Pub Date : 2024-09-25DOI: 10.1109/tmi.2024.3467377
Wen Li, Nan An, Fuzhi Cao, Wenli Wang, Chunhui Wang, Weinan Xu, Yang Gao, Xiaolin Ning
{"title":"Source Imaging Method based on Spatial Smoothing and Edge Sparsity (SISSES) and Its Application to OPM-MEG","authors":"Wen Li, Nan An, Fuzhi Cao, Wenli Wang, Chunhui Wang, Weinan Xu, Yang Gao, Xiaolin Ning","doi":"10.1109/tmi.2024.3467377","DOIUrl":"https://doi.org/10.1109/tmi.2024.3467377","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142321527","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 : 2024-09-25DOI: 10.1109/tmi.2024.3467384
Bin Gao, Aiju Yu, Chen Qiao, Vince D. Calhoun, Julia M. Stephen, Tony W. Wilson, Yu-Ping Wang
{"title":"An Explainable Unified Framework of Spatio-Temporal Coupling Learning with Application to Dynamic Brain Functional Connectivity Analysis","authors":"Bin Gao, Aiju Yu, Chen Qiao, Vince D. Calhoun, Julia M. Stephen, Tony W. Wilson, Yu-Ping Wang","doi":"10.1109/tmi.2024.3467384","DOIUrl":"https://doi.org/10.1109/tmi.2024.3467384","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142321528","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}
{"title":"UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration","authors":"Runshi Zhang, Hao Mo, Junchen Wang, Bimeng Jie, Yang He, Nenghao Jin, Liang Zhu","doi":"10.1109/tmi.2024.3467919","DOIUrl":"https://doi.org/10.1109/tmi.2024.3467919","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142321529","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}
Identification of Alzheimer's disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the ℓ2,0-norm, EMLE exploits an ℓ2,γ-norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The ℓ2,γ-norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the ℓ2,0-norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix γ-norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer's Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.
{"title":"Enhanced Multimodal Low-rank Embedding based Feature Selection Model for Multimodal Alzheimer's Disease Diagnosis.","authors":"Zhi Chen,Yongguo Liu,Yun Zhang,Jiajing Zhu,Qiaoqin Li,Xindong Wu","doi":"10.1109/tmi.2024.3464861","DOIUrl":"https://doi.org/10.1109/tmi.2024.3464861","url":null,"abstract":"Identification of Alzheimer's disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the ℓ2,0-norm, EMLE exploits an ℓ2,γ-norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The ℓ2,γ-norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the ℓ2,0-norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix γ-norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer's Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275168","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}
Colorectal cancer plays a dominant role in cancer-related deaths, primarily due to the absence of obvious early-stage symptoms. Whole-stage colorectal disease diagnosis is crucial for assessing lesion evolution and determining treatment plans. However, locality difference and disease progression lead to intra-class disparities and inter-class similarities for colorectal lesion representation. In addition, interpretable algorithms explaining the lesion progression are still lacking, making the prediction process a "black box". In this paper, we propose IPNet, a dual-branch interpretable network with progressive loss for whole-stage colorectal disease diagnosis. The dual-branch architecture captures unbiased features representing diverse localities to suppress intra-class variation. The progressive loss function considers inter-class relationship, using prior knowledge of disease evolution to guide classification. Furthermore, a novel Grain-CAM is designed to interpret IPNet by visualizing pixel-wise attention maps from shallow to deep layers, providing regions semantically related to IPNet's progressive classification. We conducted whole-stage diagnosis on two image modalities, i.e., colorectal lesion classification on 129,893 endoscopic optical images and rectal tumor T-staging on 11,072 endoscopic ultrasound images. IPNet is shown to surpass other state-of-the-art algorithms, accordingly achieving an accuracy of 93.15% and 89.62%. Especially, it establishes effective decision boundaries for challenges like polyp vs. adenoma and T2 vs. T3. The results demonstrate an explainable attempt for colorectal lesion classification at a whole-stage level, and rectal tumor T-staging by endoscopic ultrasound is also unprecedentedly explored. IPNet is expected to be further applied, assisting physicians in whole-stage disease diagnosis and enhancing diagnostic interpretability.
结直肠癌在癌症相关死亡中占主导地位，这主要是由于结直肠癌没有明显的早期症状。全阶段结直肠疾病诊断对于评估病变演变和确定治疗方案至关重要。然而，地域差异和疾病进展导致结直肠病变表征的类内差异和类间相似性。此外，解释病变进展的可解释算法仍然缺乏，这使得预测过程成为一个 "黑箱"。在本文中，我们提出了用于全阶段结直肠疾病诊断的具有渐进损失的双分支可解释网络 IPNet。双分支架构捕捉代表不同局部的无偏特征，以抑制类内变异。渐进损失函数考虑了类间关系，利用疾病演变的先验知识来指导分类。此外，我们还设计了一种新颖的 Grain-CAM，通过可视化从浅层到深层的像素注意力图来解释 IPNet，提供与 IPNet 渐进式分类语义相关的区域。我们对两种图像模式进行了全阶段诊断，即对 129893 张内窥镜光学图像进行结直肠病变分类，以及对 11072 张内窥镜超声图像进行直肠肿瘤 T 分期。结果表明，IPNet 超越了其他最先进的算法，准确率分别达到 93.15% 和 89.62%。特别是，它为息肉与腺瘤、T2 与 T3 等挑战建立了有效的决策边界。研究结果表明，IPNet 尝试在整个阶段对结直肠病变进行分类，并通过内窥镜超声对直肠肿瘤进行 T 型分期进行了前所未有的探索。预计 IPNet 将得到进一步应用，协助医生进行全阶段疾病诊断，并提高诊断的可解释性。
{"title":"IPNet: An Interpretable Network with Progressive Loss for Whole-stage Colorectal Disease Diagnosis.","authors":"Junhu Fu,Ke Chen,Qi Dou,Yun Gao,Yiping He,Pinghong Zhou,Shengli Lin,Yuanyuan Wang,Yi Guo","doi":"10.1109/tmi.2024.3459910","DOIUrl":"https://doi.org/10.1109/tmi.2024.3459910","url":null,"abstract":"Colorectal cancer plays a dominant role in cancer-related deaths, primarily due to the absence of obvious early-stage symptoms. Whole-stage colorectal disease diagnosis is crucial for assessing lesion evolution and determining treatment plans. However, locality difference and disease progression lead to intra-class disparities and inter-class similarities for colorectal lesion representation. In addition, interpretable algorithms explaining the lesion progression are still lacking, making the prediction process a \"black box\". In this paper, we propose IPNet, a dual-branch interpretable network with progressive loss for whole-stage colorectal disease diagnosis. The dual-branch architecture captures unbiased features representing diverse localities to suppress intra-class variation. The progressive loss function considers inter-class relationship, using prior knowledge of disease evolution to guide classification. Furthermore, a novel Grain-CAM is designed to interpret IPNet by visualizing pixel-wise attention maps from shallow to deep layers, providing regions semantically related to IPNet's progressive classification. We conducted whole-stage diagnosis on two image modalities, i.e., colorectal lesion classification on 129,893 endoscopic optical images and rectal tumor T-staging on 11,072 endoscopic ultrasound images. IPNet is shown to surpass other state-of-the-art algorithms, accordingly achieving an accuracy of 93.15% and 89.62%. Especially, it establishes effective decision boundaries for challenges like polyp vs. adenoma and T2 vs. T3. The results demonstrate an explainable attempt for colorectal lesion classification at a whole-stage level, and rectal tumor T-staging by endoscopic ultrasound is also unprecedentedly explored. IPNet is expected to be further applied, assisting physicians in whole-stage disease diagnosis and enhancing diagnostic interpretability.","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142273441","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 : 2024-09-17DOI: 10.1109/tmi.2024.3462415
Wen Li, Fuzhi Cao, Nan An, Wenli Wang, Chunhui Wang, Weinan Xu, Yang Gao, Xiaolin Ning
{"title":"Source Extent Estimation in OPM-MEG: A Two-Stage Champagne Approach","authors":"Wen Li, Fuzhi Cao, Nan An, Wenli Wang, Chunhui Wang, Weinan Xu, Yang Gao, Xiaolin Ning","doi":"10.1109/tmi.2024.3462415","DOIUrl":"https://doi.org/10.1109/tmi.2024.3462415","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236332","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 : 2024-09-16DOI: 10.1109/tmi.2024.3461737
Guanghui Yue, Lixin Zhang, Jingfeng Du, Tianwei Zhou, Wei Zhou, Weisi Lin
{"title":"Subjective and Objective Quality Assessment of Colonoscopy Videos","authors":"Guanghui Yue, Lixin Zhang, Jingfeng Du, Tianwei Zhou, Wei Zhou, Weisi Lin","doi":"10.1109/tmi.2024.3461737","DOIUrl":"https://doi.org/10.1109/tmi.2024.3461737","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236333","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 : 2024-09-16DOI: 10.1109/tmi.2024.3461312
Jianpo Su, Bo Wang, Zhipeng Fan, Yifan Zhang, Ling-Li Zeng, Hui Shen, Dewen Hu
{"title":"M2DC: A Meta-Learning Framework for Generalizable Diagnostic Classification of Major Depressive Disorder","authors":"Jianpo Su, Bo Wang, Zhipeng Fan, Yifan Zhang, Ling-Li Zeng, Hui Shen, Dewen Hu","doi":"10.1109/tmi.2024.3461312","DOIUrl":"https://doi.org/10.1109/tmi.2024.3461312","url":null,"abstract":"","PeriodicalId":13418,"journal":{"name":"IEEE Transactions on Medical Imaging","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236361","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：