IEEE Transactions on Radiation and Plasma Medical Sciences最新文献

{"title":"Plasma-Activated Hydrogel Mask for Acne Treatment","authors":"Jinkun Chen;Weiji Yang;Mengke Li;Xinwei Lu;Xian Wang;Shengduo Xu;Jishen Zhang;Zifeng Wang;Hao Zhang;Li Guo;Yuan Zhao;Dingxin Liu;Xiaohua Wang;Mingzhe Rong;Yumin Xia;Yongping Shao","doi":"10.1109/TRPMS.2025.3639050","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3639050","url":null,"abstract":"Facial masks have a vast market in the cosmetic and medical fields. To enhance the therapeutic effects of facial masks, many additives are used, which inevitably leads to a series of problems, such as safety issues. Therefore, we proposed an efficient and safe antimicrobial plasma-activated hydrogel mask (PAHM). PAHM combines a plasma-activated ammonium acryloyldimethyltaurate/VP copolymer hydrogel (PAAH) and a plasma-activated MS (PAMS). The plasma produced liquid-phase reactive species in plasma-activated AH (PAAH) which disrupted the cross-linking structure but had highly effective and short-term sterilizing effects. While plasma etching of cotton fibers can produce reactive functional groups, and PAMS has a long-term antimicrobial effect. Moreover, PAAH can load uniformly on PAMS and prevent water evaporation. The synergistic effect of them enhances the effectiveness and duration of PAHM. In vitro studies revealed that PAHM could kill more than 99.99% of S. aureus and P. acnes, and is effective for more than a week. In vivo experiments revealed that PAHM could effectively treat acne symptoms, inhibit the expression of inflammatory factors and reduce epidermal layer thickness without significant irritation. This work presents a novel approach to plasma application and, which has great potential for cosmetic and dermatological treatments and other applications.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1169-1183"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AMGL: Adaptive Multimodal Graph Learning for Brain Disease Prediction","authors":"Runsheng Wu;Jianbin He;Guoheng Huang;Xiaochen Yuan;Zhoule Feng;Yan Li;Guo Zhong;Wing-Kuen Ling;Chi-Man Pun;Qi Yang","doi":"10.1109/TRPMS.2026.3658322","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3658322","url":null,"abstract":"Graph-based approaches have been widely adopted in biomedical applications for modeling multimodal data, particularly in the accurate diagnosis and effective treatment of brain disorders. Most existing graph-based multimodal medical data processing methods typically extract features by fusing multimodal information through weighted operations, and then manually define graph structures based on specific modalities to learn patient representations via graph embedding. However, these methods often overlook the complex correlations and discrepancies across modalities, making it difficult to obtain highly relevant information. Moreover, the prior construction of an appropriate graph presents a considerable challenge, as manually defined structures are susceptible to spurious or noisy edges. These factors inevitably lead to incorrect predictions in real-world clinical scenarios. To address these limitations, we propose an end-to-end adaptive multimodal graph learning (AMGL) framework that comprises two key modules: modal-aware integration learning (MAIL) and cluster-constrained adaptive graph learning (CAGL). MAIL captures both intermodal relevance and complementarity to construct enriched modality-aware representations, while CAGL performs adaptive graph learning based on data clustering and utilizes a graph-gated neural network (GGNN) for disease prediction. The experimental results on the TADPOLE and autism brain imaging data exchange (ABIDE) datasets demonstrate that our method achieves superior classification accuracy and generalization capability, with an average performance gain of 2%–3% over state-of-the-art approaches. The code of AMGL is available at <uri>https://github.com/WuJUNEhhh/AMGL</uri>","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1011-1023"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Material Decomposition in Photon-Counting Computed Tomography With Diffusion Models: Comparative Study and Hybridization With Variational Regularizers","authors":"Corentin Vazia;Thore Dassow;Alexandre Bousse;Jacques Froment;Béatrice Vedel;Franck Vermet;Alessandro Perelli;Jean-Pierre Tasu;Dimitris Visvikis","doi":"10.1109/TRPMS.2026.3651354","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3651354","url":null,"abstract":"PCCT has emerged as a promising imaging technique, enabling spectral imaging and material decomposition (MD). However, images typically suffer from a low signal-to-noise ratio (SNR) due to constraints, such as low photon counts and sparse-view settings, which provoke artifacts. To prevent this, variational methods minimize a data-fit function coupled with handcrafted regularizers that mimic a prior by enforcing image properties, such as gradient sparsity. In the last few years, diffusion models (DMs) have become predominant in the field of generative models and have been used as a learned prior for image reconstruction. This work investigates the use of DMs as regularizers for MD tasks in photon-counting computed tomography (PCCT), specifically using diffusion posterior sampling (DPS) guidance. Three DPS-based approaches—image-domain two-step DPS (ImTDPS), projection-domain two-step DPS (ProjTDPS), and one-step DPS (ODPS)—are evaluated. The first two methods achieve MD in two steps by performing reconstruction and MD separately. The last method, ODPS, samples the material images directly from the measurement data. The results indicate that ODPS achieves superior performance compared to ImTDPS and ProjTDPS, providing sharper, noise-free and crosstalk-free images. Furthermore, we introduce a novel hybrid method for scenarios involving materials absent from the training dataset which combines DM priors with standard variational handcrafted regularizers for the materials unknown to the DM. This hybrid method demonstrates improved MD quality compared to a standard variational method and does not require additional training of the DM neural network (NN).","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1075-1087"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerated Physics-Guided Diffusion Model for 3-D Limited-Angle Reconstruction of Cardiac Computed Tomography","authors":"Shuo Han;Bahareh Morovati;Yongtong Liu;Changsheng Fang;Shuyi Fan;Li Zhou;Yu Shi;Ge Wang;Hengyong Yu","doi":"10.1109/TRPMS.2025.3650342","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3650342","url":null,"abstract":"Cardiovascular diseases (CVDs) remain the leading cause of morbidity and mortality worldwide. Computed tomography (CT) plays an important role in the diagnosis and management of CVDs. However, the temporal resolution of current cardiac CT imaging techniques is still insufficient to freeze the beating heart. One solution to improve temporal resolution is fast data acquisition for a limited-angle range. Unfortunately, this approach introduces significant limited-angle artifacts that compromise image quality. Diffusion models have shown promising results to address this issue by effectively reconstructing missing data, but the process is typically time-consuming. In this article, we propose a novel method for 3-D limited-angle reconstruction using a diffusion model, optimized to significantly reduce computational time. Specifically, our approach integrates the regularized derivative least square (RDLS) algorithm with denoising diffusion implicit models. The numerical simulations and clinical data experiments demonstrate that the proposed model outperforms the existing methods both quantitatively and qualitatively. Compared with DDS, our method delivers an <inline-formula> <tex-math>$1.8{times }$ </tex-math></inline-formula> speedup on the simulated dataset and a <inline-formula> <tex-math>$3.4{times }$ </tex-math></inline-formula> speedup on the real clinical dataset.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1088-1098"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"First Experimental Measurement of Prompt Gamma Imaging With Real-Time Neutron Rejection via Pulse Shape Discrimination","authors":"O. Halfon;C. Riboldi;K. Urban;G. Borghi;M. Carminati;M. Donetti;M. Pullia;F. Camera;C. Fiorini","doi":"10.1109/TRPMS.2026.3658224","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3658224","url":null,"abstract":"Prompt gamma imaging (PGI) holds strong potential for range verification in hadrontherapy; yet, its performance is challenged by neutron-induced background, especially in carbon ion treatments. To mitigate this issue, a dedicated imaging system integrating pulse shape discrimination (PSD) capabilities for real-time neutron discrimination was designed and experimentally validated. The detector employs a Cs₂LiYCl₆:Ce (CLYC) scintillator coupled to SiPM arrays and compact acquisition electronics, allowing real-time computation of digital PSD coefficients. Interaction point reconstruction within the crystal is achieved through an artificial neural network (ANN), whose inputs are the SiPM signal amplitudes processed by four custom 16-channel GAMMA application-specified integrated circuits (ASICs). In this work, the system is operated as a prompt gamma (PG) camera using a knife-edge (KE) collimator to retrieve PG emission profiles from the irradiated target, enabling range verification while efficiently reducing uncorrelated neutron contributions. We present the outcomes of the first experimental PGI campaign at the Centro Nazionale di Adroterapia Oncologica (CNAO), Pavia, Italy, during carbon ion irradiation, demonstrating, according to our knowledge, the first improvement in Bragg peak (BP) localization precision enabled by PSD-based neutron background rejection.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1132-1142"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11364246","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877902","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":"Patlak-Guided Self-Supervised Learning for Dynamic PET Denoising","authors":"Qiong Liu;Xueqi Guo;Yu-Jung Tsai;Jean-Dominique Gallezot;Ming-Kai Chen;Liang Guo;Huidong Xie;Vladimir Panin;Richard E. Carson;Chi Liu","doi":"10.1109/TRPMS.2026.3656480","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3656480","url":null,"abstract":"Quantitative 18F-FDG Patlak <inline-formula> <tex-math>$K_{i}$ </tex-math></inline-formula> images provide physiologically meaningful measures of glucose influx, but they are substantially noisier than standardized uptake value (SUV) images because they are estimated from short-duration dynamic frames. This study aims to improve the quality and quantitative reliability of <inline-formula> <tex-math>$K_{i}$ </tex-math></inline-formula> images by applying a self-supervised deep learning framework for dynamic positron emission tomography (PET) denoising. We propose the Patlak-guided self-supervised denoising network (PG-SSDNet), a multiframe CycleGAN-based model that incorporates a Patlak consistency loss to preserve tracer kinetics across frames. PG-SSDNet was evaluated on 14-frame and 6-frame whole-body 18F-FDG dynamic PET datasets from 27 patients. Performance was compared with a supervised U-Net, a single-frame CycleGAN, and a multiframe CycleGAN without Patlak guidance. Metrics included mean normalized residual sum of squares (MNRSS) of Patlak fits, liver normalized standard deviation (NSTD), and lesion signal-to-noise ratio (SNR). PG-SSDNet consistently reduced noise while maintaining the kinetic fidelity. It achieved the lowest Patlak fitting errors (MNRSS: <inline-formula> <tex-math>$0.98% {,}pm {,}0.14%$ </tex-math></inline-formula> for 14 frames and <inline-formula> <tex-math>$0.85% {,}pm {,}0.11%$ </tex-math></inline-formula> for 6 frames), the lowest liver NSTD values (<inline-formula> <tex-math>$0.105 pm 0.037$ </tex-math></inline-formula> for 14 frames and <inline-formula> <tex-math>$0.211 pm 0.107$ </tex-math></inline-formula> for 6 frames), and the highest lesion SNR across all methods, while preserving accurate mean <inline-formula> <tex-math>$K_{i}$ </tex-math></inline-formula> values. PG-SSDNet effectively denoises 18F-FDG dynamic PET data while preserving Patlak linearity, improving both lesion quantification and image quality. Unlike supervised methods, it requires no paired noisy/clean datasets, making it practical for clinical deployment. Future work will extend PG-SSDNet to other tracers with different kinetic properties and to larger multicenter datasets.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1037-1048"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Member Get-a-Member (MGM) Program","authors":"","doi":"10.1109/TRPMS.2026.3726131","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3726131","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1184-1184"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11677018","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877937","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":"Impact of Detector Parameters and Image Resolution Modeling on Dedicated Brain PET Imaging","authors":"Min Gao;Samuel Matej;Joel S. Karp;Suleman Surti","doi":"10.1109/TRPMS.2025.3649140","DOIUrl":"10.1109/TRPMS.2025.3649140","url":null,"abstract":"High performance brain PET scanners suitable for accurate and precise measurement of uptake in small regions of the brain require high spatial resolution (1.5–2 mm) together with high system sensitivity. While small cross section crystals are needed to achieve high spatial resolution with pixelated detectors, effective system sensitivity requires long crystals and good time-of-flight (TOF) resolution. In addition, depending on crystal thickness, some level of depth-of-interaction (DOI) capability may also be needed to reduce parallax error. While various methods for DOI measurement can be utilized within the detector, the impact on reconstructed spatial resolution as a function of crystal thickness needs to be carefully evaluated. The focus of this work is to use Monte Carlo simulations to evaluate the impact of crystal size, thickness, and DOI resolution on the reconstructed spatial resolution in a high-resolution brain scanner design. Two crystal cross sections were chosen, 1.6 mm <inline-formula> <tex-math>$times 1$ </tex-math></inline-formula>.6 mm and 2 mm <inline-formula> <tex-math>$times $ </tex-math></inline-formula> 2 mm, and three different LSO crystal thickness (10, 15, and 20 mm) were evaluated. We evaluated these system designs without DOI capability and with DOI resolution (4–12 mm) for varying crystal thickness. In addition, we evaluated the use of image-space resolution modeling (IRM) techniques, which can mitigate losses in spatial resolution and positioning accuracy due to parallax error and Compton scatter, and to complement the advantages of DOI capability. A brain size elliptical phantom with small spheres was simulated to study the overall benefit in uptake measurements for small objects using the contrast recovery coefficient (CRC) metric. Our results show that a system with 2 mm <inline-formula> <tex-math>$times $ </tex-math></inline-formula> 2 mm crystals can provide comparable image quality in terms of CRC measurement than one with 1.6 mm <inline-formula> <tex-math>$times 1$ </tex-math></inline-formula>.6 mm crystals. However, crystal thickness has a bigger impact on spatial resolution and CRC with performance degrading with best performance achieved with 10 mm thick crystals. DOI measurement is necessary with longer crystals in order to maintain good imaging performance with high sensitivity. For the 15-mm thick crystals 9 mm, DOI resolution is needed to compensate for the loss in spatial resolution compared to 10-mm thick crystals without DOI, but still with lower CRC. A similar conclusion is reached for 20-mm crystals with 4-mm DOI resolution. Alternatively, IRM methods can provide improved and similar performance for all crystal thicknesses studied here, indicating a pathway for achieving our brain scanner design goals without additional cost, complexity, and performance tradeoffs. This work provides a systematic investigation for designing future brain PET systems.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1124-1131"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147609202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mutually Orthogonal Plane-Based Optical-Flow-Regulated Diffusion Model for Stationary Head CT Reconstruction","authors":"Qi Wang;Weiwen Wu;Fenglin Liu;Yufang Cai;Yueh Z. Lee;Youzuo Lin;Zirong Li;Yinan Feng;Jianping Lu;Christina R. Inscoe;Ge Wang","doi":"10.1109/TRPMS.2026.3658816","DOIUrl":"https://doi.org/10.1109/TRPMS.2026.3658816","url":null,"abstract":"Stationary head computed tomography (sHCT) plays a critical role in detecting intracranial lesions. However, its fixed gantry restricts projection angles and undermines reconstruction accuracy. Recent studies have shown that score-based generative models (SGMs) can restore high-quality images from limited projections in 2-D limited-angle CT. Extending SGMs to 3-D sHCT is still challenging, as achieving high-resolution images without incurring excessive computational cost remains an open problem. To address this challenge, this study proposes a mutually orthogonal plane-based optical-flow-regulated (MOPO) diffusion model that effectively balances sampling efficiency and reconstruction accuracy. Specifically, we establish a 3-D artifact-aware framework that incorporates a cross-plane attention mechanism to explicitly model and mitigate interslice artifact propagation. Furthermore, we design a mutually orthogonal plane-based (MOP) accelerated sampler capable of reducing the sampling process to as few as 10–20 steps. This approach achieves up to a <inline-formula> <tex-math>$160times $ </tex-math></inline-formula> speedup while maintaining high reconstruction accuracy. To ensure global consistency, an anisotropic optical flow (AOF) regularization is introduced, constructing nonrigid displacement fields between adjacent slices for structural coherence. The experimental results demonstrate that the MOPO-based framework outperforms existing methods in artifact suppression, detail preservation, and computational efficiency, providing a novel solution for high-fidelity and accelerated sHCT reconstruction.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 7","pages":"1024-1036"},"PeriodicalIF":3.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tri-Domain Filtering Transformer for CT Metal Artifact Reduction","authors":"Pengju Liu;Hongzhi Zhang;Chunwei Tian;Feng Jiang;Yudong Zhang;Wangmeng Zuo","doi":"10.1109/TRPMS.2025.3643857","DOIUrl":"https://doi.org/10.1109/TRPMS.2025.3643857","url":null,"abstract":"Current computed tomography (CT) metal artifact reduction (MAR) methods struggle with real-world clinical applications due to their inability to adapt to diverse scanner parameterizations and imaging protocols. These methods often rely on rigid cross-domain operations, such as image-level concatenation or sequential domain conversion, leading to spectral-phase discontinuities and geometric misalignments that may limit artifact suppression in complex cases. To overcome this, we propose the tri-domain filtering transformer for CT MAR (TFT-MAR), which explores feature-granular tri-domain synergy (spatial, spectral, and sinogram-feature domains). First, spatial–spectral–sinogram mixing filtering (S3MF) replaces conventional image-level operations with feature-granular filters, where spatial modules suppress fine-grained artifacts, spectral operators enforce global intensity consistency, and Radon-aware units dynamically adapt to projection physics. Second, the cross-domain self-attention mechanism (CDSA) bridges these domains via physics-constrained token interaction, resolving parameter mismatches by synchronizing texture preservation and geometric constraints. Third, a dual-stream global–local gated feed-forward network (GLGFN) disentangles global spectral dependencies and local edge patterns, preventing high-frequency distortions during multidomain fusion. Rigorous experiments on the synthesized DeepLesion and clinical metal-implant benchmarks, along with radiologist study and extension to MRI super-resolution, demonstrate that TFT-MAR outperforms existing CT MAR techniques while exhibiting robust generalizability. It preserves microstructural details critical for diagnosis, as supported by radiologist evaluations that indicate improved clinical usability.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"10 6","pages":"872-887"},"PeriodicalIF":3.8,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148442433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}