IEEE transactions on medical imaging最新文献

{"title":"Multi-Granularity Adversarial Generation Integrated Consistency Representation for Chest Low-Contrast-Enhanced CT Synthesis","authors":"Lin Zhao;Shangwen Yang;Dianlin Hu;Zhan Wu;Huazhong Shu;Chunfeng Yang;Jean-Louis Coatrieux;Yang Chen","doi":"10.1109/TMI.2026.3677497","DOIUrl":"10.1109/TMI.2026.3677497","url":null,"abstract":"Contrast-enhanced CT (CECT) is essential for clinical evaluation of vessel structures and function. However, high contrast agent dose increases the risk of renal injury. Reducing contrast agent dose decreases the contrast between vessels and surrounding tissues, which complicates diagnosis. Despite their potential in CECT synthesis, existing methods often suffer from edge unclarity, contrast anomalies, and texture distortion, limiting their clinical applicability. This paper proposes a novel Multi-granularity Adversarial Generation Integrated Consistency Representation (MAGIC) for high-quality synthesis from low-contrast-enhanced CT to clinical usable CECT. MAGIC addresses current problems through four innovations: 1) Multi-Granularity Refined Booster (MRB) introduces contextual refinement and cross granularity boosting mechanisms for mining the multi-granularity contextual information to enhance feature representation capability, thus improving tissue edge clarity. 2) Supervised Contrast Enhancement Module (SCEM) imbues MAGIC with the ability to enhance tissue contrast, which leverages supervised images to adaptively adjust the contrast information of soft tissue structures and vessels, effectively overcoming the challenge of contrast anomalies. 3) Hierarchical Harmonized Consistency Representation (HHCR) utilizes domain consistency to construct a novel auxiliary loss for harmonizing the semantic and content relationships of multi-level hierarchical features to improve tissue texture performance, ensuring accurate restoration of real textures. 4) Dual-path Dynamic Collaborative Discriminator (DDCD) is designed with complementary strategies and injects content priors to dynamically collaborate the discrimination process, thereby comprehensively evaluating the fidelity of the synthesized results. Qualitative and quantitative results demonstrate that MAGIC significantly outperforms existing methods in edge clarity, image contrast, and texture restoration, underscoring its substantial clinical potential.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"4907-4922"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147507550","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":"Active Noise Cancellation in Ultra-Low Field MRI: Distinct Strategies for Different Channels","authors":"Jiali He;Sheng Shen;Jiamin Wu;Yamei Dai;Liang Tan;Zheng Xu","doi":"10.1109/TMI.2026.3714814","DOIUrl":"10.1109/TMI.2026.3714814","url":null,"abstract":"Ultra-low field magnetic resonance imaging (ULF-MRI) systems operating in open environments are highly susceptible to composite electromagnetic interference (EMI). Different imaging channels respond non-uniformly to EMI owing to their distinct coupling characteristics. Here, we investigate channel-specific interference pathways in a permanent–magnet–based low-field MRI system and show that saddle coils are intrinsically more vulnerable to transverse EMI components than solenoidal coils. To mitigate these heterogeneous coupling effects, we propose a dual-stage suppression strategy that combines front-end spatial-domain inverse field reconstruction with back-end channel-adaptive active noise cancellation. Experiments demonstrate that this approach suppresses EMI by more than 80%, substantially improves inter-channel signal-to-noise ratio (SNR) consistency, and enhances the fused-image SNR by ~24%. These findings elucidate the channel-dependent nature of EMI coupling and establish targeted mitigation strategies, providing both a theoretical basis and practical guidance for noise suppression in future array-coil ULF-MRI systems.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5084-5096"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148522576","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":"DiffShape: Decoupling Shape Priors With Conditional Diffusion for Robust Brain Extraction","authors":"Yifan Li;Zizheng Li;Haoyu Wang;Yuchen Lu;Carola-Bibiane Schönlieb;Chao Li;Xi Chen","doi":"10.1109/TMI.2026.3716658","DOIUrl":"10.1109/TMI.2026.3716658","url":null,"abstract":"Skull stripping is a critical preprocessing step for reliable neuroimaging analysis. Although recent deep learning methods have made remarkable progress in accurate brain extraction, their generalization capability remains limited across heterogeneous imaging protocols and diverse pathological conditions. This limitation arises from their predominant reliance on voxel-intensity information without incorporating explicit anatomical constraints. To address this issue, we introduce DiffShape, a conditional diffusion framework that explicitly <italic>decouples</i> brain shape generation from direct voxel-wise intensity-to-label prediction and uses the generated shape as a prior to strengthen existing skull-stripping models. Specifically, DiffShape represents brain geometry using a one-dimensional polar–radius vector, providing a compact and tractable shape representation that enables efficient diffusion modeling over a learned low-dimensional shape manifold. Conditioning the diffusion process on the input image, DiffShape learns a noise-to-shape denoising trajectory that progressively transforms random noise into anatomically plausible brain geometries. The input image serves as a conditioning signal that steers the denoising trajectory toward patient-specific geometry, while the learned diffusion dynamics drive noisy shape samples toward high-probability regions of the conditional brain shape distribution, thereby preserving anatomical plausibility under heterogeneous contrasts or pathological variations. We evaluate DiffShape across datasets containing both healthy and pathological cases, and it consistently improves segmentation accuracy over state-of-the-art skull-stripping methods, demonstrating a promising direction for enhancing segmentation generalization in medical imaging.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5178-5190"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11623311","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148586369","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":"Controllable Echocardiogram Video Generation Driven by Fine-Grained Cardiac Motion","authors":"Jinduo Wang;Zhi Lu;Binquan Wang;Dongheng Zhang;Yang Hu;Da Zhu;Xiangbin Pan;Yan Chen","doi":"10.1109/TMI.2026.3713406","DOIUrl":"10.1109/TMI.2026.3713406","url":null,"abstract":"Echocardiogram video synthesis has emerged as a promising solution to alleviate data scarcity for training intelligent diagnostic models and to enhance clinical education. However, existing methods are typically conditioned on a single scalar metric, such as left ventricular ejection fraction (LVEF), which fails to capture the complex temporal dynamics of cardiac motion and thus limits clinical applicability. To address this limitation, we propose a novel image-to-video synthesis framework guided by left ventricular volume–time curves (VTCs), which provide a more comprehensive representation of cardiac function beyond conventional scalar indicators. Specifically, we develop a VTC-conditioned diffusion model for controllable echocardiogram video generation. Building upon this formulation, we introduce a two-stage architecture, where a latent optical flow module captures motion dynamics, and a conditioned image-to-flow sequence model subsequently generates temporally coherent motion patterns. This design enables efficient echocardiographic video generation with physiologically consistent cardiac dynamics, while the adversarial loss further improves visual fidelity by reducing blurring artifacts. In addition, to address the scarcity of labeled data, we propose a semi-supervised framework for extracting VTCs directly from echocardiogram videos. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance, enabling fine-grained control of cardiac dynamics and advancing the practical applicability of generative models in echocardiography.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"4997-5013"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148441092","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":"Taking a Deep Look at Multi-Rater Agreement for Calibrated Medical Image Segmentation","authors":"Jingjing Li;Huidong Xie;Wei Ji;Zongwei Zhou;Shuang Yu;Junde Wu;Qi Bi;Yefeng Zheng","doi":"10.1109/TMI.2026.3714338","DOIUrl":"10.1109/TMI.2026.3714338","url":null,"abstract":"In medical image analysis, it is common to collect multiple annotations from different clinical experts or raters to mitigate potential diagnostic inaccuracies. However, in computer vision research, it has been conventional to adopt ground-truth labels generated either by majority voting or by selecting a single rater’s annotation. Such practices overlook the rich information embedded in the original multi-rater annotations, particularly the patterns of agreement and disagreement among experts. In this paper, we propose to explicitly model multi-rater (dis-)agreement, referred to as MRNet+, which offers several key innovations. First, an Expertise-aware Inferring Module (EIM) is developed to incorporate the expertise level of each rater as prior knowledge, thereby forming discriminative semantic features. Second, our method efficiently infers inter-observer variability through a disentangled erasing-based Multi-rater Knowledge Modeling (MKM) module. Third, the cues pertaining to multi-rater (dis-)agreement are further leveraged through a Multi-rater Perception Module (MPM) to enhance segmentation performance. To the best of our knowledge, this is the first method to generate calibrated predictions that account for varying expertise levels in medical image segmentation. Moreover, MRNet+ is computationally efficient, achieving real-time performance with a speed of 89 FPS on <inline-formula> <tex-math>$256times 256$ </tex-math></inline-formula> images. We validate our framework across ten medical segmentation tasks spanning diverse imaging modalities. In all cases, MRNet+ consistently outperforms state-of-the-art specialized methods, highlighting its effectiveness and broad applicability to real-world medical image segmentation scenarios. Source code is available at <uri>https://github.com/jiwei0921/MRNet_plus</uri>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5059-5071"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462583","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":"MultiFair: Multimodal Balanced Fairness-Aware Medical Classification With Dual-Level Gradient Modulation","authors":"Md. Zubair;Hao Zheng;Grayson W. Armstrong;Lucy Q. Shen;Gabriela Wilson;Yu Tian;Xingquan Zhu","doi":"10.1109/TMI.2026.3713843","DOIUrl":"10.1109/TMI.2026.3713843","url":null,"abstract":"Medical decision systems increasingly rely on data from multiple sources to ensure reliable and unbiased diagnosis. However, existing multimodal learning models fail to achieve this goal because they often overlook two critical challenges. First, various data modalities may learn unevenly, thereby converging to a model biased towards certain modalities. Second, the model may emphasize learning on certain demographic groups causing unfair performances. The two aspects can influence each other, as different data modalities may favor respective groups during optimization, leading to both imbalanced and unfair multimodal learning. This paper proposes a novel approach called <italic>MultiFair</i> for multimodal medical classification, which addresses these challenges with a dual-level gradient modulation process. MultiFair dynamically modulates training gradients regarding the optimization direction and magnitude at both data modality and group levels. We evaluate MultiFair on three real-world medical classification datasets with diverse demographic attributes, including multiclass classification and missing-modality settings. Experimental results demonstrate its effectiveness.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"5041-5058"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148458255","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":"Polarization-Sensitive Module for Optical Coherence Tomography Instruments","authors":"Po-Yi Lee;Chuan-Bor Chueh;Milen Shishkov;Sebastián Ruiz-Lopera;Tai-Ang Wang;Hsiang-Chieh Lee;Teresa Chen;Brett E. Bouma;Martin Villiger","doi":"10.1109/TMI.2026.3713071","DOIUrl":"10.1109/TMI.2026.3713071","url":null,"abstract":"Polarization-sensitive optical coherence tomography (PS-OCT) extends OCT by analyzing the polarization states of backscattered light to quantify tissue birefringence. However, conventional implementations require polarization-diverse detection and are therefore incompatible with most commercial OCT systems. As a result, PS-OCT has largely remained restricted to specialized research groups, limiting its broader scientific and clinical use. Here, we present a modular PS-OCT framework that integrates with a standard spectral-domain OCT platform through a detachable rotating achromatic half-wave plate in the sample arm. This waveplate modulates both incident and reflected polarization states. Three or more repeated measurements at distinct waveplate orientations enable reconstruction of the sample’s round-trip Jones matrix and the corresponding polarization properties. To mitigate random phase variations between repeated measurements, we introduce a phase optimization strategy. We validate the framework with imaging of birefringent phantoms and the human retina <italic>in vivo</i>, demonstrating reliable reconstruction of retardance and optic axis orientation. In this study, we implemented a polarization-sensitive module on the SPECTRALIS platform with minimal hardware modification. The framework could be extended to other OCT systems with appropriate mechanical integration and access to acquisition data. By reducing the hardware complexity typically associated with conventional PS-OCT, this framework may facilitate broader adoption of PS-OCT imaging in both research and clinical settings.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"4985-4996"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148432025","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":"RADAR: A Difference-Aware Retrieval With Organ-Level Alignment for Change Radiology Report Generation","authors":"Yizhi Pan;Guanqun Sun;Yingying Zhu;Haitao Jiang;Han Shu;Le Minh Nguyen","doi":"10.1109/TMI.2026.3712240","DOIUrl":"10.1109/TMI.2026.3712240","url":null,"abstract":"Automated report generation is limited to static, single-image analysis, failing to address the critical clinical need for longitudinal comparison in monitoring disease progression and treatment efficacy. To bridge this gap, we introduce the new task of Change Radiology Report Generation (CRRG) which aims to automatically generate a comparative radiology report describing interval changes between a patient’s current and prior radiological images. To address this challenge, we propose RADAR, a novel framework that integrates deep visual comparison with knowledge-rich text generation. For robust visual analysis, RADAR employs an “align first, then compare” strategy via an organ-level alignment module, to first mitigate non-pathological artifacts before precisely identifying key pathological changes. Our text generation framework integrates soft prompts for visual evidence with a structured four-step workflow for clinical reasoning. Factual accuracy is enhanced by our Knowledge-Infused Generation (KIG) component, which dynamically retrieves knowledge from a database of similar pathological cases. To anchor our newly proposed task of CRRG and facilitate robust evaluation, we introduce the first comprehensive benchmark, featuring a meticulously curated and processed dataset. Extensive experiments on our benchmark demonstrate that RADAR outperforms existing methods on most evaluation metrics. Our work successfully elevates automated radiological assessment from static analysis to dynamic monitoring, producing interpretable and clinically relevant change reports for longitudinal comparison.","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"45 10","pages":"4954-4969"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148432021","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":"Message in a Bottleneck: Interpretable Deep Learning for Dynamic Effective Brain Connectivity.","authors":"Pavel Popov, Cristian Morasso, Giorgio Dolci, Ilaria Boscolo Galazzo, Godfrey Pearlson, David Danks, Vince Calhoun, Gloria Menegaz, Sergey Plis","doi":"10.1109/TMI.2026.3735891","DOIUrl":"10.1109/TMI.2026.3735891","url":null,"abstract":"<p><p>Deep learning (DL) approaches find increasingly more applications in medical imaging analysis, where they excel at predictive tasks such as diagnosis classification, but often offer little insight on the underlying mechanisms governing complex systems, a key goal of scientific inquiry. One way to bridge this gap is to design DL architectures for modeling the underlying system reflected in imaging data, which can give insights into the system through the analysis of fitted models. In this spirit, we present a novel approach for deep extraction of causally informed features via restricted architecture (DECIFRA), designed for multivariate time series modeling. DECIFRA introduces an interpretable bottleneck in its computation flow, where dynamically generated transition matrices exclusively model the directed influences between channels over time. These matrices function as both the model's internal computational mechanism and its primary, interpretable output that gives insights into the cross-channel interactions. To validate our method, we apply it to the challenging task of learning dynamic brain connectivity from functional magnetic resonance imaging (fMRI) data. We demonstrate that DECIFRA learns stable, reproducible connectivity patterns that are discriminative for group-level analysis. Moreover, these learned dynamics can be fine-tuned for specific classification tasks, improving predictive performance while retaining interpretability. Our findings show that DECIFRA captures functionally grounded brain connectivity patterns, with certain dynamics associated with age or schizophrenia classification tasks and others consistently preserved across tasks.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042970","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":"Dictionary-based Pathology Mining with Hard-instance-assisted Classifier Debiasing for Genetic Biomarker Prediction from WSIs.","authors":"Ling Zhang, Boxiang Yun, Ting Jin, Qingli Li, Xinxing Li, Yan Wang","doi":"10.1109/TMI.2026.3735360","DOIUrl":"10.1109/TMI.2026.3735360","url":null,"abstract":"<p><p>Prediction of genetic biomarkers, e.g., microsatellite instability in colorectal cancer is crucial for clinical decision making. However, two primary challenges hamper accurate prediction: (1) It is difficult to construct a pathology-aware representation involving the complex interconnections among pathological components. (2) Whole slide images contain a large proportion of areas unrelated to genetic biomarkers, which make the model easily overfit simple but irrelevant instances. We hereby propose a dictionary-based hierarchical pathology mining with hard-instance-assisted classifier debiasing framework to address these challenges, dubbed as D²Bio. Our first module, dictionary-based hierarchical pathology mining, is able to mine diverse and very fine-grained pathological contextual interaction without the limit to the distances between patches. The second module, hard-instance-assisted classifier debiasing, learns a debiased classifier via focusing on hard but task-related features, without any additional annotations. Experimental results on five cohorts show the superiority of our method, with over 4% improvement in AUROC compared with the second best on the TCGA-CRC-MSI cohort. Our analysis further shows the clinical interpretability of D²Bio in genetic biomarker diagnosis and potential clinical utility in survival analysis. Code, patient-level dataset splits, patch coordinates, and preprocessing scripts will be available at https://github.com/DeepMed-Lab-ECNU/D2Bio.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149032287","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}