Physics in medicine and biology最新文献

{"title":"Physics-constrained and geometry-aware deep reconstruction for limited-angle CBCT.","authors":"Mingzhe Hu, Shaoyan Pan, Yuan Gao, Huiqiao Xie, Jill Remick, Chih-Wei Chang, Justin Roper, Zhen Tian, Xiaofeng Yang","doi":"10.1088/1361-6560/aeb59b","DOIUrl":"https://doi.org/10.1088/1361-6560/aeb59b","url":null,"abstract":"<p><strong>Objective: </strong>Limited-angle cone-beam computed tomography (CBCT) is attractive for imageguided radiotherapy and imaging-guided procedure when full-arc acquisition is impractical, but the incomplete angular sampling leads to severe streaking, shading, and structural distortion. This study aimed to develop a physics-constrained and geometry-aware deep reconstruction framework for recovering anatomically faithful volumetric CBCT from limited-angle projections.&#xD;Approach: We propose PCGA-Net, a dual-domain reconstruction framework that combines projection completion, analytic geometric reconstruction, and image-domain refinement within a unified cross-domain design. Specifically, a projection completion module first estimates missingangle information from the measured limited-angle projections. A geometry-aware reconstruction module then maps the completed projections into image space using differentiable cone-beam forward and backward-projection operators. Finally, a volumetric refinement module suppresses residual artifacts and restores anatomical detail under geometry-guided cross-domain consistency supervision. The framework was evaluated on three cohorts: gynecologic highdose-rate brachytherapy, abdominal liver 4DCT, and head-and-neck CBCT.&#xD;Main Results: Across all three cohorts, PCGA-Net consistently outperformed conventional limitedangle FDK reconstruction and the compared learning-based baselines, cGAN and PatRecon-Net, in both qualitative and quantitative evaluation. On the gynecologic HDR brachytherapy cohort, PCGA-Net achieved an MAE of 34.47 ± 6.28 HU, an SSIM of 0.87 ± 0.04, and a PSNR of 35.79 ± 0.95 dB. On the abdominal liver 4DCT cohort, PCGA-Net achieved 39.27 ± 6.10 HU MAE, 0.82 ± 0.03 SSIM, and 36.85 ± 1.16 dB PSNR.On the head-and-neck CBCT cohort, PCGA-Net achieved 28.42 ± 4.88 HU MAE, 0.91 ± 0.05 SSIM, and 38.52 ± 0.95 dB PSNR. In all three cohorts, PCGA-Net exceeded cGAN and PatRecon-Net across all evaluated metrics. &#xD;Significance: These results indicate that jointly enforcing projection-domain completion, analytic imaging geometry, and image-domain refinement is an effective strategy for limited-angle CBCT reconstruction. PCGA-Net provides a robust short-arc reconstruction framework across multiple anatomical sites, supporting its potential utility in constrained imageguided therapeutic and procedural settings.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149207659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of depth-of-interaction and spatially-variant point-spread-function model on the performance of ultra-high resolution brain PET.","authors":"Tianyi Zeng, Yassir Najmaoui, Jiazhen Zhang, Tommaso Volpi, Kathryn Fontaine, Yanis Chemli, Yifan Hu, Jean-Dominique Gallezot, Chen Sun, Yihuan Lu, Georges El Fakhri, Richard E Carson, Thibault Marin","doi":"10.1088/1361-6560/aeafa5","DOIUrl":"10.1088/1361-6560/aeafa5","url":null,"abstract":"<p><p><i>Objective.</i>To implement a spatially-variant point spread function (VarPSF) model for the NeuroEXPLORER (NX) brain positron emission tomography (PET) scanner in the open-source Yale Reconstruction Toolkit for PET, and investigate the interplay between depth-of-interaction (DOI) resolution and resolution modeling.<i>Approach.</i>PSF parameters were estimated from simulated and physically measured point sources. Three primary DOI configurations were evaluated: eight-layer DOI (8DOI), two-layer DOI (2DOI), and no DOI (noDOI), with an additional 4DOI comparison in the off-center simulated Derenzo study. Reconstructions using VarPSF, a spatially-invariant PSF measured at the field-of-view center (SinglePSF), and no PSF modeling (noPSF) were assessed using simulated Derenzo and brain phantoms, a physical Derenzo phantom, and one non-human primate (NHP) scan.<i>Main results.</i>In simulated and physical Derenzo studies, VarPSF yielded higher peak-to-valley ratios than SinglePSF and noPSF at the final evaluated iterations, with pronounced gains at large radial offsets. In the simulated brain phantom, VarPSF reduced the estimated transverse blur by 0.3 mm relative to SinglePSF and 0.5 mm relative to noPSF in 2DOI, and by 0.6 mm and 0.8 mm, respectively, in noDOI. In the NHP study, VarPSF improved contrast and structural delineation with reduced DOI encoding at approximately matched white-matter coefficient of variation, while its incremental benefit over SinglePSF was small with 8DOI at clinically relevant iteration settings.<i>Significance.</i>Spatially-variant PSF modeling can partially compensate for limited DOI information. The findings motivate combining modest DOI capability with accurate resolution modeling, while further validation is required for redesigned detectors and fully corrected acquisitions. The open-source implementation enables controlled investigation of the complementary roles of DOI encoding and resolution modeling.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13673226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149113807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards artificial intelligence based preoperative dosimetry for liver⁹⁰Y selective internal radiation therapy.","authors":"E Morel-Corlu, F Lalys, A Petit, P Haigron, S Esneault, Y Rolland, M Garreau","doi":"10.1088/1361-6560/aeabea","DOIUrl":"10.1088/1361-6560/aeabea","url":null,"abstract":"<p><p><i>Objective.</i>Selective internal radiation therapy delivers Y-90 microspheres through the hepatic arterial system to achieve tumoricidal absorbed dose while limiting normal-tissue irradiation. Current pre-treatment dosimetry requires angiography and 99 mTc-MAA imaging, resulting in an invasive and resource-intensive workflow. This study evaluates the feasibility of estimating post-therapy Y-90 dose distribution directly from diagnostic multiphasic CT using an automated deep-learning pipeline, without requiring angiography or surrogate-particle imaging.<i>Approach.</i>In 152 treatments from the multicenter PROACTIF registry, arterial- and portal-phase CT, together with clinically documented perfusion territories and injected activities, were processed through automated segmentation, rigid registration, differential CT generation, and a generative model synthesizing a PET-like Y-90 activity map. Absorbed-dose maps were computed using the Local Dose Deposition method, and predictive accuracy was assessed using tumor dose-volume metrics and voxelwise spatial agreement.<i>Main results.</i>For the best-performing configuration, the median tumor D70 error was 23 Gy, with substantial inter-patient variability reflecting the challenges of CT-only dose prediction. High-dose coverage (V200) showed a similar pattern. In contrast, spatial agreement was consistently strong, with perfused-volume gamma passing rates around 93% and tumor-level rates around 85%, indicating that the macro-scale distribution of microspheres can be approximated from diagnostic CT. The full pipeline was fully automated and produced predictive dosimetry in under<i>30 S. Significance.</i>Pre-angiography CT contains exploitable information about arterial enhancement and perfusion patterns that enables feasible CT-only prediction of Y-90 spatial distribution. While tumor-level absorbed-dose metrics remain variable, the strong spatial agreement suggests potential utility as an early planning tool to support patient selection or guide catheterization strategy prior to angiography.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149031161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-fidelity 3D geometric reconstruction of pelvic organs from MRI: a hybrid deep learning and iterative optimization approach.","authors":"Hui Wang, Xiaowei Li, Chenxin Zhang, Yifan Feng, Jianwei Zuo, Yumeng Tang, Xiuli Sun, Jianliu Wang, Bing Xie, Jiajia Luo","doi":"10.1088/1361-6560/aeb598","DOIUrl":"https://doi.org/10.1088/1361-6560/aeb598","url":null,"abstract":"<p><strong>Objective: </strong>The generation of high-fidelity, high-quality three-dimensional (3D) pelvic organ geometries from magnetic resonance imaging (MRI)-derived segmentation masks remains challenging. This study aimed to develop and evaluate a hybrid framework for reconstructing the bladder, uterus, and rectum, and to assess its geometric fidelity, mesh-quality proxy performance, and reconstruction efficiency.&#xD;Approach. We developed a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: (1) a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; (2) a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and (3) a holistic synergy mechanism-where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality.&#xD;Main results. Before iterative refinement, the proposed model outperformed representative deep learning-based reconstruction methods in geometric fidelity, achieving CD/DSC values of 5.5 × 10⁻³/0.788 for the bladder, 3.7 × 10⁻³/0.839 for the rectum, and 4.2 × 10⁻³/0.900 for the uterus. Deep learning-based initialization enabled the complete hybrid framework to converge within approximately 100 iterations, with a reconstruction time of approximately 35 s per organ on a CPU and 1.5 s on a GPU. At the patient level, the mean minSICN and minSIGE values of the 10 worst volumetric elements were 0.0807 and 0.0844, respectively, exceeding those achieved by traditional geometric post-processing methods.&#xD;Significance. The proposed framework connects image-domain segmentation with structural-domain applications by efficiently generating high-fidelity, high-quality pelvic organ geometries with improved mesh-quality proxy performance. These geometries may support statistical shape assessment and may provide candidate surface representations for subsequent volumetric meshing and solver-specific biomechanical validation.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149207667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive physics-inspired angular-spatial modeling for multi-shell diffusion MRI denoising.","authors":"Suchao Ma, Yuanjun Wang","doi":"10.1088/1361-6560/aeb599","DOIUrl":"https://doi.org/10.1088/1361-6560/aeb599","url":null,"abstract":"<p><strong>Objective: </strong>Multi-shell diffusion magnetic resonance imaging (dMRI) provides rich q-space information but is susceptible to noise, which can disrupt spatial anatomy, intra-shell directional relationships, inter-shell signal attenuation, and downstream diffusion parameter estimation. We aim to develop a denoising method that jointly preserves spatial structure, directional information, and shell-specific signal characteristics.</p><p><strong>Approach: </strong>We propose ASD-NCSM, an adaptive physics-inspired angular-spatial framework with a fixed three-stage alternating architecture. It combines intra-shell differential angular graph message passing with 2.5D spatial residual refinement. Noise-Conditioned Shell Modulation (NCSM) adaptively regulates angular updates according to b-value, spatial residual and angular dispersion proxies, and local gating. A Shell-wise Physical Attenuation and Angular Relation Consistency (SPARC) objective further constrains shell-wise signal fidelity, logarithmic attenuation, and local angular structure. The model was evaluated on HCP multi-shell dMRI with simulated noise and independently acquired real in vivo brain dMRI data.</p><p><strong>Main results: </strong>Across five simulated noise levels from 2% to 10%, ASD-NCSM achieved the best overall DWI restoration among MPPCA, 1D-CNN, ECDM, SAN2N, and dMRI-Swin, with consistent subject-level advantages in PSNR, SSIM, and NRMSE. At 6% noise, principal-direction angular nRMSE was 32.68 ± 2.76%, with significant differences from all five baselines after Holm correction. ASD-NCSM also achieved the lowest mean MAE for FA, MD, AD, and RD, and the lowest relative MAE for ODI and FISO, while NDI was comparable to 1D-CNN and dMRI-Swin. For real data without noise-free references, Q-PEFT yielded the lowest angular cross-fit inconsistency (2.29 ± 0.10%) across three test subjects while maintaining limited signal and downstream-parameter changes.</p><p><strong>Significance: </strong>ASD-NCSM jointly preserves spatial continuity, directional geometry, and shell-level attenuation, providing balanced signal recovery, directional preservation, and downstream parameter stability for multi-shell dMRI denoising.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149207673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Direct probabilistic IMPT treatment planning with setup and range errors for neuro-oncological patients.","authors":"J R de Jong, S Breedveld, S J M Habraken, M S Hoogeman, J I de Jong, D Lathouwers, Z Perkó","doi":"10.1088/1361-6560/aeb08b","DOIUrl":"https://doi.org/10.1088/1361-6560/aeb08b","url":null,"abstract":"<p><p><i>Objective</i>. To show computational feasibility of a previously proposed probabilistic planning approach on a neuro-oncological patient group, we compared probabilistic plans with (automated) robust plans for one patient (group A) that could achieve sufficient clinical target coverage and for four patients (group B) where target coverage had to be compromised due to organ-at-risk (OAR) dose constraints.<i>Approach</i>. The probabilistic approach is percentile-based and uses the fact that a (dose) percentile can be approximated as a linear combination of its expected value and standard deviation. This allows us to formulate objectives and constraints with patient-specific acceptance probabilities. The optimization has a nested structure: the inner optimization optimizes the beam weights for a given percentile estimate, while an outer loop iteratively updates and improves the accuracy of the percentile estimate. For every outer iteration, the optimization is warm-started from the previous iteration. Percentiles are efficiently calculated by sampling a polynomial chaos expansion of the dose-influence matrix.<i>Main results</i>. The patient in group A achieved cumulative OAR dose reductions (of OAR-related DVH-metrics) of 23.1 GyRBE, for identical target coverage. Target coverage improved for all patients in group B (the 10th percentile ofincreased up to 0.61 GyRBE), at the same time reaching cumulative OAR dose reductions (of OAR-related DVH-metrics) up to about 40 GyRBE. Probabilistic plans were optimized in 44 h to 226 h. For two representative patients, eliminating warm-starting (i.e. the outer loop) from the approach reduced total optimization times to below 10 h (which took originally 80 h and 141 h).<i>Significance</i>. Compared to robust optimization methods, the probabilistic approach achieves improved trade-offs between probabilistic target coverage and OAR sparing, potentially leading to better treatments.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":"71 20","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149195611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A wavelet-guided diffusion method for brain magnetic resonance parameter mapping using MOLED-based datasets: proof-of-principle.","authors":"Che Wang, Linyu Fan, Qizhi Yang, Zejun Wu, Yiru Lin, Yong Zhang, Congbo Cai, Jianfeng Bao, Shuhui Cai","doi":"10.1088/1361-6560/aeb08a","DOIUrl":"10.1088/1361-6560/aeb08a","url":null,"abstract":"<p><p><i>Objective.</i>Quantitative magnetic resonance imaging (qMRI) can noninvasively acquire parametric maps, providing quantitative biomarkers for clinical assessment. Parametric maps, such as<i>T</i>₂,<i>T</i>₂^*, and apparent diffusion coefficient (ADC), characterize distinct biophysical processes in tissue in an interpretable, numerical manner. Owing to their distinct physical origins, various parametric maps differ in physical units, numerical magnitudes, and dynamic ranges. Even for the same type of parametric map, inter-subject differences may still exist in anatomical morphology, tissue characteristics, and the local distributions of parameter values. However, deep learning methods trained in image-domain directly learn pixel-level parameter values, and variations in numerical scales and subject-specific parameter distributions may result in anatomical detail loss and localized artifacts in certain tasks. To address this challenge and to deliver dependable quantitative references for clinical assessment, we propose a wavelet-guided diffusion method.<i>Approach.</i>We extend the discrete convolution wavelet transform (DCWT) to two dimensions and combine it with a conditional denoising diffusion method to develop a diffusion-based DCWT (Diff-DCWT) for parameter mapping. Diff-DCWT achieves accurate parameter mapping under the guidance of wavelet coefficient maps, thereby reducing reliance on image domain learning. The performance of Diff-DCWT is evaluated through simulation and<i>in vivo</i>experiments across<i>T</i>₂,<i>T</i>₂^*, and ADC mapping tasks.<i>Main Results.</i>Both simulation and healthy volunteer experiments demonstrate that<i>T</i>₂,<i>T</i>₂^*, and ADC maps obtained from Diff-DCWT maintain excellent visual quality and quantitative accuracy. Clinical case studies suggest the potential utility of Diff-DCWT-derived<i>T</i>₂and ADC maps for stroke staging and help distinguish lesional from normal brain regions in glioma.<i>Significance.</i>Diff-DCWT establishes a high-fidelity framework for parameter mapping and exhibits preliminary clinical value in stroke staging and glioma characterization. Moreover, this work demonstrates the potential of wavelet-domain prior guidance for deep learning-based qMRI applications.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149113662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physics-informed machine learning-based dose calculation for patients undergoing fluoroscopically guided interventional procedures.","authors":"Haegin Han, Keith Griffin, Monjoy Saha, A Kyle Jones, Steve Dean Mann, Kevin Wunderle, Donald Miller, Nina Petoussi-Henss, David G Sutton, Choonsik Lee","doi":"10.1088/1361-6560/aeb597","DOIUrl":"https://doi.org/10.1088/1361-6560/aeb597","url":null,"abstract":"<p><strong>Objective: </strong>To develop and evaluate a physics-informed machine-learning framework for rapid organ-dose estimation in fluoroscopically guided interventional procedures without requiring patient-specific imaging.&#xD;Approach: We used 385 adult radiation dose structured reports from three procedure types-bilateral carotid angiography, percutaneous biliary drainage, and liver chemoembolization-comprising more than 50,000 irradiation events. A body-size-matched computational phantom was selected using patient sex, height, and weight. RDSR-derived beam parameters and engineered descriptors of beam-organ geometry and attenuation were used to train organ-specific XGBoost models for localized organs and a multi-output multilayer perceptron model for four distributed tissues. Monte Carlo-derived dose coefficients from NCIRF3 were used as target values.&#xD;Main results: In the held-out test set of 12,683 irradiation events, 49.4% and 84.8% of XGBoost-based localized-organ estimates were within ±5% and ±20% of the Monte Carlo-derived values, respectively. The corresponding proportions were 88.2% and 98.0% for the distributed-tissue estimates and 87.6% and 98.3% for detriment-weighted dose. The median relative prediction error across organs and tissues was 0.37% (interquartile range, -3.68% to 4.99%). A reliability score was developed to support uncertainty-aware interpretation. The framework required approximately 0.3 s per irradiation event, corresponding to an approximately 290-fold acceleration relative to conventional Monte Carlo simulation under the benchmark conditions.&#xD;&#xD;Significance: The proposed image-free framework enables rapid organ-dose estimation when patient imaging is unavailable and may support large retrospective epidemiological studies and uncertainty-aware dose monitoring. Because development and validation were limited to three procedure types and relied on reconstructed phantom-beam geometry, external validation is required before application to other procedures or high-precision individual clinical decisions.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149207723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"X-ray projection-guided deformation vector field estimation and dynamic CBCT imaging using patient-specific vector-quantized diffusion.","authors":"Zifeng Li, Yongqi Zhu, Daochi Qu, Zhanghua Luo, Feng Chi, Hua Zhang","doi":"10.1088/1361-6560/aeb062","DOIUrl":"10.1088/1361-6560/aeb062","url":null,"abstract":"<p><p><i>Objective.</i>To develop a conditional vector-quantized (VQ) diffusion-based dynamic cone beam computed tomography imaging framework using dual-view x-ray projections for accurate reconstruction of respiratory-induced lung tumor motion, with the potential to enable four-dimensional (4D) target verification during lung radiotherapy.<i>Methods.</i>Patient-specific respiratory motion models were constructed from planning 4D- computed tomography(CT) images using deformable image registration and principal component analysis (PCA). Synthetic DVFs were generated by sampling PCA coefficients and applied to the reference-phase CT images to produce dynamic three-dimensional (3D) volumes, from which paired dual-view DRRs were generated. A conditional VQ diffusion framework was developed, consisting of separate two-dimensional and 3D vector quantized variational autoencoder s for encoding DRRs and DVFs into discrete latent representations, followed by a conditional diffusion model to learn the mapping from x-ray projection features to deformation vector field (DVF) latent representations. During inference, dual-view x-ray projections were encoded and processed by the conditional diffusion model to estimate DVFs, which were then used to deform the reference CT image and reconstruct temporally resolved 3D volumes.<i>Results.</i>The simulation study demonstrates that the estimated DVFs effectively captured the respiratory-induced deformation of lung tumors, and the reconstructed dynamic volume CT images demonstrated accurate anatomical motion characteristics across respiratory phases.<i>Conclusion.</i>The proposed patient-specific VQ diffusion framework enables accurate estimation of respiratory-induced lung tumor motion from dual-view x-ray projections and facilitates the high-temporal-resolution dynamic volume CT reconstruction. The results demonstrate its potential as an image-guided solution for tumor motion tracking in lung tumor radiotherapy.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149113476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-GPU parallel framework for DOI-enabled long axial field-of-view PET image reconstruction.","authors":"Zhao Wang, Xin Zhao, Zhengkun Dong, Wei Liu, Qiyu Peng, Qiushi Ren, Zhaoheng Xie","doi":"10.1088/1361-6560/aeabe8","DOIUrl":"10.1088/1361-6560/aeabe8","url":null,"abstract":"<p><p><i>Objective.</i>Depth-of-interaction (DOI)-enabled long axial field-of-view (LAFOV) positron emission tomography (PET) can mitigate parallax-induced resolution degradation, but DOI modeling substantially expands the lines-of-response space and increases computational cost. This study aimed to develop a scalable reconstruction framework for DOI-enabled LAFOV-PET.<i>Approach.</i>We present an optimized multi-GPU reconstruction framework based on list-mode ordered-subsets expectation maximization. The framework targets the major computational bottlenecks of DOI-enabled LAFOV-PET reconstruction, including sensitivity image calculation and Monte Carlo-based scatter estimation.<i>Main results.</i>The extended IQ phantom demonstrated near-linear scalability across multiple GPUs for sensitivity image calculation and Monte Carlo-based scatter estimation. Additional Derenzo and hybrid anthropomorphic phantom studies validated the imaging benefits of DOI modeling, including improved spatial resolution and performance under realistic imaging conditions.<i>Significance.</i>The proposed framework improves the scalability of DOI-enabled LAFOV-PET reconstruction by enabling its dominant computational components to efficiently utilize available GPU resources, establishing a foundation for high-performance reconstruction in next-generation PET systems.</p>","PeriodicalId":20185,"journal":{"name":"Physics in medicine and biology","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149031171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}