Pub Date : 2026-01-12DOI: 10.1109/tmi.2026.3653667
Jigmi Basumatary, Yousuf Aborahama, Yang Zhang, Yide Zhang, Yushun Zeng, Cindy Z. Liu, Qifa Zhou, Lihong V. Wang
{"title":"High-Speed Volumetric Dual-Mode Ultrasound and Photoacoustic Tomography with a Single-Element Detector","authors":"Jigmi Basumatary, Yousuf Aborahama, Yang Zhang, Yide Zhang, Yushun Zeng, Cindy Z. Liu, Qifa Zhou, Lihong V. Wang","doi":"10.1109/tmi.2026.3653667","DOIUrl":"https://doi.org/10.1109/tmi.2026.3653667","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"27 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145955128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/tmi.2026.3652170
Jiakai Zhou, Yang Wang, Chaolin Huang, Chao Dai, Chunyu Tan
{"title":"CeLR: A Transformer-based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-ray Imaging","authors":"Jiakai Zhou, Yang Wang, Chaolin Huang, Chao Dai, Chunyu Tan","doi":"10.1109/tmi.2026.3652170","DOIUrl":"https://doi.org/10.1109/tmi.2026.3652170","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"20 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145955130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-06DOI: 10.1109/tmi.2026.3651389
Han Wu,Haoyuan Chen,Lin Zhou,Qi Xu,Zhiming Cui,Dinggang Shen
Precise landmark annotation in cardiac ultrasound images is fundamental for quantitative cardiac health assessment. However, the time-intensive nature of manual annotation typically constrains clinicians to annotate only selected key frames, limiting comprehensive temporal analysis capabilities. While recent automated landmark detection methods have demonstrated success for key-frame analysis, they fail to effectively utilize the intrinsic temporal information across cardiac sequence. To bridge this gap, we present SemiEchoTracker, a novel semi-supervised framework that enables comprehensive landmark tracking throughout echocardiography sequences while requiring supervision only on key frames. Our framework introduces three key innovative strategies: 1) a co-training mechanism that enforces mutual consistency between spatial detection and temporal tracking, enabling accurate intermediate frame detection without additional annotations, 2) a guided DINOv2 pretraining strategy that is specially tailored for extracting fine-grained echocardiography-specific spatial features, and 3) a perception-aware spatial-temporal (PAST) attention module that efficiently captures inter- and intra-frame relationships in echocardiography videos. Extensive validation on three datasets across multiple cardiac views demonstrates that our method not only achieves state-of-the-art detection performance on the keyframes but also yields accurate frame-by-frame prediction, which is important for dynamic cardiac analysis in clinicians.
{"title":"Semi-Supervised Landmark Tracking in Echocardiography Video via Spatial-Temporal Co-Training and Perception-Aware Attention.","authors":"Han Wu,Haoyuan Chen,Lin Zhou,Qi Xu,Zhiming Cui,Dinggang Shen","doi":"10.1109/tmi.2026.3651389","DOIUrl":"https://doi.org/10.1109/tmi.2026.3651389","url":null,"abstract":"Precise landmark annotation in cardiac ultrasound images is fundamental for quantitative cardiac health assessment. However, the time-intensive nature of manual annotation typically constrains clinicians to annotate only selected key frames, limiting comprehensive temporal analysis capabilities. While recent automated landmark detection methods have demonstrated success for key-frame analysis, they fail to effectively utilize the intrinsic temporal information across cardiac sequence. To bridge this gap, we present SemiEchoTracker, a novel semi-supervised framework that enables comprehensive landmark tracking throughout echocardiography sequences while requiring supervision only on key frames. Our framework introduces three key innovative strategies: 1) a co-training mechanism that enforces mutual consistency between spatial detection and temporal tracking, enabling accurate intermediate frame detection without additional annotations, 2) a guided DINOv2 pretraining strategy that is specially tailored for extracting fine-grained echocardiography-specific spatial features, and 3) a perception-aware spatial-temporal (PAST) attention module that efficiently captures inter- and intra-frame relationships in echocardiography videos. Extensive validation on three datasets across multiple cardiac views demonstrates that our method not only achieves state-of-the-art detection performance on the keyframes but also yields accurate frame-by-frame prediction, which is important for dynamic cardiac analysis in clinicians.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"183 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145907534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-26DOI: 10.1109/tmi.2025.3648788
Jie Du,Haoyang Luo,Wenbing Chen,Peng Liu,Tianfu Wang
Existing multi-organ segmentation methods usually rely on large and fully labeled datasets for training. However, medical image datasets are typically decentralized by privacy constraints and partially labeled due to the high costs of full annotation in clinical practice, resulting in label inconsistency across medical centers. Federated learning offers privacy-preserving decentralized training, but the label inconsistency leads to significant divergence in local model parameters across medical centers, thereby hindering the achievement of the global optimum. To resolve this issue, an effective and communication-efficient Federated Learning under Reliable Supervision (FedRS) is proposed, which ensures: i) the local models are trained with reliable supervisory information through the proposed Less-Forgetting and Less-Constraint loss functions, thereby reducing the divergence in local model parameters; and ii) the global model is aggregated based on the consistency of predictions between each local model (after local training) and the global model (received before training), thereby enhancing the reliability of the global model. Extensive experimental results on nine publicly available 3D abdominal CT image datasets show that our FedRS outperforms localized, centralized, and state-of-the-art federated learning methods on both in-federation and out-of-federation datasets, demonstrating its effectiveness and strong generalization capability. In particular, our FedRS only utilizes a model with only 4.1M parameters as its backbone, thereby significantly reducing its communication cost. The source code is publicly available at https://github.com/luohy812/FedRS.
{"title":"FedRS: Federated Learning Under Reliable Supervision for Multi-Organ Segmentation With Inconsistent Labels.","authors":"Jie Du,Haoyang Luo,Wenbing Chen,Peng Liu,Tianfu Wang","doi":"10.1109/tmi.2025.3648788","DOIUrl":"https://doi.org/10.1109/tmi.2025.3648788","url":null,"abstract":"Existing multi-organ segmentation methods usually rely on large and fully labeled datasets for training. However, medical image datasets are typically decentralized by privacy constraints and partially labeled due to the high costs of full annotation in clinical practice, resulting in label inconsistency across medical centers. Federated learning offers privacy-preserving decentralized training, but the label inconsistency leads to significant divergence in local model parameters across medical centers, thereby hindering the achievement of the global optimum. To resolve this issue, an effective and communication-efficient Federated Learning under Reliable Supervision (FedRS) is proposed, which ensures: i) the local models are trained with reliable supervisory information through the proposed Less-Forgetting and Less-Constraint loss functions, thereby reducing the divergence in local model parameters; and ii) the global model is aggregated based on the consistency of predictions between each local model (after local training) and the global model (received before training), thereby enhancing the reliability of the global model. Extensive experimental results on nine publicly available 3D abdominal CT image datasets show that our FedRS outperforms localized, centralized, and state-of-the-art federated learning methods on both in-federation and out-of-federation datasets, demonstrating its effectiveness and strong generalization capability. In particular, our FedRS only utilizes a model with only 4.1M parameters as its backbone, thereby significantly reducing its communication cost. The source code is publicly available at https://github.com/luohy812/FedRS.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"1 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145835979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-26DOI: 10.1109/tmi.2025.3648756
L Guo,A Bialkowski,A Abbosh
Well-designed and trained deep neural networks can solve inverse electromagnetic problems much faster than conventional solvers. However, they need a physics framework to ensure producing physically correct results. Since most physics-guided deep learning inverse solvers require substantial training with numerous epochs, each involving solving a forward problem, their accuracy and efficiency are largely defined by the utilized forward solver, which becomes a bottleneck for their practical training. Thus, a fast and accurate self-supervised deep learning forward solver is presented. The solver uses a physics-based framework that divides the domain into two regions: an interior region, which includes any scatterers, and an exterior region, which represents the background medium. A hybrid loss function, incorporating Maxwell's curl equation and integral equation with the well-defined scalar background's Green's function, is employed to guide the scattered field generated from the neural network, ensuring global and local accuracy. To verify the generality of the solver, it is trained on random objects and tested on realistic models, showing high global and local metrics accuracy. For example, more than 95% of testing cases using the proposed method achieve less than 0.15 root-mean-square error in the calculated scattered field and dielectric properties of the imaged domain compared to the ground truth. In contrast, two recent deep learning methods could only realize that level of accuracy for less than 50% of the tested cases. The reported method is 97% faster than conventional solvers, enabling the development of reliable deep-learning inverse solvers.
{"title":"Medical Microwave Imaging Using Physics-Guided Deep Learning Part 1: The Forward Solver.","authors":"L Guo,A Bialkowski,A Abbosh","doi":"10.1109/tmi.2025.3648756","DOIUrl":"https://doi.org/10.1109/tmi.2025.3648756","url":null,"abstract":"Well-designed and trained deep neural networks can solve inverse electromagnetic problems much faster than conventional solvers. However, they need a physics framework to ensure producing physically correct results. Since most physics-guided deep learning inverse solvers require substantial training with numerous epochs, each involving solving a forward problem, their accuracy and efficiency are largely defined by the utilized forward solver, which becomes a bottleneck for their practical training. Thus, a fast and accurate self-supervised deep learning forward solver is presented. The solver uses a physics-based framework that divides the domain into two regions: an interior region, which includes any scatterers, and an exterior region, which represents the background medium. A hybrid loss function, incorporating Maxwell's curl equation and integral equation with the well-defined scalar background's Green's function, is employed to guide the scattered field generated from the neural network, ensuring global and local accuracy. To verify the generality of the solver, it is trained on random objects and tested on realistic models, showing high global and local metrics accuracy. For example, more than 95% of testing cases using the proposed method achieve less than 0.15 root-mean-square error in the calculated scattered field and dielectric properties of the imaged domain compared to the ground truth. In contrast, two recent deep learning methods could only realize that level of accuracy for less than 50% of the tested cases. The reported method is 97% faster than conventional solvers, enabling the development of reliable deep-learning inverse solvers.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"123 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145836041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-22DOI: 10.1109/tmi.2025.3647129
Dong Liu, Haoyuan Xia, Chuyu Wang, Hongyan Xiang, Yukang Huang, S. Kevin Zhou
{"title":"GSR: A Gaussian Splatting-Based Reconstruction Framework for EIT","authors":"Dong Liu, Haoyuan Xia, Chuyu Wang, Hongyan Xiang, Yukang Huang, S. Kevin Zhou","doi":"10.1109/tmi.2025.3647129","DOIUrl":"https://doi.org/10.1109/tmi.2025.3647129","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"31 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-19DOI: 10.1109/tmi.2025.3646479
Xin Hong, Yongze Lin, Zhenghao Wu
{"title":"Alzheimer’s Disease Diagnosis Based on Derivative Dynamic Time Warping Functional Connectivity Networks","authors":"Xin Hong, Yongze Lin, Zhenghao Wu","doi":"10.1109/tmi.2025.3646479","DOIUrl":"https://doi.org/10.1109/tmi.2025.3646479","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"56 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145784489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-18DOI: 10.1109/tmi.2025.3645821
Yuanzhi Cheng,Zean Liu,Shinichi Tamura
The exploitation of label hierarchy is crucial for effective brain tumor segmentation. Nevertheless, existing methods grapple with two key limitations. First, they lack the hierarchical dependency of predictions across different label levels, rendering the network outputs less interpretable. Second, they fail to exploit the hierarchal similarity among labels, thus hindering potential accuracy enhancement. To address these limitations, we present a novel framework termed deep hierarchy-aware segmentation (DHAS), which achieves both hierarchically interpretable and high-accuracy predictions. Specifically, to generate hierarchical predictions, the network is designed to output pixel-wise probability conditional upon the parent label and is hybrid-trained from conditional to unconditional probability. To utilize the label similarity, we propose a tree-triplet loss, which imposes the hierarchy-induced distance within the feature embedding space. Experimental results on three datasets, BraTS2018, BraTS2019 and BraTS2020, show that our proposed framework achieves significantly better performance than other hierarchy-exploiting methods, and it ranks fifth top among 383 participating methods in Brats2020 Challenge. The improved performance and interpretable predictions promise the potential of DHAS for clinical applications in brain tumor segmentation. Furthermore, its generalization is demonstrated for cardiac segmentation on ACDC dataset.
{"title":"Deep Hierarchy-Aware Segmentation: A Novel Framework for MRIs Brain Tumor Segmentation.","authors":"Yuanzhi Cheng,Zean Liu,Shinichi Tamura","doi":"10.1109/tmi.2025.3645821","DOIUrl":"https://doi.org/10.1109/tmi.2025.3645821","url":null,"abstract":"The exploitation of label hierarchy is crucial for effective brain tumor segmentation. Nevertheless, existing methods grapple with two key limitations. First, they lack the hierarchical dependency of predictions across different label levels, rendering the network outputs less interpretable. Second, they fail to exploit the hierarchal similarity among labels, thus hindering potential accuracy enhancement. To address these limitations, we present a novel framework termed deep hierarchy-aware segmentation (DHAS), which achieves both hierarchically interpretable and high-accuracy predictions. Specifically, to generate hierarchical predictions, the network is designed to output pixel-wise probability conditional upon the parent label and is hybrid-trained from conditional to unconditional probability. To utilize the label similarity, we propose a tree-triplet loss, which imposes the hierarchy-induced distance within the feature embedding space. Experimental results on three datasets, BraTS2018, BraTS2019 and BraTS2020, show that our proposed framework achieves significantly better performance than other hierarchy-exploiting methods, and it ranks fifth top among 383 participating methods in Brats2020 Challenge. The improved performance and interpretable predictions promise the potential of DHAS for clinical applications in brain tumor segmentation. Furthermore, its generalization is demonstrated for cardiac segmentation on ACDC dataset.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":"1 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145777345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：