{"title":"弱监督回转铰对应的几何感知图匹配框架","authors":"Zhibin He, Wuyang Li, Tianming Liu, Xiang Li, Junwei Han, Tuo Zhang, Yixuan Yuan","doi":"10.1016/j.media.2025.103820","DOIUrl":null,"url":null,"abstract":"Achieving precise alignment of inter-subject brain landmarks, such as the gyral hinge (GH), would enhance the correspondence of brain function across subjects, thereby advancing our understanding of brain anatomy-function relationship and brain mechanisms. Recent methods mainly focus on identifying the correspondences of GHs by utilizing point-to-point ground truth. However, labeling point-to-point GH correspondences between subjects for the entire brain is laborious and time-consuming, given the presence of over 400 GHs per brain. To remedy this problem, we propose a Geometry-Aware Graph Matching framework, dubbed GAGM, for weakly supervised gyral hinge correspondence solely based on brain prior information. Specifically, we propose a Shape-Aware Graph Establishment (SAGE) module to ensure a comprehensive representation of geometry features in GH. SAGE constructs a structured graph by incorporating GH coordinates, shapes, and inter-GH relationships to model entire brain GHs and learns the spatial relation between them. Moreover, to reduce the optimization difficulties, Region-Aware Graph Matching (RAGM) module is proposed for multi-scale matching. RAGM leverages prior knowledge of the multi-scale relationship between GHs and brain regions and incorporates inter-scale semantic consistency to ensure both intra-region consistency and inter-region variability of GH features, ultimately achieving accurate GH matching. Extensive experiments on two public datasets, HCP and CHCP, demonstrate the superiority of our method over state-of-the-art methods. Our code: <ce:inter-ref xlink:href=\"https://github.com/ZhibinHe/GAGM\" xlink:type=\"simple\">https://github.com/ZhibinHe/GAGM</ce:inter-ref>.","PeriodicalId":18328,"journal":{"name":"Medical image analysis","volume":"53 1","pages":""},"PeriodicalIF":11.8000,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GAGM: Geometry-aware graph matching framework for weakly supervised gyral hinge correspondence\",\"authors\":\"Zhibin He, Wuyang Li, Tianming Liu, Xiang Li, Junwei Han, Tuo Zhang, Yixuan Yuan\",\"doi\":\"10.1016/j.media.2025.103820\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Achieving precise alignment of inter-subject brain landmarks, such as the gyral hinge (GH), would enhance the correspondence of brain function across subjects, thereby advancing our understanding of brain anatomy-function relationship and brain mechanisms. Recent methods mainly focus on identifying the correspondences of GHs by utilizing point-to-point ground truth. However, labeling point-to-point GH correspondences between subjects for the entire brain is laborious and time-consuming, given the presence of over 400 GHs per brain. To remedy this problem, we propose a Geometry-Aware Graph Matching framework, dubbed GAGM, for weakly supervised gyral hinge correspondence solely based on brain prior information. Specifically, we propose a Shape-Aware Graph Establishment (SAGE) module to ensure a comprehensive representation of geometry features in GH. SAGE constructs a structured graph by incorporating GH coordinates, shapes, and inter-GH relationships to model entire brain GHs and learns the spatial relation between them. Moreover, to reduce the optimization difficulties, Region-Aware Graph Matching (RAGM) module is proposed for multi-scale matching. RAGM leverages prior knowledge of the multi-scale relationship between GHs and brain regions and incorporates inter-scale semantic consistency to ensure both intra-region consistency and inter-region variability of GH features, ultimately achieving accurate GH matching. Extensive experiments on two public datasets, HCP and CHCP, demonstrate the superiority of our method over state-of-the-art methods. Our code: <ce:inter-ref xlink:href=\\\"https://github.com/ZhibinHe/GAGM\\\" xlink:type=\\\"simple\\\">https://github.com/ZhibinHe/GAGM</ce:inter-ref>.\",\"PeriodicalId\":18328,\"journal\":{\"name\":\"Medical image analysis\",\"volume\":\"53 1\",\"pages\":\"\"},\"PeriodicalIF\":11.8000,\"publicationDate\":\"2025-09-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical image analysis\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1016/j.media.2025.103820\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical image analysis","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.media.2025.103820","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
GAGM: Geometry-aware graph matching framework for weakly supervised gyral hinge correspondence
Achieving precise alignment of inter-subject brain landmarks, such as the gyral hinge (GH), would enhance the correspondence of brain function across subjects, thereby advancing our understanding of brain anatomy-function relationship and brain mechanisms. Recent methods mainly focus on identifying the correspondences of GHs by utilizing point-to-point ground truth. However, labeling point-to-point GH correspondences between subjects for the entire brain is laborious and time-consuming, given the presence of over 400 GHs per brain. To remedy this problem, we propose a Geometry-Aware Graph Matching framework, dubbed GAGM, for weakly supervised gyral hinge correspondence solely based on brain prior information. Specifically, we propose a Shape-Aware Graph Establishment (SAGE) module to ensure a comprehensive representation of geometry features in GH. SAGE constructs a structured graph by incorporating GH coordinates, shapes, and inter-GH relationships to model entire brain GHs and learns the spatial relation between them. Moreover, to reduce the optimization difficulties, Region-Aware Graph Matching (RAGM) module is proposed for multi-scale matching. RAGM leverages prior knowledge of the multi-scale relationship between GHs and brain regions and incorporates inter-scale semantic consistency to ensure both intra-region consistency and inter-region variability of GH features, ultimately achieving accurate GH matching. Extensive experiments on two public datasets, HCP and CHCP, demonstrate the superiority of our method over state-of-the-art methods. Our code: https://github.com/ZhibinHe/GAGM.
期刊介绍:
Medical Image Analysis serves as a platform for sharing new research findings in the realm of medical and biological image analysis, with a focus on applications of computer vision, virtual reality, and robotics to biomedical imaging challenges. The journal prioritizes the publication of high-quality, original papers contributing to the fundamental science of processing, analyzing, and utilizing medical and biological images. It welcomes approaches utilizing biomedical image datasets across all spatial scales, from molecular/cellular imaging to tissue/organ imaging.