Jingru Fu, Adrian V Dalca, Bruce Fischl, Rodrigo Moreno, Malte Hoffmann
{"title":"LEARNING ACCURATE RIGID REGISTRATION FOR LONGITUDINAL BRAIN MRI FROM SYNTHETIC DATA.","authors":"Jingru Fu, Adrian V Dalca, Bruce Fischl, Rodrigo Moreno, Malte Hoffmann","doi":"10.1109/isbi60581.2025.10980859","DOIUrl":null,"url":null,"abstract":"<p><p>Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects, they have demonstrated limitations when applied to longitudinal (within-subject) registration, where achieving precise alignment is critical. Building on an existing framework for anatomy-aware, acquisition-agnostic affine registration, we propose a model optimized for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle nonlinear transforms, the model estimates more accurate rigid transforms than previous cross-subject networks and performs robustly on longitudinal registration pairs within and across magnetic resonance imaging (MRI) contrasts.</p>","PeriodicalId":74566,"journal":{"name":"Proceedings. IEEE International Symposium on Biomedical Imaging","volume":"2025 ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12237398/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. IEEE International Symposium on Biomedical Imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/isbi60581.2025.10980859","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/5/12 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Rigid registration aims to determine the translations and rotations necessary to align features in a pair of images. While recent machine learning methods have become state-of-the-art for linear and deformable registration across subjects, they have demonstrated limitations when applied to longitudinal (within-subject) registration, where achieving precise alignment is critical. Building on an existing framework for anatomy-aware, acquisition-agnostic affine registration, we propose a model optimized for longitudinal, rigid brain registration. By training the model with synthetic within-subject pairs augmented with rigid and subtle nonlinear transforms, the model estimates more accurate rigid transforms than previous cross-subject networks and performs robustly on longitudinal registration pairs within and across magnetic resonance imaging (MRI) contrasts.