Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography最新文献

{"title":"A Theoretical Prediction of CT-based Radiomics Feature Variance to Improve the Performance of Classification Models.","authors":"Huay Din, Yijie Yuan, Grace Hyun Kim, Michael McNitt-Gray, J Webster Stayman, Grace J Gang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p><i>Radiomics</i> involves the high-throughput extraction of quantitative image biomarkers for analysis in machine learning models. While this field holds immense potential for personalized medicine, the clinical translation of radiomic models is severely hampered by their intrinsic dependency on image acquisition properties, degrading downstream predictive performance. In this work, we propose a statistical framework to explicitly account for stochastic-based feature uncertainty. We derive an analytic variance estimator through a novel use of noise power spectrum (NPS) information to linearly propagate image noise to radiomic features. The accuracy of this estimator was validated against Monte Carlo simulations. The predicted and measured feature variance were compared through z-score normalized percentage error with the predicted variance achieving a prediction error of <20% across the majority of histogram and gray level co-occurrence features. We subsequently integrated these variance estimates to an uncertainty aware support vector machine (TSVC [1]) and compare the results to the standard support vector machine model. We simulated a simple classification problem with known per-sample variance estimates and show that TSVC has the capacity to either perform just as well, or better than the standard SVM. These results demonstrate that 1) variance estimates of features can be reliably obtained and 2) illustrate the potential utility of incorporating variance information to enhance model performance.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"9 ","pages":"71-76"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730140/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149328443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiable Forward and Back Projectors for Gradient-Based Deformable Motion Estimation.","authors":"Xiao Jiang, Grace J Gang, J Webster Stayman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Accurate estimation and compensation of patient motion are critical for many X-ray imaging applications, including image-guided interventions, cone-beam CT (CBCT) reconstruction, and multi-phase CT imaging. While gradient-based optimization may offer an effective framework for motion estimation, its practicality has been limited by the difficulty of computing analytical gradients of forward and back-projection operators with respect to motion. To address this issue, our recent work proposed a scalable, accurate, and efficient differentiable projector with respect to rigid patient motion. In this work, we extend this method from rigid motion to deformable motion by deriving analytical gradients of forward and back-projectors with respect to a spatially varying displacement vector field (DVF) in the continuous domain. We show that, similar to the rigid case, these gradients preserve the same integration structure as the original projection operators, enabling effective gradient computation using standard projector and backprojector implementations. The proposed method is evaluated in two X-ray imaging tasks: deformable 2D/3D registration using simulated biplane radiography and motion-compensated filtered backprojection (FBP) reconstruction. Simulation results demonstrate effective deformable motion estimation for both 2D/3D registration and motion-compensated FBP tasks, where both qualitative assessment and quantitative analysis reveal substantially reduced projection mismatch and motion-induced artifacts. These results indicate that the proposed differentiable projector provides a practical solution for gradient-based deformable motion estimation and compensation.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"9 ","pages":"108-111"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730153/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149328444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mixed Prior Diffusion Posterior Sampling for High Resolution CT Reconstruction.","authors":"Peiqing Teng, Xin Wang, Jian Zhou, Liang Cai, Tzu-Cheng Lee, Ruoqiao Zhang, J Webster Stayman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Diffusion models have a demonstrated ability to estimate complex prior distributions, including classes of image data. Diffusion Posterior Sampling (DPS) has recently emerged as a powerful framework for incorporating such learned priors into inverse problems; however, the performance of DPS is limited by the ability to train high-quality priors. This is particularly true in x-ray computed tomography, where patient data must balance noise and spatial resolution within acceptable x-ray dose limits. In this work, we propose Mixed Prior Diffusion Posterior Sampling (Mixed Prior DPS) that integrates global and local diffusion priors in the reconstruction. The global diffusion model is trained on full CT volume with modest spatial resolution to capture large-scale anatomical structures and lower frequency content. A local diffusion model trained on high-resolution patches focuses on fine-scale, high-frequency details. The two priors are combined in the Fourier domain to form a mixed posterior mean, and a masking strategy is employed to apply prior mixing selectively within an appropriate local region-of-interest while employing standard-resolution DPS elsewhere. This framework permits the use of modest resolution CT datasets for global context in conjunction with specialized high-resolution datasets (e.g. organ or tissue specific scans based on specialized protocols or on <i>ex vivo</i> samples where high-resolution, low-noise images can be collected without radiation dose constraints). In this work, we created a high-resolution lung training dataset for the local prior model using a CBCT benchtop system and a (plastinated) physical lung specimen. Experimental results on simulated low-dose CT demonstrate that the proposed method improves spatial resolution and data consistency as compared with filtered backprojection, standard DPS, and DPS with resampling, while preserving fine lung structures. These results highlight the effectiveness of multi-resolution prior integration for low-dose CT reconstruction.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"9 ","pages":"350-354"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730141/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149328447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diffusion Posterior Sampling for Angiographic Reconstruction using Limited Angle and Sparse View data for 4D-DSA.","authors":"Shudong Li, Suyu Liao, Peiqing Teng, J Webster Stayman, Grace J Gang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Four-dimensional digital subtraction angiography (4D-DSA) is an effective modality for the diagnosis and treatment planning of neurovascular interventions. Single time point 4D-DSA Projection data is usually underdetermined for a 3D reconstruction. Current image formation therefore relies on approximations using a 3D-DSA. In this work, we investigate application of advanced reconstruction on limited angle and sparse view data acquired at a single time point in 4D-DSA. We adopted the diffusion posterior sampling (DPS) algorithm which combines a physics-based data fidelity with an anatomically realistic diffusion prior. The diffusion prior was trained using axial slices extracted from 3D liver vasculature generative model. A total variation (TV) penalty along the z direction was applied to encourage continuity between slices. We compared DPS with a model-based approach using a directional TV penalty (DTV). We simulated a single-arc geometry on a single-plane C-arm and inverse geometry tomosynthesis system as well as an orthogonal-arc geometry achievable using a bi-plane C-arm systems. The DPS algorithm is able to reconstruct high-fidelity vascular anatomy under the challenging geometry of 10 views over a single arc of 40 degrees. As expected, vessels with thinner branches and/or branches in directions corresponding to the missing frequencies are more challenging to reconstruct. Orthogonal arcs improve the reconstruction quality of both algorithms, indicating the importance of more distributed angular sampling. DPS outperforms DTV under all conditions evaluated. The DPS algorithm provides an effective approach to reconstruction 4D-DSA data acquired using limited angle and sparse view geometries.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"9 ","pages":"355-358"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730154/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149328445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Focal Spot Design Optimization for High-Resolution CT.","authors":"Yue Fan, Xiao Jiang, Grace J Gang, J Webster Stayman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Recent advances in improved detector resolution including photon counting CT has helped to enable high-resolution diagnostic computed tomography (CT). However, the finite size of the X-ray tube focal spot has emerged as a dominant limitation on spatial resolution. While reducing focal spot size improves resolution, it also limits photon fluence. This can result in unacceptable levels of noise, particularly for larger patients. Novel x-ray tube designs may be required to overcome these fluence limitations. Previous work has shown that using structured focal spots, multiple x-ray sources, and advanced reconstruction models has the potential to overcome classic noise-resolution trade-offs. In this work, we write down general expressions for the imaging performance of a multi-focal spot CT system and use those predictors to design structured focal spots based on specific imaging tasks. Specifically, an analytic performance model is developed that explicitly links extended focal spot shape to the system modulation transfer function (MTF) and noise power spectrum (NPS) through local Fourier-based approximations. This model enables efficient prediction of a task-weighted detective quantum efficiency (DQE) and supports gradient-based optimization of focal spot emission patterns under physical fluence constraints. Focusing on high-frequency imaging tasks, we formulate the design problem as minimizing NPS within a prescribed spatial-frequency band and solve it using first-order optimization with multiple random initializations. Simulation studies demonstrate that the optimized focal spot designs substantially suppress high-frequency noise compared to a conventional small focal spot (limited fluence) configuration, yielding marked improvements in task-specific DQE. Analytical NPS predictions closely match empirical estimates from noisy reconstructions, validating the accuracy of the proposed model. These results highlight focal spot shape as a powerful and previously underutilized degree of freedom in CT system design and establish task-based, gradient-driven focal spot optimization as a promising approach for enhancing high-resolution CT performance.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"9 ","pages":"77-80"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13730139/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149328446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Spectral CT: Combining rapid kVp-switching and dual-layer detectors for high sensitivity iodine imaging.","authors":"Olivia F Sandvold, Roland Proksa, Heiner Daerr, Kevin M Brown, Thomas Koehler, Amy E Perkins, Grace J Gang, J Webster Stayman, Ravindra M Manjeshwar, Peter B Noël","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Over the past two decades, spectral computed tomography (CT) has undergone significant advancements, particularly in the realm of diagnostic accuracy, prompting a surge in clinical studies. This research examines the development of a new hybrid spectral CT system that combines a clinical-grade rapid kVp-switching X-ray tube with a dual-layer detector, aiming to boost quantitative spectral imaging performance in different clinical applications. The performance of the system was evaluated using varying tube voltages, duty cycles, and rotation times to enhance spectral outcomes. This experimental setup allowed for adjustments in parameters such as tube voltage pairs (140/80 and 120/70 kVp), duty cycles (ranging from 15/85 to 75/25), and tube currents (300 and 570 mA), which were tested on both large and small phantoms. The quantitative analysis was conducted using a two-input projection-based material decomposition approach. The study highlighted the impact of spectral weighting schemes on noise reduction and quantification bias in iodine density images. Results indicated that the maximum spectral separation scheme presented the least bias, suggesting its potential for improved clinical applications and outcomes. In conclusion, the research underscores the potential of integrating dual-energy technologies in hybrid spectral CT systems.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"2024 ","pages":"451-454"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11937910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT Reconstruction using Nonlinear Diffusion Posterior Sampling with Detector Blur Modeling.","authors":"Shudong Li, Xiao Jiang, Yuan Shen, J Webster Stayman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>There has been a great deal of work seeking to improve image quality in CT reconstruction through deep-learning-based denoising; however, there are many applications where it is spatial resolution that limits application and diagnostics. In this work, we week to improve spatial resolution in CT reconstructions through a combination of deep learning and physical modeling of detector blur. To achieve this goal, we leverage diffusion models as deep image priors to help regularize a joint deblurring and reconstruction problem. Specifically, we adopt Diffusion Posterior Sampling (DPS) as a way to combine a deep prior with a likelihood-based forward model for the measurements. The model we adopt is nonlinear since detector blur is applied after the nonlinear attenuation given by the Beer-Lambert lab. We trained a score estimator for a CT score-based prior, and then apply Bayes rule to combine this prior with a measurement likelihood score for CT reconstruction with detector blur. We demonstrate the approach in simulated data, and compare image outputs with traditional filtered-backprojection (FBP) and model-based iterative reconstruction (MBIR) across a range of exposures. We find a particular advantage of the DPS approach for low exposure data and report on major differences in the errors between DPS and classical reconstruction methods.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"2024 ","pages":"30-33"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11378848/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142157204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CT Material Decomposition using Spectral Diffusion Posterior Sampling.","authors":"Xiao Jiang, Grace J Gang, J Webster Stayman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>In this work, we introduce a new deep learning approach based on diffusion posterior sampling (DPS) to perform material decomposition from spectral CT measurements. This approach combines sophisticated prior knowledge from unsupervised training with a rigorous physical model of the measurements. A faster and more stable variant is proposed that uses a \"jumpstarted\" process to reduce the number of time steps required in the reverse process and a gradient approximation to reduce the computational cost. Performance is investigated for two spectral CT systems: dual-kVp and dual-layer detector CT. On both systems, DPS achieves high Structure Similarity Index Metric Measure(SSIM) with only 10% of iterations as used in the model-based material decomposition(MBMD). Jumpstarted DPS (JSDPS) further reduces computational time by over 85% and achieves the highest accuracy, the lowest uncertainty, and the lowest computational costs compared to classic DPS and MBMD. The results demonstrate the potential of JSDPS for providing relatively fast and accurate material decomposition based on spectral CT data.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"2024 ","pages":"324-327"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11412325/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142303109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long-term quantitative stability of a first-generation dual-source photon-counting CT.","authors":"Leening P Liu, Pouyan Pasyar, Olivia F Sandvold, Pooyan Sahbaee, Harold I Litt, Peter B Noël","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The introduction of the first clinical photon-counting CT (PCCT) presents an opportunity to improve and expand quantitative imaging to new applications with its high spatial resolution and stellar quantitative capabilities. Despite this potential, PCCT employs a photon-counting detector that introduces unknowns including temporal stability that is critical to separating biological changes from scanner changes and variation in longitudinal studies. For the purpose of determining the temporal stability of a first-generation dual-source PCCT, a phantom was subjected to near-weekly scans across a two-year period, in both single-source and dual-source modes. Virtual monoenergetic images (VMI) at 40, 70, 100, and 190 keV and iodine density maps were analyzed to determine changes in relative error and noise both related and unrelated to software/hardware changes. VMIs demonstrated improvements in quantification for dual-source mode associated with software and hardware updates but otherwise illustrated invariance with variation ranging from 0.03 to 0.08%. VMI noise similarly exhibited stability between and with major scanner updates with a maximum change of 4 HU. Iodine density maps also displayed stability between scanner updates with variation up to 0.1 mg/mL but significant improvements in quantification, especially in dual-source mode, that allowed relative error in single-source and dual-source modes to match at -0.04 and -0.02 mg/mL, respectively. Spectral results in PCCT showed temporal stability over time that improved quantification accuracy particularly for dual-source mode. This stability will boost confidence in quantitative metrics such as in longitudinal studies and thus facilitate more clinical applications that may change the workflow of diagnostic radiology.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"2024 ","pages":"479-482"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11832022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143442875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Material Decomposition and Scatter Estimation for Spectral CT.","authors":"Altea Lorenzon, Stephen Z Liu, Xiao Jiang, Grace J Gang, J Webster Stayman, Grace J Gang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Accurate scatter correction is essential to obtain highquality reconstructions in computed tomography. While many correction strategies for this longstanding issue have been developed, additional efforts may be required for spectral CT imaging - which is particularly sensitive to unmodeled biases. In this work we explore a joint estimation approach within a one-step model-based material decomposition framework to simultaneously estimate material densities and scatter profiles in spectral CT. The method is applied to simulated phantom data obtained using a parametric additive scatter mode, and compared to the unmodeled scatter scenario. In these preliminary experiments, We find that this joint estimation approach has the potential to significantly reduce artifacts associated with unmodeled scatter and to improve material density estimates.</p>","PeriodicalId":90477,"journal":{"name":"Conference proceedings. International Conference on Image Formation in X-Ray Computed Tomography","volume":"2024 ","pages":"186-189"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11391857/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142303110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}