2026-04-13T07:30:10Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/715902025-10-23T15:21:48Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Comte, Valentí author Alenyà Sistané, Mireia author Urru, Andrea author Recober Martín, Judith author Nakaki, Ayako author Crovetto, Francesca author Camara, Oscar author Gratacós Solsona, Eduard author Eixarch, Elisenda author Crispi Brillas, Fàtima author Piella Fenoy, Gemma author Ceresa, Mario author González Ballester, Miguel Ángel, 1973- author 2025-10-21T05:43:53Z 2025-10-21T05:43:53Z 2025 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. 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). http://hdl.handle.net/10230/71590 Registration Segmentation Cascade Deep learning Fetal brain Deep cascaded registration and weakly-supervised segmentation of fetal brain MRI