Deep cascaded registration and weakly-supervised segmentation of fetal brain MRI

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Comte, Valentí
• dc.contributor.author Alenyà Sistané, Mireia
• dc.contributor.author Urru, Andrea
• dc.contributor.author Recober Martín, Judith
• dc.contributor.author Nakaki, Ayako
• dc.contributor.author Crovetto, Francesca
• dc.contributor.author Camara, Oscar
• dc.contributor.author Gratacós Solsona, Eduard
• dc.contributor.author Eixarch, Elisenda
• dc.contributor.author Crispi Brillas, Fàtima
• dc.contributor.author Piella Fenoy, Gemma
• dc.contributor.author Ceresa, Mario
• dc.contributor.author González Ballester, Miguel Ángel, 1973-
• dc.date.accessioned 2025-10-21T05:43:53Z
• dc.date.available 2025-10-21T05:43:53Z
• dc.date.issued 2025
• dc.description.abstract Deformable image registration is a cornerstone of many medical image analysis applications, particularly in the context of fetal brain magnetic resonance imaging (MRI), where precise registration is essential for studying the rapidly evolving fetal brain during pregnancy and potentially identifying neurodevelopmental abnormalities. While deep learning has become the leading approach for medical image registration, traditional convolutional neural networks (CNNs) often fall short in capturing fine image details due to their bias toward low spatial frequencies. To address this challenge, we introduce a deep learning registration framework comprising multiple cascaded convolutional networks. These networks predict a series of incremental deformation fields that transform the moving image at various spatial frequency levels, ensuring accurate alignment with the fixed image. This multi-resolution approach allows for a more accurate and detailed registration process, capturing both coarse and fine image structures. Our method outperforms existing state-of-the-art techniques, including other multi-resolution strategies, by a substantial margin. Furthermore, we integrate our registration method into a multi-atlas segmentation pipeline and showcase its competitive performance compared to nnU-Net, achieved using only a small subset of annotated images as atlases. This approach is particularly valuable in the context of fetal brain MRI, where annotated datasets are limited. Our pipeline for registration and multi-atlas segmentation is publicly available at https://github.com/ValBcn/CasReg.en
• dc.description.sponsorship This publication is part of the project PCI2021-122044- 2A, funded by the project ERA-NET NEURON Cofund2, by MCIN/AEI/10.13039/501100011033/and by the European Union “NextGenerationEU”/PRTR. G. Piella is supported by ICREA under the ICREA Academia programme. We also thank the study participants for their personal time and commitment to the IMPACT BCN Trial, and all the medical staff, residents, midwives, nurses, MR platform, and researchers of BCNatal especially Annachiara Basso, MD and Kilian Vellvé, MD for their support in the MR data collection. IMPACT BCN Trial was partially funded by a grant from “la Caixa” Foundation (LCF/PR/GN18/10310003); Cerebra Foundation for the Brain Injured Child (Carmarthen, Wales, UK); ASISA Foundation; AGAUR under grant 2017 SGR No. 1531 and Instituto de Salud Carlos III (ISCIII), PI18/00073, co-funded by the European Union. A. Nakaki has received the support of a fellowship from la Caixa Foundation under grant number LCF/BQ/DR19/11740018. F.Crovetto reports a personal fee from Centro de Investigaciones Biomédicas en Red sobre Enfermedades Raras (CIBERER).en
• dc.format.mimetype application/pdf
• dc.identifier.citation Comte V, Alenya M, Urru A, Recober J, Nakaki A, Crovetto F, et al. Deep cascaded registration and weakly-supervised segmentation of fetal brain MRI. Heliyon. 2025 Jan;11(1):e40148. DOI: 10.1016/j.heliyon.2024.e40148
• dc.identifier.doi http://dx.doi.org/https://doi.org/10.1016/j.heliyon.2024.e40148
• dc.identifier.issn 2405-8440
• dc.identifier.uri http://hdl.handle.net/10230/71590
• dc.language.iso eng
• dc.publisher Elsevier
• dc.relation.ispartof Heliyon. 2025 Jan;11(1):e40148
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PCI2021-122044-2A
• dc.rights © 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Registrationen
• dc.subject.keyword Segmentationen
• dc.subject.keyword Cascadeen
• dc.subject.keyword Deep learningen
• dc.subject.keyword Fetal brainen
• dc.title Deep cascaded registration and weakly-supervised segmentation of fetal brain MRIen
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion