IEEE Transactions on Radiation and Plasma Medical Sciences最新文献_第9页

IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information IEEE辐射与等离子体医学科学汇刊信息

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-12-31 DOI: 10.1109/TRPMS.2025.3644423

引用次数: 0

IEEE Transactions on Radiation and Plasma Medical Sciences Information for Authors IEEE辐射与等离子体医学科学汇刊作者信息

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-12-31 DOI: 10.1109/TRPMS.2025.3644465

引用次数: 0

IEEE DataPort IEEE DataPort

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-12-31 DOI: 10.1109/TRPMS.2025.3644469

引用次数: 0

2025 Index IEEE Transactions on Radiation and Plasma Medical Sciences 2025年IEEE辐射与等离子体医学科学汇刊

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-10 DOI: 10.1109/TRPMS.2025.3630358

引用次数: 0

DG-DiT: Dual-Branch Gating Diffusion Transformer for Multi-Tracer and Multi-Scanner Brain PET Image Denoising. DG-DiT：用于多示踪和多扫描仪脑PET图像去噪的双支路门控扩散变压器。

IF 3.8

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-07 DOI: 10.1109/trpms.2025.3630161

Ziyuan Zhou, Fan Yang, Tzu-An Song, Bowen Lei, Yubo Zhang, Joyita Dutta

{"title":"DG-DiT: Dual-Branch Gating Diffusion Transformer for Multi-Tracer and Multi-Scanner Brain PET Image Denoising.","authors":"Ziyuan Zhou, Fan Yang, Tzu-An Song, Bowen Lei, Yubo Zhang, Joyita Dutta","doi":"10.1109/trpms.2025.3630161","DOIUrl":"10.1109/trpms.2025.3630161","url":null,"abstract":"<p><p>Diffusion probabilistic models (DPMs) have been demonstrated to be effective for denoising positron emission tomography (PET) images due to their ability to model complex data distributions. However, limitations in efficiency, accuracy, and generalizability remain open challenges in this area. In PET denoising, where high fidelity to the ground truth is critical, DPMs often require a large number of iterations and tend to offer limited quantitative accuracy. Moreover, traditional DPMs struggle to model variabilities in the data distribution arising from the use of multiple scanners and tracers. To address these issues, we propose a dual-branch gating diffusion transformer (DG-DiT) network for multi-tracer and multi-scanner PET denoising. The proposed DG-DiT exploits the strong distribution modeling capabilities of a diffusion transformer (DiT) to learn prior knowledge from a compact and regularized latent space. The design of the latent space enables efficient few-step diffusion. In addition, an image restoration transformer (IRT) model is employed for generating the final denoised image. The DiT backbone and the IRT both utilize a dual-branch gating mechanism to efficiently fuse information from multiple inputs. We conducted extensive experiments on multi-tracer and multi-scanner datasets. The results demonstrate that the proposed DG-DiT model achieves the highest quantitative accuracy across every scanner and tracer, with a PSNR improvement of up to 0.2 dB compared to several state-of-the-art deep learning models. Contrast-to-noise ratio evaluation shows that the proposed model is able to recover contrast in small and critical brain regions while effectively reducing noise. This suggests that the proposed DG-DiT model can consistently deliver superior denoising performance.</p>","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":" ","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12931958/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147311111","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}

引用次数: 0

IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information IEEE辐射与等离子体医学科学汇刊信息

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-04 DOI: 10.1109/TRPMS.2025.3623747

引用次数: 0

IEEE DataPort IEEE DataPort

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-04 DOI: 10.1109/TRPMS.2025.3624770

引用次数: 0

>Member Get-a-Member (MGM) Program >米高梅会员入会计划

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-04 DOI: 10.1109/TRPMS.2025.3624772

引用次数: 0

IEEE Transactions on Radiation and Plasma Medical Sciences Information for Authors IEEE辐射与等离子体医学科学汇刊作者信息

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-11-04 DOI: 10.1109/TRPMS.2025.3623749

引用次数: 0

IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information IEEE辐射与等离子体医学科学汇刊信息

IF 3.5

IEEE Transactions on Radiation and Plasma Medical Sciences Pub Date : 2025-09-05 DOI: 10.1109/TRPMS.2025.3599622

引用次数: 0