SEARCH · Engineering Papers
Results for “Image reconstruction”
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.
Live cell imaging of cellular dynamics in poplar wood using computational cannula microscopy
This study presents significant advancements in computational cannula microscopy for live imaging of cellular dynamics in poplar wood tissues. Leveraging machine-learning models such as pix2pix for image reconstruction, we achieved high-resolution imaging with a field of view of 55µm using a 50µm-core diameter probe. Our method allows for real-time image reconstruction at 0.29 s per frame with a mean absolute error of 0.07. We successfully captured cellular-level dynamics in vivo , demonstrating morphological changes at resolutions as small as 3µm. We implemented two types of probabilistic neural network models to quantify confidence levels in the reconstructed images. This approach facilitates context-aware, human-in-the-loop analysis, which is crucial for in vivo imaging where ground-truth data is unavailable. Using this approach we demonstrated deep in vivo computational imaging of living plant tissue with high confidence (disagreement score ⪅0.2). This work addresses the challenges of imaging live plant tissues, offering a practical and minimally invasive tool for plant biologists.
Quantification and visualization of uncertainties in reconstructed penumbral images of implosions at Omega
Penumbral imaging is a technique used in plasma diagnostics in which a radiation source shines through one or more large apertures onto a detector. To interpret a penumbral image, one must reconstruct it to recover the original source. The inferred source always has some error due to noise in the image and uncertainty in the instrument geometry. Interpreting the inferred source thus requires quantification of that inference’s uncertainty. Markov chain Monte Carlo algorithms have been used to quantify uncertainty for similar problems but have never been used for the inference of the shape of an image. Because of this, there are no commonly accepted ways of visualizing uncertainty in two-dimensional data. This paper demonstrates the application of the Hamiltonian Monte Carlo algorithm to the reconstruction of penumbral images of fusion implosions and presents ways to visualize the uncertainty in the reconstructed source. This methodology enables more rigorous analysis of penumbral images than has been done in the past.
Real-time High-resolution X-Ray Computed Tomography
Computed Tomography (CT) serves as a key imaging technology that relies on computationally intensive filtering and back-projection algorithms for 3D image reconstruction. While conventional high-resolution image reconstruction (> 2K3) solutions provide quick results, they typically treat reconstruction as an offline workload to be performed remotely on large-scale HPC systems. The growing demand for post-construction AI-driven analytics and the need for real-time adjustments call for high-resolution reconstruction solutions that are feasible on local computing resources, i.e. a multi-GPU server at most. In this paper, we propose a novel approach that utilizes Tensor Cores to optimize image reconstruction without sacrificing precision. We also introduce a framework designed to enable real-time execution of end-to-end distributed image reconstruction in a multi-GPU environment. Evaluations conducted on a single Nvidia A100 and H100 GPU show performance improvements of 1.91 × and 2.15 × compared to highly optimized production libraries. Furthermore, our framework, when deployed on 8-card Nvidia A100 GPU system, demonstrates the ability to reconstruct real-world datasets into 20483 volumes (32 GB) in slightly more than one minute and 40963 volumes (256 GB) in 7 minutes.
Exploiting voxel-sparsity for bone imaging with sparse-view cone-beam computed tomography
An optimization-based image reconstruction frame work is developed specifically for bone imaging. This framework exploits voxel-sparsity by use of ℓ 1 -norm image regularization and it enables image reconstruction from sparse-view cone-beam computed tomography (CBCT) acquisition. The effectiveness of the voxel-sparsity regularization is enhanced by using a blurred image representation. Ramp-filtering is included in the data discrepancy term and it has the effect of acting as a preconditioner, reducing the necessary number of iterations. The bone image reconstruction framework is demonstrated on CBCT data taken from an equine metacarpal condyle specimen.
3D Quantification of Pore Networks and Anthropogenic Carbon Mineralization in Stacked Basalt Reservoirs
Basalt formations are promising candidates for the geologic storage of anthropogenic CO 2 due to their storage capacity, porosity, permeability, and reactive geochemical trapping ability. The Wallula Basalt Carbon Storage Pilot Project demonstrated that supercritical CO 2 injected into >800 m deep Columbia River Basalt Group stacked reservoir flow tops mineralizes to ankerite-siderite-aragonite on month-year timescales, with 60% of the 977 metric tonnes of CO 2 converted within two years. The potential impacts of mineral precipitation and consequent changes on rock porosity, pore structure, pore size, and pore size distributions have likely been underestimated hitherto. Herein, we address these knowledge gaps using X-ray Micro Computed Tomography (XMT) to evaluate the pore network architecture of sidewall cores recovered two years after CO 2 injection. In the present study, we performed a detailed quantitative analysis of the CO 2 -reacted basalt cores by XMT imaging. Reconstructed 3D images were analyzed to study the distribution and volumetric details of porosity and carbonate nodules in the cores along with the various other phases, providing insight into paragenesis and carbonate growth mechanisms, including mineralogic/chemical zonation. Finally, these findings are being used to parametrize multiphase reactive transport models to predict the fate and transport of subsurface CO 2 , enabling scale-up to commercial-scale geologic carbon storage in basalts and other reactive mafic-ultramafic formations.
Boosting Noise2Inverse via enhanced model selection for denoising computed tomography data
Synchrotron-based x-ray tomographic imaging enables the examination of the internal structure of materials at high spatial and temporal resolution. Experimental constraints can impose dose and time limits on the measurements, introducing a higher level of noise and artifacts in the reconstructed images. Deep learning has emerged as a powerful tool to remove noise from reconstructed images. Recently, the Noise2Inverse method was designed specifically for denoising reconstructed images without requiring paired noisy and clean images. This method creates multiple statistically independent reconstructions used to pair the data in which training involves transforming one reconstruction into the other, and vice versa. Originally designed to be used after a fixed number of epochs, we see in practice that this approach may not produce the optimal model and may unnecessarily waste computational resources. Therefore, we propose an alternative method of identifying the best model during training that aligns with the Noise2Inverse method. During validation, we compare the model output of the multiple reconstructions among each other. We hypothesize that the best model is the one that produces images with the highest similarity, implying a convergence in the predicted material properties and absorption values. To compare model outputs, we consider the absolute error, square error, structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and cosine similarity. We evaluate our method on two simulated tomography datasets and two, real-world, low-contrast, high-energy x-ray tomography datasets. We show our approach is more effective at determining the best model, up to an increase of 12.50% and 12.53% in SSIM and PSNR, respectively, while only requiring a fifth of the training time compared to the original approach.
Evaluating Machine Learning-Based MRI Reconstruction Using Digital Image Quality Phantoms
Quantitative and objective evaluation tools are essential for assessing the performance of machine learning (ML)-based magnetic resonance imaging (MRI) reconstruction methods. However, the commonly used fidelity metrics, such as mean squared error (MSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR), often fail to capture fundamental and clinically relevant MR image quality aspects. To address this, we propose evaluation of ML-based MRI reconstruction using digital image quality phantoms and automated evaluation methods. Our phantoms are based upon the American College of Radiology (ACR) large physical phantom but created in k-space to simulate their MR images, and they can vary in object size, signal-to-noise ratio, resolution, and image contrast. Our evaluation pipeline incorporates evaluation metrics of geometric accuracy, intensity uniformity, percentage ghosting, sharpness, signal-to-noise ratio, resolution, and low-contrast detectability. We demonstrate the utility of our proposed pipeline by assessing an example ML-based reconstruction model across various training and testing scenarios. The performance results indicate that training data acquired with a lower undersampling factor and coils of larger anatomical coverage yield a better performing model. The comprehensive and standardized pipeline introduced in this study can help to facilitate a better understanding of the performance and guide future development and advancement of ML-based reconstruction algorithms.
Advancing the Frontiers of Deep Learning for Low-Dose 3D Cone-Beam CT Reconstruction
X-ray computed tomography (CT) is an important noninvasive medical imaging modality for studying the structural details of internal organs. Image reconstruction in CT is an inverse problem of recovering an object's internal structure from the absorption profile of X-ray beams (sinogram) measured using a detector. The classical variational approach for CT reconstruction minimizes an energy functional using an appropriate iterative algorithm. Motivated by the success of deep learning (DL), researchers have begun to leverage training data and enhanced computing capabilities in recent years to produce high-fidelity reconstructed images. Nonetheless, much of the academic research in DL algorithms for CT has focused primarily on the two-dimensional setting (with simplified forward operators and noise model) for proofs-of-concept, and a comprehensive benchmarking of various classical and data-driven CT reconstruction approaches has not beenundertaken. The key objective of our CT reconstruction grand challenge was to promote methodological advancements for both classical and DL-based approaches for clinical CT with a reasonably accurately simulated 3D CT forward operator and noise model. We have utilized the publicly available LIDC-IDRI dataset and simulated sinograms and FDK images corresponding to two dose levels (clinical- and low-dose, constituting two tracks of the challenge) starting from the normal-dose images as the ground truth. In this paper, we summarize the motivation, context, and results of our challenge, and highlight the future research directions in DL for clinical CT.
Scalable FBP decomposition for cone-beam CT reconstruction
Filtered Back-Projection (FBP) is a fundamental compute intense algorithm used in tomographic image reconstruction. Cone-Beam Computed Tomography (CBCT) devices use a cone-shaped X-ray beam, in comparison to the parallel beam used in older CT generations. Distributed image reconstruction of cone-beam datasets typically relies on dividing batches of images into different nodes. This simple input decomposition, however, introduces limits on input/output sizes and scalability.We propose a novel decomposition scheme and reconstruction algorithm for distributed FPB. This scheme enables arbitrarily large input/output sizes, eliminates the redundancy arising in the end-to-end pipeline and improves the scalability by replacing two communication collectives with only one segmented reduction. Finally, we implement the proposed decomposition scheme in a framework that is useful for all current-generation CT devices (7th gen). In our experiments using up to 1024 GPUs, our framework can construct 40963 volumes, for real-world datasets, in under 16 seconds (including I/O).
AAPM Truth‐based CT (TrueCT) reconstruction grand challenge
Background: This Special Report summarizes the 2022, AAPM grand challenge on Truth-based CT image reconstruction. Purpose: To provide an objective framework for evaluating CT reconstruction methods using virtual imaging resources consisting of a library of simulated CT projection images of a population of human models with various diseases. Methods: Two hundred unique anthropomorphic, computational models were created with varied diseases consisting of 67 emphysema, 67 lung lesions, and 66 liver lesions. The organs were modeled based on clinical CT images of real patients. The emphysematous regions were modeled using segmentations from patient CT cases in the COPDGene Phase I dataset. For the lung and liver lesion cases, 1–6 malignant lesions were created and inserted into the human models, with lesion diameters ranging from 5.6 to 21.9 mm for lung lesions and 3.9 to 14.9 mm for liver lesions. The contrast defined between the liver lesions and liver parenchyma was 82 ± 12 HU, ranging from 50 to 110 HU. Similarly, the contrast between the lung lesions and the lung parenchyma was defined as 781 ± 11 HU, ranging from 725 to 805 HU. For the emphysematous regions, the defined HU values were −950 ± 17 HU ranging from −918 to −979 HU. The developed human models were imaged with a validated CT simulator. The resulting CT sinograms were shared with the participants. The participants reconstructed CT images from the sinograms and sent back their reconstructed images. Further, the reconstructed images were then scored by comparing the results against the corresponding ground truth values. The scores included both task-generic (root mean square error [RMSE] and structural similarity matrix [SSIM]), and task-specific (detectability index [d’] and lesion volume accuracy) metrics. For the cases with multiple lesions, the measured metric was averaged across all the lesions. To combine the metrics with each other, each metric was normalized to a range of 0 to 1 per disease type, with “0” and “1” being the worst and best measured values across all cases of the disease type for all received reconstructions. Results: The True-CT challenge attracted 52 participants, out of which 5 successfully completed the challenge and submitted the requested 200 reconstructions. Across all participants and disease types, SSIM absolute values ranged from 0.22 to 0.90, RMSE from 77.6 to 490.5 HU, d’ from 0.1 to 64.6, and volume accuracy ranged from 1.2 to 753.1 mm3. The overall scores demonstrated that participant “A” had the best performance in all categories, except for the metrics of d’ for lung lesions and RMSE for liver lesions. Participant “A” had an average normalized score of 0.41 ± 0.22, 0.48 ± 0.32, and 0.42 ± 0.33 for the emphysema, lung lesion, and liver lesion cases, respectively. Conclusions: The True-CT challenge successfully enabled objective assessment of CT reconstructions with the unique advantage of access to a diverse population of diseased human models with known ground truth. This study highlights the significant potential of virtual imaging trials in objective assessment of medical imaging technologies.
Quantification of LEU Holdup using gamma ray imaging and inverse transport solver
Holdup is the residual amount of special nuclear material (SNM) remaining in a processing facility after the bulk materials have been cleaned out. In commercial uranium processing facilities, quantification of holdup is a major challenge because of the highly variable shapes and sizes of the deposits. Any method that attempts to generalize and calibrate deposit shapes in order to quantify holdup will be prone to high uncertainties. Uncertainties on the order of ±50% are typical in holdup results. In international safeguards applications, a ±50% uncertainty can result in a large amount of material unaccounted for (MUF) thereby increasing the difficulty of detecting material diversion and facility misuse. An imaging-based methodology has been developed with the objective of significantly reducing this uncertainty by using the true deposit shape, instead of relying on oversimplified geometric assumptions. The project is a collaboration between ORNL, Y-12, and the University of Tennessee, Knoxville, TN. Uranium sources of known masses were measured using the Germanium Gamma-ray Imager (GeGI), a high-resolution imaging spectrometer, creating a pixelated map for each spectral bin. Two different gamma imaging methods are employed in this work: coded aperture imaging and Compton imaging. A validated MonteCarlo model of the detector has been developed using the GEANT4 code for determining the intrinsic response of the detector, its enclosure, and the coded aperture mask. An inverse transport solver based on the Markov Chain Monte-Carlo approach known as Differential Evolution Adaptive Metropolis (DREAM) is employed to use the measurement data from the image pixels (coded aperture or Compton) to solve for the mass of 235 U in the deposit. A reliable method based on the DREAM solver has been developed to flag the infinite thickness condition of a uranium deposit. The project team is working towards improving the image reconstruction for Compton imaging so that a better localization of the source can be achieved. Besides treating the coded aperture and Compton imaging methods independently, the project is also evaluating a combined method that uses the Compton scatter data from a coded aperture measurement. GEANT4 simulations are being performed to evaluate the combined approach. The impact on the DREAM optimization as the source thickness progressively approaches infinite thickness is being evaluated. A number of uranium sources available at ORNL have been measured, and the DREAM results have been tested and validated for the coded aperture imaging. A similar effort will be carried out to validate the Compton based method once the development of algorithms for better localization are complete. The imaging based quantification is very amenable to unattended monitoring of holdup accumulation at key measurement points. A proof of concept measurement has been completed to demonstrate this capability The current work used the high energy resolution imager GeGI. However, the approach and methodologies are applicable to other imagers such as the cadmium zin telluride (CZT) based imager manufactured by H3D, Inc.
Closed-Form Approximation of the Total Variation Proximal Operator
Total variation (TV) is a widely used function for regularizing imaging inverse problems that is particularly appropriate for images whose underlying structure is piecewise constant. TV regularized optimization problems are typically solved using proximal methods, but the way in which they are applied is constrained by the absence of a closed-form expression for the proximal operator of the TV function. A closed-form approximation of the TV proximal operator has previously been proposed, but its accuracy was not theoretically explored in detail. Here, we address this gap by making several new theoretical contributions, proving that the approximation leads to a proximal operator of some convex function, it is equivalent to a gradient descent step on a smoothed version of TV, and that its error can be fully characterized and controlled with its scaling parameter. We experimentally validate our theoretical results on image denoising and sparse-view computed tomography (CT) image reconstruction.
Assembly and Initial Testing of the Gamma-Ray Emission Tomography Assessment Prototype for Irradiated Fuel
The following report documents the final development, assembly, and initial testing of the gamma-ray emission tomography assessment system (GRETA-1) for post-irradiation examination of irradiated fuel. It includes descriptions of the system components, including the high-purity germanium gamma-ray detector, the surrounding shield and collimator, the sample scanning hardware, and the control and collection software package. A series of MCNP6 simulations were performed that modeled a fuel rod scan to test image reconstruction algorithms with a complex and understood source distribution. A bench-top scan of isotopic check sources was also performed and analyzed using standard image reconstruction algorithms. The system is currently awaiting deployment at Idaho National Laboratory’s Hot Fuel Examination Facility.
Fused x-ray and fast neutron CT reconstruction for imaging large and dense objects
Megavolt x-ray computed tomography (CT) is a powerful tool for three-dimensional characterization. However, its utility is limited for large objects composed of high-atomic number (Z) materials, where x rays fail to penetrate. Information from fast neutron CT (FNCT) can complement x-ray CT reconstructions since fast neutrons can more readily penetrate high-Z objects. In this work, we demonstrate a method for combining FNCT and x-ray CT data to create a single reconstruction, more accurate than could be achieved with either x rays or fast neutrons alone. The algorithm was tested on an exemplar comprising multiple concentric, nested cylinders of different materials. Simulated and empirical x-ray CT data were acquired for the exemplar using a 9 MV bremsstrahlung spectrum. Additional simulated and empirical FNCT data were acquired using an accelerator based fast neutron source. The FNCT data were used to synthesize x-ray CT data and augment the x-ray CT data missing due to lack of penetration. This approach mitigates artifacts that would otherwise negatively affect the accuracy and resolution of a single-modality reconstructed volume.
Calibration method for a spectral computerized tomography system
A calibration method for an x-ray computerized tomography system and a method of tomographic reconstruction are provided. The calibration method includes steps of measuring at least one point spread function (PSF) at each of a plurality of points, compressing each PSF, and in one or more storing operations, storing the compressed PSFs in a computer-accessible storage medium. The PSF measurements are made in a grid of calibration points in a field of view (FOV) of the system. In the measuring step, an absorber is positioned at each of the calibration points, and an x-ray projection is taken at least once at each of those absorber positions. In the method of tomographic image reconstruction, projection data from an x-ray tomographic projection system are input to an iterative image reconstruction algorithm. The algorithm retrieves and utilizes a priori system information (APSI) The APSI comprises comprising point spread functions (PSFs) of all voxels in a voxelization of the field of view that are compressed in the form of vectors of parameters. For utilization, each retrieved vector of parameters is decompressed so as to generate a discretized PSF.
Fusing Semantic Features with Gaussian Splatting for Enhanced Satellite Image Surface Reconstruction
Explore the source record for details and available documents.
Progress in penumbral image source reconstruction with finite penetrating radiation
Explore the source record for details and available documents.