IEEE transactions on medical imaging最新文献

{"title":"Mechanically Anisotropic Multi-modal Phantoms for Elastography Imaging.","authors":"Samyuktha S Kolluru, Kaden D Bock, Shruthi Srinivasan, Kevin N Eckstein, Wren E Wightman, Ned C Rouze, Juan Manuel Uruena Vargas, Philip V Bayly, Kathryn R Nightingale","doi":"10.1109/TMI.2026.3735475","DOIUrl":"10.1109/TMI.2026.3735475","url":null,"abstract":"<p><p>Mechanical anisotropy is a promising biomarker of tissue health because many tissues contain organized fibrous structures that can be disrupted by injury or disease. Elastographic imaging methods have recently emerged to noninvasively quantify anisotropic mechanical properties in soft fibrous tissues like brain white matter or muscle. Calibrated phantoms that reproduce anisotropic tissue behavior are necessary for clinical translation of these methods, but durable, validated, anisotropic, elastography phantoms are not currently available. To address this need, we fabricated mechanically anisotropic lattice composite phantoms by embedding directionally scaled, 3D-printed, polyethylene glycol diacrylate (PEGDA) lattices in polyacrylamide (PAA) gel matrix. Apparent shear moduli governing deformations parallel and perpendicular to the scaling direction in these phantoms were estimated using magnetic resonance elastography (MRE) and ultrasound shear wave elastography (SWE). The properties of the phantom composite materials were independently characterized by benchtop dynamic shear testing (DST). All measurements were repeated over a four week period to assess stability of the phantoms over time. Both elastography imaging methods (MRE and SWE) detected anisotropy in lattice composite phantoms and identified differences in properties between different phantoms. Some quantitative differences were also observed between estimates of shear moduli and anisotropy obtained by MRE, SWE and DST, attributable to different features of each method. These phantoms and their fabrication protocols are available at the National Medical Phantom Library (NMPL) [1], to serve as assessment and calibration tools for anisotropic elastography imaging methods.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149032280","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":"Comorbidity-Aware Radiology Report Generation.","authors":"Hongze Zhu, Hong Liu, Yawen Huang, Chen Hu, Jiaxuan Jiang, Ming Hu, Xun Lin, Gaoyi Yang, Yefeng Zheng","doi":"10.1109/TMI.2026.3735241","DOIUrl":"10.1109/TMI.2026.3735241","url":null,"abstract":"<p><p>Chest X-ray report generation systems are valuable for assisting disease diagnosis and improving healthcare efficiency. However, existing methods still face two key challenges. First, multiple diseases often co-occur, leading to a combinatorial explosion of label combinations and sparse supervision for learning a generalizable image-to-label mapping. Second, standard autoregressive training is primarily optimized for local linguistic fluency, but provides limited direct supervision for global clinical fidelity, often resulting in omissions or contradictions in complex multi-abnormality cases. To address these issues, we introduce a geometry-aware multimodal large-model framework. The framework leverages hyperbolic geometry as a hierarchy-aware inductive bias and applies hierarchy-consistent constraints at three levels: representation, loss, and reinforcement signals. Specifically, we build a hyperbolic contrastive language-image pre-training (CLIP) model to align image-text semantics; estimate class prototypes from single-label cases and perform prototype-driven hyperbolic contrastive learning to enforce radius ordering for multi-label samples; and incorporate a learnable hyperbolic soft reward into the group relative policy optimization (GRPO) framework to directly optimize clinical accuracy. On the MIMIC-CXR benchmark, HyCoRG obtains BLEU-4 of 0.136 as well as clinical F1 of 0.515, indicating improved disease-level clinical consistency. Ablation studies confirm that both the framework and the geometric constraints contribute independently and synergistically. Our approach improves both linguistic quality and diagnostic fidelity, and offers a transferable hierarchy-aware paradigm for multi-label medical text generation. The code is publicly available at https://github.com/hongzezhu/HyCoRG.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003221","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":"SurgDepth: Test-Time Adaptation of Depth Foundation Models for Surgical Scene Understanding.","authors":"Shengyao Wang, Junpei Xue, Xincong Zhong, Yihang Bao, Lingfeng Yao, Jinze Yu, Miao Pan, Jiang Liu","doi":"10.1109/TMI.2026.3734640","DOIUrl":"10.1109/TMI.2026.3734640","url":null,"abstract":"<p><p>Accurate depth estimation from endoscopic images is fundamental to surgical navigation, augmented reality, and robotic assistance, yet depth foundation models trained on natural images degrade severely on surgical endoscopy, and existing adaptation methods require surgical training data for each new camera and clinical environment. We propose SurgDepth, a test-time adaptation (TTA) framework that adapts pre-trained depth foundation models to surgical endoscopy without any labeled surgical data. SurgDepth combines two self-supervised signals-stereo photometric consistency for rectified stereo pairs, and flip equivariance requiring only single images-with selective decoder adaptation and two tuning-free reliability mechanisms: a progress-aware anchor regularization and a structural-trust safeguard for poorly-illuminated sequences. Through the first systematic study of TTA for dense depth regression (eight baselines), we show that existing TTA methods consistently fail in this setting: entropy-based methods degrade regardless of the number of adapted parameters, and temporal-photometric adaptation diverges on non-rigid tissue. SurgDepth reduces AbsRel by up to 63% with stereo pairs and 42% without, improves four of five cross-domain evaluation settings (three of four unseen datasets; Hamlyn is evaluated under two protocols), generalizes across seven foundation models, and attains the lowest AbsRel (0.128) on the complete standard Hamlyn benchmark among all reported methods. All results evaluate relative (median-scaled) depth; 20-step convergence (0.4 s) makes SurgDepth practical for relative-depth applications such as augmented-reality overlay and reconstruction initialization.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148993171","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":"Separation of Water Components from Multi-Echo MRI Data Using Deep Learning-Assisted Subspace Modeling.","authors":"Ruihao Liu, Yudu Li, Yue Guan, Ziwen Ke, Shuoyun Feng, Weijun Tang, Yiping P Du, Yao Li, Zhi-Pei Liang","doi":"10.1109/TMI.2026.3733701","DOIUrl":"10.1109/TMI.2026.3733701","url":null,"abstract":"<p><p>MRI data acquired using multi-echo spin-echo or gradient-echo sequences contain \"encoded\" water signals from various tissue compartments, i.e., myelin, axon, and extracellular space. Accurate separation of these components is desirable for tissue characterization in healthy and diseased states. However, this signal decomposition problem is very challenging because the encoding matrix is highly ill-conditioned and as a result, its solution is often sensitive to noise and practical data perturbations (e.g., B₀ field inhomogeneity). This paper presents a new method to address this problem, which synergistically integrates physics-based spatiotemporal priors and machine learning to constrain the variations allowed for each water component while providing flexibility to capture subject- and experiment-dependent signal changes. Specifically, we introduced a probabilistic union-of-subspaces model with pre-learned spectral bases to enforce temporal constraints while incorporating spatial priors derived from deep learning-based image translation. To further accommodate subject- and experiment-specific signal variations, a generalized series model was employed to adapt the pre-learned subspace model to a specific dataset. With the proposed model and learned priors, water separation was done under the Bayesian statistical framework. Numerical simulations and experimental evaluations demonstrated that the proposed method significantly improved the accuracy of the estimated myelin, axonal, and extracellular water components. The new method will enhance the practical utility of multi-component water imaging for basic neuroscience and clinical applications and also provide a useful framework for separating overlapping spatiotemporal signals.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042471","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":"SAMReg: SAM-enabled Image Registration with ROI-based Correspondence.","authors":"Shiqi Huang, Tingfa Xu, Ziyi Shen, Shaheer Ullah Saeed, Wen Yan, Dean Barratt, Yipeng Hu","doi":"10.1109/TMI.2026.3734150","DOIUrl":"10.1109/TMI.2026.3734150","url":null,"abstract":"<p><p>This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The distinct properties of the proposed ROI-based correspondence are discussed, in the context of potential benefits in clinical applications following image registration, compared with alternative correspondence-representing approaches, such as those based on sampled displacements and spatial transformation functions. These benefits include a clear connection between learning-based image registration and segmentation, which in turn motivates two cases of image registration approaches using (pre-)trained segmentation networks. Based on the segment anything model (SAM), a vision foundation model for segmentation, we develop a new registration algorithm SAMReg, which does not require any training (or training data), gradient-based fine-tuning or prompt engineering. The proposed SAMReg models are evaluated across five real-world applications, including intra-subject registration tasks with cardiac MR and lung CT, challenging inter-subject registration scenarios with prostate MR and retinal imaging, and an additional evaluation with a non-clinical example with aerial image registration. The proposed methods outperform both intensity-based iterative algorithms and DDF-predicting learning-based networks across tested metrics including Dice and target registration errors on anatomical structures, and further demonstrates competitive performance compared to weakly-supervised registration approaches that rely on fully-segmented training data. Open source code and examples are available at SAMReg.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149043009","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":"The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction.","authors":"Lidia Garrucho, Smriti Joshi, Kaisar Kushibar, Richard Osuala, Maciej Bobowicz, Xavier Bargallo, Paulius Jarusevicius, Kai Geissler, Raphael Schafer, Muhammad Alberb, Tony Xu, Anne Martel, Daniel Sleiman, Navchetan Awasthi, Hadeel Awwad, Joan C Vilanova, Robert Marti, Daan Schouten, Jeong Hoon Lee, Mirabela Rusu, Eleonora Poeta, Luisa Vargas, Eliana Pastor, Maria A Zuluaga, Jessica Kachele, Dimitrios Bounias, Alexandra Ertl, Katarzyna Gwozdziewicz, Maria-Laura Cosaka, Pasant M Abo-Elhoda, Sara W Tantawy, Shorouq S Sakrana, Norhan O Shawky-Abdelfatah, Amr Muhammad Abdo-Salem, Androniki Kozana, Eugen Divjak, Gordana Ivanac, Katerina Nikiforaki, Michail E Klontzas, Rosa Garcia-Dosda, Meltem Gulsun-Akpinar, Oguz Lafci, Carlos Martin-Isla, Oliver Diaz, Laura Igual, Karim Lekadir","doi":"10.1109/TMI.2026.3733343","DOIUrl":"10.1109/TMI.2026.3733343","url":null,"abstract":"<p><p>Breast cancer is the most frequently diagnosed malignancy among women worldwide and a leading cause of cancer-related mortality. Dynamic contrast-enhanced magnetic resonance imaging plays a central role in tumor characterization and treatment monitoring, particularly in patients receiving neoadjuvant chemotherapy. However, existing artificial intelligence models for breast magnetic resonance imaging are typically developed and evaluated using heterogeneous datasets, study populations, and assessment protocols, making direct comparison difficult and limiting understanding of model robustness across institutions and clinically relevant patient subgroups. The MAMA-MIA Challenge was designed to address these challenges by providing a standardized benchmark for the joint evaluation of primary tumor segmentation and prediction of pathologic complete response using pre-treatment magnetic resonance imaging only. The training cohort comprised 1,506 patients from multiple institutions in the United States, while evaluation was conducted on an external test set of 574 patients from three independent European centers to assess cross-continental and cross-institutional generalization. A unified scoring framework combined predictive performance with subgroup consistency across age, menopausal status, and breast density. Twenty-one international teams participated in the final evaluation phase. Results demonstrate substantial performance variability under a common external evaluation framework and reveal trade-offs between overall accuracy and subgroup fairness. The challenge provides standardized datasets, evaluation protocols, and public resources to promote the development of robust and equitable artificial intelligence systems for breast cancer imaging.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042706","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":"Dual-Dynamic In-Context Learning for Medical Image Segmentation.","authors":"Tiana Tianying Chen, Liangli Zhen, Yanyu Xu, Shishuais Hu, Huazhu Fu, Limsoon Wong","doi":"10.1109/TMI.2026.3733484","DOIUrl":"10.1109/TMI.2026.3733484","url":null,"abstract":"<p><p>Visual in-context learning (ICL) enables medical image segmentation models to adapt to new tasks using only a small set of annotated support images, without additional model fine-tuning. This makes visual ICL promising for clinical deployment, yet a fundamental limitation remains. Current ICL models lack the intrinsic ability to adaptively integrate supports based on their relevance to the query. By either aggregating supports uniformly or relying on external retrieval, these methods limit query-aware support integration within the model itself. We introduce Dual-DSA (Dual-Dynamic Support Alignment), a reliability-aware visual ICL framework that dynamically integrates supports at the patch and support-set levels. At the patch level, DynPatch-Align selectively attends to relevant support regions for each query location, enabling fine-grained contextual alignment. At the support set level, evidential fusion integrates support-conditioned predictions based on uncertainty and consistency, and provides an Aggregate Evidential Confidence Score for reliability assessment. Together, these mechanisms enable intrinsic, query-adaptive support integration across both levels. Extensive experiments on 11 medical imaging datasets across endoscopy, breast ultrasound, and thyroid ultrasound show that Dual-DSA achieves strong full-coverage performance, obtaining the best Dice score on 8 out of 11 datasets and consistently outperforming its attention-based ICL backbone. Furthermore, the derived confidence scores correlate with segmentation quality and enable confidence-based rejection to improve retained-case performance, providing a practical mechanism for quality control in clinical workflows.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042916","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":"Proof-of-Concept Study of Task-Based Adaptive SPECT Imaging via System Sampling Strategies on a 12-Head Robotic SPECT Platform.","authors":"Yifei Jin, Ling-Jian Meng","doi":"10.1109/TMI.2026.3733006","DOIUrl":"10.1109/TMI.2026.3733006","url":null,"abstract":"<p><p>In this work, we explored a computational framework for task-based adaptive SPECT imaging based on a robotic platform. The framework has two key components. First, we utilized the modified uniform Cramér-Rao bound (MUCRB) to approximate the imaging variance attainable with a given system configuration characterized by the imaging time distribution (ITD) over a discretized system configuration space. Second, we developed a computational approach to enable direct optimization of the ITD (and the associated system configuration) to achieve a minimum imaging variance. To enable efficient system optimization, a convex surrogate of the MUCRB-based variance metric was derived, and a non-uniform object-space pixelation (NUOP) strategy was introduced to reduce computational load, while preserving resolution within regions of interest (ROIs). This framework was evaluated using simulation studies with a 12-camera-head robotic SPECT system. We used several phantoms and a series of performance measures to demonstrate the effectiveness of the adaptive imaging strategy. For the brain phantom, the adapted ITD reduced RMSE from 859.0 to 734.3. For the hot-rod phantom, RMSE was reduced from 1411.9/1316.5 to 1191.2/1138.0 across the two ROIs, while CRC increased from 0.092/0.351 to 0.181/0.604. For the cold-rod phantom, RMSE was reduced from 720.0/691.1 to 603.5/587.4 across the two ROIs relative to whole-view ITD, while CRC increased from 0.069/0.150 to 0.373/0.499. These results demonstrated that the proposed framework enables efficient, task-specific optimization of acquisition strategies and significantly improved ROI image quality.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042997","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":"Simulation and Design Study of Edge-on GaAs:Cr Detector for Clinical Photon Counting CT.","authors":"Tao Zhong, He Li, Wenhui Qin, Xiaopeng Yu, Xiaochun Lai","doi":"10.1109/TMI.2026.3730875","DOIUrl":"10.1109/TMI.2026.3730875","url":null,"abstract":"<p><p>Chromium-compensated Gallium Arsenide (GaAs:Cr) has emerged as a promising sensor material for photon counting detectors (PCDs) due to its excellent resistivity and charge carrier mobility. However, due to the limitations of the Cr compensation process, the GaAs:Cr wafer thickness is less than 1 mm, which distorts its X-ray absorption efficiency and limits its application in clinical computed tomography (CT). This study proposes a GaAs detector with an edge-on structure for clinical photon counting CT (PCCT) applications. To evaluate the performance of the detector, we modeled the spectral response and analyzed material decomposition (MD) noise using a full-chain detector model. In imaging domain study, digital phantoms, such as low contrast phantom, Gammex phantom, and XCAT digital phantoms, were virtually scanned to assess the image uniformity, CT number accuracy, material decomposition, and virtual mono-energetic imaging (VMI) performance, with the detector system modeled to reflect actual PCCT prototypes. The results indicate that the GaAs:Cr detector exhibits excellent mono-energetic spectrum response and low material decomposition (MD) noise. Additionally, the GaAs:Cr detector provides lower noise, higher contrast-to-noise ratio (CNR) in VMI results, and more precise concentration measurements in quantitative analysis, compared to existing PCDs. These findings highlight the feasibility of developing GaAs:Cr detectors for clinical CT applications, offering potential advantages over existing PCDs.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148893022","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":"Multi-Granularity Graph-Mamba Multi-Instance Learning for Unlabeled Autofluorescence Whole-Slide Image Classification.","authors":"Jiuyang Dong, Yu Lei, Junjun Jiang, Jiahan Li, Haiyu Zhou, Yongbing Zhang","doi":"10.1109/TMI.2026.3729829","DOIUrl":"10.1109/TMI.2026.3729829","url":null,"abstract":"<p><p>Multi-instance learning (MIL) has significantly advanced AI-assisted cancer diagnosis using histochemically stained whole-slide images (WSIs). However, acquiring such WSIs is time-consuming, labor-intensive, and environmentally unfriendly. To address this, we propose using unlabeled autofluorescence (UAF) WSIs as a cost-effective alternative for MIL-based diagnosis. We introduce a dedicated UAF WSI dataset, LCUHI-UAF, along with a matched H&E-stained WSI dataset, LCUHI-H&E, derived from the same tissue sections for direct comparison. To tackle the low signal-to-noise ratio and blurred morphological details in UAF images for classification tasks, we propose a novel Multi-Granularity Graph-Mamba (MGGM) MIL framework. In this framework, each WSI is represented as a graph constructed from the spatial coordinates of tissue instances, allowing graph convolution to capture local spatial dependencies while the Mamba architecture models long-range relationships. A multi-granularity mechanism is further proposed to enable comprehensive representation of hierarchical relationships among cell clusters and microenvironments within the tissue. Experiments on the paired lung cancer datasets LCUHI-H& E and LCUHI-UAF show that MGGM-MIL achieves top-performing results across two pre-trained feature settings. These results simultaneously confirm the viability of UAF-stained WSIs as a cost-effective substitute for H&E in cancer diagnosis. Additional evaluation on the Camelyon16 breast cancer dataset further validates the generalizability of MGGM-MIL across tissue types. Code is available at https://github.com/JiuyangDong/MGGMMIL.</p>","PeriodicalId":94033,"journal":{"name":"IEEE transactions on medical imaging","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148883150","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}