Abstract
Longitudinal Magnetic Resonance Imaging (MRI) coupled with image registration approaches is a well-established approach for estimating spatio-temporal brain development. We present a study of diffeomorphic registration paradigms abilities for modelling fetal brain deformations during cortical gyrification. We investigate how the use of longitudinal MRI sequences can improve the accuracy of deformation estimates. First, we introduce an approach that integrates multiple time points into a stationary velocity field (SVF)-based longitudinal registration framework, enabling to model continuous spatio-temporal deformations from the full MRI sequence. Second, we assess this approach alongside existing diffeomorphic registration methods on two fetal brain atlases, evaluating their ability to capture the dynamic processes of fetal cortical maturation. Our results show that even though all evaluated methods systematically underestimate cortical deformations during gyrification, registration approaches leveraging the full MRI sequence estimate spatiotemporal deformations more aligned with the fetal brain developmental trajectory.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/PIPPI_009.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
BibTex
@InProceedings{ScaFlo_Longitudinal_MICCAISAT2026,
author = { Scalvini, Florian AND Kerachni, Anne AND Rousseau, François AND Passat, Nicolas},
title = { { Longitudinal registration of human fetal brain MRI } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17257},
month = {pending},
page = {pending}
}