IEEE transactions on medical imaging最新文献_第8页

EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery. EndoMatcher：基于多域预训练的机器人辅助手术内镜图像匹配器。

IEEE transactions on medical imaging Pub Date : 2026-08-06 DOI: 10.1109/TMI.2026.3721133

Bingyu Yang, Qingyao Tian, Yimeng Geng, Huai Liao, Xinyan Huang, Jiebo Luo, Hongbin Liu

{"title":"EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery.","authors":"Bingyu Yang, Qingyao Tian, Yimeng Geng, Huai Liao, Xinyan Huang, Jiebo Luo, Hongbin Liu","doi":"10.1109/TMI.2026.3721133","DOIUrl":"10.1109/TMI.2026.3721133","url":null,"abstract":"Generalizable dense feature matching in endoscopic images is crucial for robot-assisted tasks, including 3D reconstruction, navigation, and surgical scene understanding. Yet, it remains challenging due to difficult visual conditions (e.g., weak textures, large viewpoint variations) and scarce annotated data. To address these challenges, we propose EndoMatcher, a generalizable endoscopic image matcher via large-scale, multi-domain data pre-training. EndoMatcher employs a two-branch Vision Transformer to extract multi-scale features, enhanced by dual interaction blocks for robust correspondence learning under difficult visual conditions. To overcome data scarcity and improve domain diversity, we construct Endo-Mix6, the first multi-domain dataset for endoscopic matching. Endo- Mix6 consists of approximately 1.2M real and synthetic image pairs across six domains, each corresponding to a distinct endoscopic data source or imaging scenario. Correspondence labels are generated through Structure-from-Motion and simulated transformations. The scale and cross-domain heterogeneity of Endo-Mix6 introduce new training challenges due to significant variations in dataset sizes, distribution shifts, and label noise. To ensure stable optimization, we adopt a progressive multi-objective training strategy that adaptively balances supervision across domains. This enhances feature learning and enables generalization to unseen organs and imaging conditions in a zero-shot fashion. Extensive zero-shot matching experiments demonstrate that EndoMatcher increases the number of inlier matches by 140.69% and 201.43% on the Hamlyn Centre and Bladder Tissue datasets over state-of-the-art methods, respectively, and improves the Matching Direction Prediction Accuracy (MDPA) from 76.0% to 85.4% on the Gastro-Matching dataset, achieving dense and accurate matching under challenging endoscopic conditions. The code is publicly available at https://github.com/Beryl2000/EndoMatcher.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687151","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}

引用次数: 0

Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline. 虚拟染色组织学中的幻觉检测：潜在空间基线。

IEEE transactions on medical imaging Pub Date : 2026-08-06 DOI: 10.1109/TMI.2026.3720925

Ji-Hun Oh, Kianoush Falahkheirkhah, John Cheville, Rohit Bhargava

引用次数: 0

Exploring the Connection between Uncertainty and Tissue Boundaries in Medical Image Segmentation. 医学图像分割中不确定度与组织边界关系的探讨。

IEEE transactions on medical imaging Pub Date : 2026-08-06 DOI: 10.1109/TMI.2026.3720501

Na Zeng, Qiao Lin, Xingyue Wang, Jiang Liu, Jonathan M Garibaldi

{"title":"Exploring the Connection between Uncertainty and Tissue Boundaries in Medical Image Segmentation.","authors":"Na Zeng, Qiao Lin, Xingyue Wang, Jiang Liu, Jonathan M Garibaldi","doi":"10.1109/TMI.2026.3720501","DOIUrl":"https://doi.org/10.1109/TMI.2026.3720501","url":null,"abstract":"Automatic medical image segmentation, as a prerequisite for clinical quantitative analysis, forms the basis of computer-aided diagnosis. However, blurry object boundaries caused by factors such as imaging quality and inherent physiological properties of tissues or lesions are the main causes of imprecise segmentation. This aligns with the common understanding that high uncertainty and misclassification tend to occur at boundaries in segmentation. To address the challenge, we investigate this phenomenon and explore the connection between uncertainty and tissue boundaries by analysing various tissues. Then an Evidential Uncertainty-Guided Boundary (EUGB) loss is further proposed to demonstrate that uncertainty information can indeed facilitate combating boundary segmentation errors. The proposed EUGB loss not only emphasizes challenging pixels along blurry boundaries using evidential uncertainty, but also introduces a regularization term that constrains uncertainty learning by penalizing incorrect predictions and reinforcing correct ones. The effectiveness of the proposed EUGB loss is verified in the public LIDC-IDRI, ISIC 2018, and OCTA-500 datasets with two classic medical image segmentation networks (U-Net and TransU-Net). Experimental results demonstrate that the proposed loss outperforms seven other segmentation loss functions in terms of boundary segmentation, while maintaining competitive region-level segmentation accuracy. Beyond introducing a new loss function, this paper provides empirical insights for selecting appropriate loss functions across different application scenarios. We systematically analyze the strengths and limitations of existing losses from multiple perspectives, including reliability and dataset characteristics. This analysis offers practical insights that enable researchers and practitioners to optimize segmentation performance based on specific data attributes.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148687224","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}

引用次数: 0

End-to-End Differentiable Photon Counting CT. 端到端可微光子计数CT。

IEEE transactions on medical imaging Pub Date : 2026-08-05 DOI: 10.1109/TMI.2026.3720353

Sen Wang, Yirong Yang, Jooho Lee, Grant M Stevens, Adam S Wang

{"title":"End-to-End Differentiable Photon Counting CT.","authors":"Sen Wang, Yirong Yang, Jooho Lee, Grant M Stevens, Adam S Wang","doi":"10.1109/TMI.2026.3720353","DOIUrl":"10.1109/TMI.2026.3720353","url":null,"abstract":"Quantitative imaging is an important feature of spectral X-ray and CT systems, especially photon-counting CT (PCCT) imaging systems, which is achieved through material decomposition (MD) using spectral measurements. In this work, we present a novel framework that makes the PCCT imaging chain end-to-end differentiable (differentiable PCCT), with which we can leverage quantitative information in the image domain to enable cross-domain learning and optimization for upstream models. Specifically, the material decomposition from maximum-likelihood estimation (MLE) was made differentiable based on the Implicit Function Theorem and inserted as a layer into the imaging chain for end-to-end optimization. This framework allows for an automatic and adaptive solution of a wide range of imaging tasks, ultimately achieving quantitative imaging through computation rather than manual intervention. The end-to-end training mechanism effectively avoids the need for direct-domain training or supervision from intermediate references as models are trained using quantitative images. We demonstrate its applicability in two representative tasks: correcting detector energy bin drift and training an object scatter correction network using cross-domain reference from quantitative material images.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148681757","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}

引用次数: 0

Reverse Imaging: Any-Sequence Generalization for Cardiac MRI Segmentation. 逆向成像：心脏MRI分割的任意序列泛化。

IEEE transactions on medical imaging Pub Date : 2026-08-05 DOI: 10.1109/TMI.2026.3720503

Yidong Zhao, Yi Zhang, Tongyun Yang, Masa Bozic-Iven, Ayda Arami, Yuchi Han, Orlando Simonetti, Hui Xue, Peter Kellman, Sebastian Weingartner, Qian Tao

{"title":"Reverse Imaging: Any-Sequence Generalization for Cardiac MRI Segmentation.","authors":"Yidong Zhao, Yi Zhang, Tongyun Yang, Masa Bozic-Iven, Ayda Arami, Yuchi Han, Orlando Simonetti, Hui Xue, Peter Kellman, Sebastian Weingartner, Qian Tao","doi":"10.1109/TMI.2026.3720503","DOIUrl":"10.1109/TMI.2026.3720503","url":null,"abstract":"Pretrained segmentation models for cardiac magnetic resonance imaging (MRI) often fail to generalize across imaging sequences due to substantial contrast variations. These variations arise from different imaging protocols, yet fundamentally, all contrasts are governed by the same underlying tissue properties, primarily captured by three components: the magnetization strength (M0), T1, and T2. Building on this insight, we introduce Reverse Imaging, a physics-driven framework for data augmentation and domain generalization in cardiac MRI. Our method infers tissue properties from observed MR images with annotation by solving an ill-posed nonlinear inverse problem, regularized by a generative prior. The prior is learned from the multiparametric saturation-recovery single shot acquisition (mSASHA) dataset for joint cardiac T1 and T2 mapping. In inference, we characterize imaging sequences as weak, moderate, or strong observations according to the physical information they provide and the degree of ill-posedness. This motivates an iterative prior-learning strategy that uses moderate T1-mapping observations to alleviate mSASHA data scarcity via pseudo tissue-property estimates. We further integrate MRI physics into posterior inference by expressing the sequence model as a likelihood term guiding the reverse diffusion process. For widely used but weak cine observations, we develop a sequence-specific ControlNet to improve efficiency and spatial consistency. Extensive experiments on eight unseen cardiac MRI sequences with markedly different contrast mechanisms show that Reverse Imaging yields plausible tissue-property estimates, supports synthesis of diverse yet physically consistent contrasts, and improves segmentation robustness under severe cross-sequence shifts.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148681739","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}

引用次数: 0

Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report. 基于CT和放射学的精细多模态融合用于喉咽癌t分期预测。

IEEE transactions on medical imaging Pub Date : 2026-08-03 DOI: 10.1109/TMI.2026.3719112

Xingyue Zhao, Yanzhou Su, Fang Zhang, Zhanghexuan Ji, Yirui Wang, Dazhou Guo, Sibo Ju, Yuehua Cheng, Yuzhen Chen, Ming Feng, Le Lu, Tsung-Ying Ho, Jian Wang, Dakai Jin, Na Shen

{"title":"Anatomy-aware Fine-grained Multimodal Fusion for Laryngopharyngeal Cancer T-Staging Prediction Using CT and Radiology Report.","authors":"Xingyue Zhao, Yanzhou Su, Fang Zhang, Zhanghexuan Ji, Yirui Wang, Dazhou Guo, Sibo Ju, Yuehua Cheng, Yuzhen Chen, Ming Feng, Le Lu, Tsung-Ying Ho, Jian Wang, Dakai Jin, Na Shen","doi":"10.1109/TMI.2026.3719112","DOIUrl":"10.1109/TMI.2026.3719112","url":null,"abstract":"Accurate T-staging is crucial for guiding personalized treatment strategies for laryngopharyngeal cancer. However, current clinical practice relies on invasive biopsy procedures, whereas CT-based staging remains challenging due to the complex patterns of tumor invasion. Recent computer-aided approaches face two key challenges: 1) Structural relationship modeling: existing methods underrepresent anatomically structured patterns of tumor invasion, as they either process whole CT volumes without tumor-specific anatomical constraints or rely on labor-intensive tumor segmentation. 2) Fine-grained cross-modal alignment: while radiology reports contain organ-specific invasion details, current methods that apply global feature fusion struggle to accurately align individual anatomical structures with their corresponding textual descriptions. To address these issues, we propose an anatomy-aware multimodal framework that integrates organ-level CT context and radiology reports into a unified representation for laryngopharyngeal T-staging. The framework first constructs an Anatomy-Structured Organ Graph (AOG) that captures invasion patterns between primary sites and surrounding organs, then performs Organ-Anchored Cross-Modal Alignment (OCA) so that each organ node aggregates textual evidence from the radiology report, and finally refines this graph representation by injecting organ-specific invasion cues extracted from the report via Report-Enhanced Graph-Refinement (REG), yielding a multimodal organ graph that combines spatial and textual evidence. Extensive experiments demonstrate that the proposed framework achieves superior performance in T-staging of laryngopharyngeal cancer.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148671640","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}

引用次数: 0

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models. MedHallTune：在视觉语言模型中减轻医学幻觉的指令调整基准。

IEEE transactions on medical imaging Pub Date : 2026-08-03 DOI: 10.1109/TMI.2026.3719326

Qiao Yan, Yuchen Yuan, Xiaowei Hu, Yihan Wang, Jiaqi Xu, Xiwen Wu, Jinpeng Li, Chi-Wing Fu, Pheng-Ann Heng

{"title":"MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models.","authors":"Qiao Yan, Yuchen Yuan, Xiaowei Hu, Yihan Wang, Jiaqi Xu, Xiwen Wu, Jinpeng Li, Chi-Wing Fu, Pheng-Ann Heng","doi":"10.1109/TMI.2026.3719326","DOIUrl":"10.1109/TMI.2026.3719326","url":null,"abstract":"The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which the models may generate seemingly plausible results that are in fact incorrect. Such hallucinations can jeopardize clinical decision making, potentially harming the diagnosis and treatments. In this work, we propose MedHallTune, a large-scale benchmark designed specifically to evaluate and mitigate hallucinations in medical VLMs. Comprising over 100,000 images and 1,000,000 instruction pairs, MedHallTune includes both hallucination and non-hallucination samples. While the dataset is primarily constructed using GPT-based generation and filtering, the evaluation split is manually verified by medical students and physicians to ensure annotation correctness and clinical reliability. We conduct a comprehensive evaluation of current medical and general VLMs using MedHallTune, assessing their performance across key metrics, including clinical accuracy, relevance, detail level, and risk level. The experimental results show that fine-tuning with MedHallTune successfully improves the ability of several existing models to manage hallucinations and boost their zero-shot performance on downstream visual-question-answering tasks, making them more reliable for practical medical applications. Our work contributes to the development of more trustworthy VLMs. The benchmark, evaluation codes and data construction prompts will be made publicly available at MedHallTune.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148671718","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}

引用次数: 0

Prediction of Articular Cartilage Markers With Multispectral Imaging 多光谱成像预测关节软骨标志物。

IEEE transactions on medical imaging Pub Date : 2026-08-01 Epub Date: 2026-06-12 DOI: 10.1109/TMI.2026.3703024

Eloi Canals Pascual;Hamidreza Masjedi;Akuroma Tolvanen;Petri Paakkari;Miika Kiema;Arash Mirhashemi;Ervin Nippolainen;Johanna P. Laakkonen;Juha Töyräs;Isaac O. Afara

{"title":"Prediction of Articular Cartilage Markers With Multispectral Imaging","authors":"Eloi Canals Pascual;Hamidreza Masjedi;Akuroma Tolvanen;Petri Paakkari;Miika Kiema;Arash Mirhashemi;Ervin Nippolainen;Johanna P. Laakkonen;Juha Töyräs;Isaac O. Afara","doi":"10.1109/TMI.2026.3703024","DOIUrl":"10.1109/TMI.2026.3703024","url":null,"abstract":"Osteoarthritis (OA) is a debilitating joint disease in which early microstructural and compositional changes in articular cartilage (AC) are challenging to detect with current diagnostic tools. We hypothesized that multispectral imaging (MSI) could capture optical signatures that predict key AC properties. To test this, we developed and evaluated an MSI-based approach for estimating tissue thickness, proteoglycan (PG) content, collagen fiber orientation, and cell morphological properties (area and circularity). Reflectance images of bovine patellar AC were acquired using a custom-built MSI system operating at six wavelengths (550–970 nm), and machine learning models were trained to predict the targeted markers. The models yielded reliable estimates for AC thickness, whereas for PG content, collagen fiber orientation, and cell circularity, they achieved moderate accuracy. This work suggests that MSI holds promise as a label-free tool for characterizing AC and detecting early degenerative changes.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 8","pages":"4470-4481"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11561006","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148240258","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

Microbubble Track-Based Functional Ultrasound Localization Microscopy in Awake Mice 基于微泡轨迹的清醒小鼠功能超声定位显微镜。

IEEE transactions on medical imaging Pub Date : 2026-08-01 Epub Date: 2026-06-17 DOI: 10.1109/TMI.2026.3704144

Yike Wang;Matthew R. Lowerison;Zhe Huang;YiRang Shin;Bing-Ze Lin;Pengfei Song

{"title":"Microbubble Track-Based Functional Ultrasound Localization Microscopy in Awake Mice","authors":"Yike Wang;Matthew R. Lowerison;Zhe Huang;YiRang Shin;Bing-Ze Lin;Pengfei Song","doi":"10.1109/TMI.2026.3704144","DOIUrl":"10.1109/TMI.2026.3704144","url":null,"abstract":"Functional neuroimaging with ultrafast ultrasound is an emerging neuroimaging tool for studying neural activities in the rodent brain. Existing methods, however, are challenged by the compromise between functional imaging sensitivity (i.e., sensitivity in detecting neural responses) and spatial resolution. For example, functional ultrasound (fUS) uses native red blood cells (RBCs) as imaging targets, which offers high functional imaging sensitivity but limited spatial resolution that is confined by the diffraction limit of ultrasound. On the other hand, functional ultrasound localization microscopy (fULM) employs intravenously injected microbubble (MB) as contrast agent to achieve super-resolved spatial resolution but at the cost of functional imaging sensitivity. This study aims to address this challenge by developing a novel, MB track-based hemodynamic activity estimation method to enhance the functional imaging sensitivity of fULM. Our approach involves conducting functional correlation analysis using the MB signals acquired from the entire MB movement track rather than individual MB centroid locations, which overcomes the signal sparsity issue in fULM. To further boost the functional sensitivity of fULM, we developed a novel approach based on indwelling jugular vein catheters to achieve fULM imaging in awake mice. The <italic>in vivo imaging results demonstrate that the proposed techniques successfully enhanced the functional imaging sensitivity of fULM without compromising its high spatial resolution. In the whisker stimulation experiments, the proposed technique enabled detection of significantly activated brain regions within fewer than five stimulation cycles (5 minutes of acquisition), reducing the required time by over 50% compared to conventional fULM.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 8","pages":"4518-4531"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11569101","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274432","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

A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter 基于等效高阶散射的多源CT神经解析融合散射校正方法。

IEEE transactions on medical imaging Pub Date : 2026-08-01 Epub Date: 2026-06-24 DOI: 10.1109/TMI.2026.3706711

Jiancong Dai;Yuxin Gao;Yingyin Zeng;Hangji Lin;Xiaoying Zhang;Shaoyong Tian;Zengxiang Pan;Jianhui Ma;Linghong Zhou;Xiaoman Duan;Guohua Cao;Yuan Xu

{"title":"A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter","authors":"Jiancong Dai;Yuxin Gao;Yingyin Zeng;Hangji Lin;Xiaoying Zhang;Shaoyong Tian;Zengxiang Pan;Jianhui Ma;Linghong Zhou;Xiaoman Duan;Guohua Cao;Yuan Xu","doi":"10.1109/TMI.2026.3706711","DOIUrl":"10.1109/TMI.2026.3706711","url":null,"abstract":"Multi-source computed tomography (MSCT) significantly improves temporal resolution but suffers from severe forward and cross scatter artifacts. Software-based scatter correction methods avoid additional hardware costs and radiation dose; however, model-based methods struggle with high-order scatter estimation, while deep learning–based methods lack physical constraints. To address these limitations, we propose a neural-analytical fusion (NAF) scatter correction method. Specifically, first-order Compton and Rayleigh scatter are analytically estimated using a GPU-accelerated physics model-based method. For high-order scatter, the multi-step scattering process is reformulated as an equivalent single-step interaction, and an equivalent high-order cross-section prediction network (EHCP-Net) is embedded within the analytical model to enable fast and physically constrained estimation of high-order scatter. The proposed method is validated on simulated and real data under different scanning geometries. Compared to the state-of-the-art scatter correction methods, our method demonstrates higher correction accuracy and effectively suppresses high-frequency artifacts. In scatter distribution comparison experiments, it achieved a mean absolute percentage error (MAPE) of less than 3% relative to Monte Carlo (MC) simulations. In scatter correction experiments, it yielded mean absolute errors (MAE) below 20 HU on simulated data, and below 30 HU on real data. The proposed method achieves effective scatter correction with strong physical constraints for MSCT.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 8","pages":"4605-4616"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148313425","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}

引用次数: 0