluated for clinical applicability. High energy SPECT/CT was evaluated for measuring {sup 209}At activity distributions in mice and phantoms. Results: Our small scale {sup 211}Rn/{sup 211}At generator system provided high purity {sup 211}At samples. The methods are immediately scalable to the level of radioactivity required for in vivo experiments with {sup 211}At. {sup 209}At-based high energy SPECT imaging was determined suitable for pursuing image-based dosimetry in mouse tumour models. In the future, we will utilize quantitative {sup 209}At-SPECT for image-based dose calculations. Conclusion: These early studies provided a foundation for future endeavours with {sup 211}At-based α-therapy. Canada is now significantly closer to clinical targeted α-therapy of cancer.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Data‐Efficient Generation of Synthetic Microstructures of Polymer‐Bonded Energetic Material With Fine‐Tuned Stable Diffusion

Among current deep learning approaches for synthetic image generation, diffusion-based models stand out in terms of algorithmic stability and ability to retain high-fidelity image features with detailed resolution. Here, in this work, we employ Dreambooth, a method for fine-tuning Stable Diffusion, on X-ray CT images of microstructure of the polymer-bonded form (PBX) of a commonly used high explosive, Pentaerythritol tetranitrate (PETN), which yields generative models for creating synthetic PBX images. The models developed here represent five classes (or ‘lots’) of microstructures and demonstrate successful generation of images of each class with high fidelity, as verified by computed classification accuracy of ∼ 94% or higher. Data augmentation afforded by such image synthesis can be used to more reliably decipher underlying statistics, build processing-structure correlations, recognize off-normal structural anomalies, and identify age-related changes. Ideas related to converting image data into appropriate density mapping and performing mesoscale simulation or surrogate modeling of detonation are also discussed.

Dreambooth↗
NASA NTRS1993

Validation of Atmospheric Correction of Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) Radiance Data Based on Radiative Transfer Modeling

An evaluation of atmospheric correction of AVIRIS data using radiative transfer codes LOWTRAN7 and MODTRAN is presented. The algorithm employed is based on a simple model of radiance L at each wavelength at the sensor that can be written approximately LAV=Lp+Tp, where subscript AV referes to AVIRIS, Lp is the path radiance and Tp is the diffuse + direct transmitted radiance of the atmosphere at AVIRIS.

Infrared Mapping↗
NASA NTRS1990

A microlensing model for QSO 2237 + 0305

Models of microlensing are presented for the four images of QSO 2237 + 0305, with the surface mass density and shear for each image based on the macrolensing model developed by Schneider et al. (1988). The computations were done with a new code that makes use of the hierarchical tree method. The high efficiency of this approach makes it possible to include up to 60,000 lensing stars with different masses. Examples are given of amplification maps, light curves, correlation functions, and amplification probabilities. All these are very strongly affected by the shear due to macrolensing. The observed changes in the luminosity of the four images of QSO 2237 + 0305 are most likely induced by microlensing.

Wambsganss, J.↗
DOE OSTI2021

Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data

Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.

13 HYDRO ENERGY↗
NASA NTRS1993

Sensor fusion display evaluation using information integration models in enhanced/synthetic vision applications

Based on existing integration models in the psychological literature, an evaluation framework is developed to assess sensor fusion displays as might be implemented in an enhanced/synthetic vision system. The proposed evaluation framework for evaluating the operator's ability to use such systems is a normative approach: The pilot's performance with the sensor fusion image is compared to models' predictions based on the pilot's performance when viewing the original component sensor images prior to fusion. This allows for the determination as to when a sensor fusion system leads to: poorer performance than one of the original sensor displays, clearly an undesirable system in which the fused sensor system causes some distortion or interference; better performance than with either single sensor system alone, but at a sub-optimal level compared to model predictions; optimal performance compared to model predictions; or, super-optimal performance, which may occur if the operator were able to use some highly diagnostic 'emergent features' in the sensor fusion display, which were unavailable in the original sensor displays.

Foyle, David C.↗
DOE OSTI2026

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗
DOE OSTI2016

TH-CD-207A-08: Simulated Real-Time Image Guidance for Lung SBRT Patients Using Scatter Imaging

Purpose: To develop a comprehensive Monte Carlo-based model for the acquisition of scatter images of patient anatomy in real-time, during lung SBRT treatment. Methods: During SBRT treatment, images of patient anatomy can be acquired from scattered radiation. To rigorously examine the utility of scatter images for image guidance, a model is developed using MCNP code to simulate scatter images of phantoms and lung cancer patients. The model is validated by comparing experimental and simulated images of phantoms of different complexity. The differentiation between tissue types is investigated by imaging objects of known compositions (water, lung, and bone equivalent). A lung tumor phantom, simulating materials and geometry encountered during lung SBRT treatments, is used to investigate image noise properties for various quantities of delivered radiation (monitor units(MU)). Patient scatter images are simulated using the validated simulation model. 4DCT patient data is converted to an MCNP input geometry accounting for different tissue composition and densities. Lung tumor phantom images acquired with decreasing imaging time (decreasing MU) are used to model the expected noise amplitude in patient scatter images, producing realistic simulated patient scatter images with varying temporal resolution. Results: Image intensity in simulated and experimental scatter images of tissue equivalent objects (water, lung, bone) match within the uncertainty (∼3%). Lung tumor phantom images agree as well. Specifically, tumor-to-lung contrast matches within the uncertainty. The addition of random noise approximating quantum noise in experimental images to simulated patient images shows that scatter images of lung tumors can provide images in as fast as 0.5 seconds with CNR∼2.7. Conclusions: A scatter imaging simulation model is developed and validated using experimental phantom scatter images. Following validation, lung cancer patient scatter images are simulated. These simulated patient images demonstrate the clinical utility of scatter imaging for real-time tumor tracking during lung SBRT.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Mimicking of corruption in images

Methods and systems are provided to generate an uncorrupted version of an image given an observed image that is a corrupted version of the image. In some embodiments, a corruption mimicking (“CM”) system iteratively trains a corruption mimicking network (“CMN”) to generate corrupted images given modeled images, updates latent vectors based on differences between the corrupted images and observed images, and applies a generator to the latent vectors to generate modeled images. The training, updating, and applying are performed until modeled images that are input to the CMN result in corrupted images that approximate the observed images. Because the CMN is trained to mimic the corruption of the observed images, the final modeled images represented the uncorrupted version of the observed images.

Anirudh, Rushil↗
DOE OSTI2015

Lung motion estimation using dynamic point shifting: An innovative model based on a robust point matching algorithm

Purpose: Image-guided radiotherapy is an advanced 4D radiotherapy technique that has been developed in recent years. However, respiratory motion causes significant uncertainties in image-guided radiotherapy procedures. To address these issues, an innovative lung motion estimation model based on a robust point matching is proposed in this paper. Methods: An innovative robust point matching algorithm using dynamic point shifting is proposed to estimate patient-specific lung motion during free breathing from 4D computed tomography data. The correspondence of the landmark points is determined from the Euclidean distance between the landmark points and the similarity between the local images that are centered at points at the same time. To ensure that the points in the source image correspond to the points in the target image during other phases, the virtual target points are first created and shifted based on the similarity between the local image centered at the source point and the local image centered at the virtual target point. Second, the target points are shifted by the constrained inverse function mapping the target points to the virtual target points. The source point set and shifted target point set are used to estimate the transformation function between the source image and target image. Results: The performances of the authors’ method are evaluated on two publicly available DIR-lab and POPI-model lung datasets. For computing target registration errors on 750 landmark points in six phases of the DIR-lab dataset and 37 landmark points in ten phases of the POPI-model dataset, the mean and standard deviation by the authors’ method are 1.11 and 1.11 mm, but they are 2.33 and 2.32 mm without considering image intensity, and 1.17 and 1.19 mm with sliding conditions. For the two phases of maximum inhalation and maximum exhalation in the DIR-lab dataset with 300 landmark points of each case, the mean and standard deviation of target registration errors on the 3000 landmark points of ten cases by the authors’ method are 1.21 and 1.04 mm. In the EMPIRE10 lung registration challenge, the authors’ method ranks 24 of 39. According to the index of the maximum shear stretch, the authors’ method is also efficient to describe the discontinuous motion at the lung boundaries. Conclusions: By establishing the correspondence of the landmark points in the source phase and the other target phases combining shape matching and image intensity matching together, the mismatching issue in the robust point matching algorithm is adequately addressed. The target registration errors are statistically reduced by shifting the virtual target points and target points. The authors’ method with consideration of sliding conditions can effectively estimate the discontinuous motion, and the estimated motion is natural. The primary limitation of the proposed method is that the temporal constraints of the trajectories of voxels are not introduced into the motion model. However, the proposed method provides satisfactory motion information, which results in precise tumor coverage by the radiation dose during radiotherapy.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

A Monte Carlo calculation model of electronic portal imaging device for transit dosimetry through heterogeneous media

Purpose: To develop and evaluate a fast Monte Carlo (MC) dose calculation model of electronic portal imaging device (EPID) based on its effective atomic number modeling in the XVMC code. Methods: A previously developed EPID model, based on the XVMC code by density scaling of EPID structures, was modified by additionally considering effective atomic number (Z{sub eff}) of each structure and adopting a phase space file from the EGSnrc code. The model was tested under various homogeneous and heterogeneous phantoms and field sizes by comparing the calculations in the model with measurements in EPID. In order to better evaluate the model, the performance of the XVMC code was separately tested by comparing calculated dose to water with ion chamber (IC) array measurement in the plane of EPID. Results: In the EPID plane, calculated dose to water by the code showed agreement with IC measurements within 1.8%. The difference was averaged across the in-field regions of the acquired profiles for all field sizes and phantoms. The maximum point difference was 2.8%, affected by proximity of the maximum points to penumbra and MC noise. The EPID model showed agreement with measured EPID images within 1.3%. The maximum point difference was 1.9%. The difference dropped from the higher value of the code by employing the calibration that is dependent on field sizes and thicknesses for the conversion of calculated images to measured images. Thanks to the Z{sub eff} correction, the EPID model showed a linear trend of the calibration factors unlike those of the density-only-scaled model. The phase space file from the EGSnrc code sharpened penumbra profiles significantly, improving agreement of calculated profiles with measured profiles. Conclusions: Demonstrating high accuracy, the EPID model with the associated calibration system may be used for in vivo dosimetry of radiation therapy. Through this study, a MC model of EPID has been developed, and their performance has been rigorously investigated for transit dosimetry.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Foundation Models for Zero-Shot Segmentation of Scientific Images without AI-Ready Data

Zero-shot and prompt-based models have excelled at visual reasoning tasks by leveraging large-scale natural image corpora, but they often fail on sparse and domain-specific scientific image data. We introduce Zenesis, a no-code interactive computer vision platform designed to reduce data readiness bottlenecks in scientific imaging workflows. Zenesis integrates lightweight multimodal adaptation for zero-shot inference on raw scientific data, human-in-the-loop refinement, and heuristic-based temporal enhancement. We validate our approach on Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) datasets of catalyst-loaded membranes. Zenesis outperforms baselines, achieving an average accuracy of 0.947, Intersection over Union (IoU) of 0.858, and Dice score of 0.923 on amorphous catalyst samples; and 0.987 accuracy, 0.857 IoU, and 0.923 Dice on crystalline samples. These results represent a significant performance gain over conventional methods such as Otsu thresholding and standalone models like the Segment Anything Model (SAM). Zenesis enables effective image segmentation in domains where annotated datasets are limited, offering a scalable solution for scientific discovery.

Mukherjee, Shubhabrata↗
DOE OSTI2024

Score-based diffusion models for generating liquid argon time projection chamber images

For the first time, we show high-fidelity generation of Liquid Argon Time Projection Chamber (LArTPC-like) data using a generative neural network. This demonstrates that methods developed for natural images do transfer to LArTPC-produced images, which, in contrast to natural images, are globally sparse but locally dense. We present the score-based diffusion method employed. We evaluate the fidelity of the generated images using several quality metrics, including modified measures used to evaluate natural images, comparisons between high-dimensional distributions, and comparisons relevant to LArTPC experiments. Published by the American Physical Society 2024

Astronomy & Astrophysics↗