CSVR: Combined Surface and Volume Registration for Neonatal Brain MRI

Saga N.B. Masui, Yourong Guo, Mohamed A. Suliman, Mattias P. Heinrich, Nashira Baena, Irina Grigorescu, Logan Z. J. Williams, Ashleigh Davies, Vanessa Kyriakopoulou, Gráinne McAlonan, Jonathan O’Muircheartaigh, Emma C. Robinson
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3424-3442, 2026.

Abstract

Nonlinear image registration is a cornerstone of neuroimaging analysis, supporting both qualitative and quantitative comparisons of brain structures across individuals and over time. While traditional volumetric registration methods, driven by voxel intensities, achieve good alignment of subcortical regions, they generally fail to capture correspondences between highly convoluted and variable cortical shapes. Surface-based methods, which instead regularise mappings as geodesics along the cortical sheet, yield improved cortical alignment but ignore the subcortical domain, limiting their utility for whole-brain analyses. A unified registration framework would address these limitations to enable integrated analysis of cortical and subcortical structures and the neuronal fibres that connect them. However, achieving this is challenging, since matching heterogeneous cortical shapes implies large volumetric displacements local to the cortex. To overcome these challenges, we introduce CSVR, the first deep learning-based framework for combined surface–volume registration of neonatal MRI. By integrating hierarchical registration strategies with discrete optimisation, CSVR achieves accurate, smooth, and anatomically plausible alignment of the entire brain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-masui26a, title = {CSVR: Combined Surface and Volume Registration for Neonatal Brain MRI}, author = {Masui, Saga N.B. and Guo, Yourong and Suliman, Mohamed A. and Heinrich, Mattias P. and Baena, Nashira and Grigorescu, Irina and Williams, Logan Z. J. and Davies, Ashleigh and Kyriakopoulou, Vanessa and McAlonan, Gr{\'a}inne and O'Muircheartaigh, Jonathan and Robinson, Emma C.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3424--3442}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/masui26a/masui26a.pdf}, url = {https://proceedings.mlr.press/v315/masui26a.html}, abstract = {Nonlinear image registration is a cornerstone of neuroimaging analysis, supporting both qualitative and quantitative comparisons of brain structures across individuals and over time. While traditional volumetric registration methods, driven by voxel intensities, achieve good alignment of subcortical regions, they generally fail to capture correspondences between highly convoluted and variable cortical shapes. Surface-based methods, which instead regularise mappings as geodesics along the cortical sheet, yield improved cortical alignment but ignore the subcortical domain, limiting their utility for whole-brain analyses. A unified registration framework would address these limitations to enable integrated analysis of cortical and subcortical structures and the neuronal fibres that connect them. However, achieving this is challenging, since matching heterogeneous cortical shapes implies large volumetric displacements local to the cortex. To overcome these challenges, we introduce CSVR, the first deep learning-based framework for combined surface–volume registration of neonatal MRI. By integrating hierarchical registration strategies with discrete optimisation, CSVR achieves accurate, smooth, and anatomically plausible alignment of the entire brain.} }
Endnote
%0 Conference Paper %T CSVR: Combined Surface and Volume Registration for Neonatal Brain MRI %A Saga N.B. Masui %A Yourong Guo %A Mohamed A. Suliman %A Mattias P. Heinrich %A Nashira Baena %A Irina Grigorescu %A Logan Z. J. Williams %A Ashleigh Davies %A Vanessa Kyriakopoulou %A Gráinne McAlonan %A Jonathan O’Muircheartaigh %A Emma C. Robinson %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-masui26a %I PMLR %P 3424--3442 %U https://proceedings.mlr.press/v315/masui26a.html %V 315 %X Nonlinear image registration is a cornerstone of neuroimaging analysis, supporting both qualitative and quantitative comparisons of brain structures across individuals and over time. While traditional volumetric registration methods, driven by voxel intensities, achieve good alignment of subcortical regions, they generally fail to capture correspondences between highly convoluted and variable cortical shapes. Surface-based methods, which instead regularise mappings as geodesics along the cortical sheet, yield improved cortical alignment but ignore the subcortical domain, limiting their utility for whole-brain analyses. A unified registration framework would address these limitations to enable integrated analysis of cortical and subcortical structures and the neuronal fibres that connect them. However, achieving this is challenging, since matching heterogeneous cortical shapes implies large volumetric displacements local to the cortex. To overcome these challenges, we introduce CSVR, the first deep learning-based framework for combined surface–volume registration of neonatal MRI. By integrating hierarchical registration strategies with discrete optimisation, CSVR achieves accurate, smooth, and anatomically plausible alignment of the entire brain.
APA
Masui, S.N., Guo, Y., Suliman, M.A., Heinrich, M.P., Baena, N., Grigorescu, I., Williams, L.Z.J., Davies, A., Kyriakopoulou, V., McAlonan, G., O’Muircheartaigh, J. & Robinson, E.C.. (2026). CSVR: Combined Surface and Volume Registration for Neonatal Brain MRI. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3424-3442 Available from https://proceedings.mlr.press/v315/masui26a.html.

Related Material