Anatomical Longitudinal Cortical Surface Registration

Aakash Saboo, Ashleigh Davies, Nashira Baena, Kaili Liang, Jiaxin Xiao, Yourong Guo, Renato Basenczi, Jonathan O’Muircheartaigh, Emma Robinson
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3152-3173, 2026.

Abstract

Longitudinal cortical surface registration is essential for accurately characterizing developmental and neurodegenerative trajectories, thereby facilitating a mechanistic understanding of cortical growth and the identification of biomarkers. This is hindered by current registration networks, which works on spherical projections of the cortical surface. Therefore, In this work, we present a novel longitudinal registration framework that operates directly on complex anatomical geometries by integrating a learning-based network with pairwise instance optimization. This hybrid strategy leverages the network to establish a robust initial alignment, which is subsequently refined through optimization to ensure high-fidelity registration. We demonstrate that this method yields growth maps with superior smoothness compared to baselines, enhancing their clinical utility, while rigorously preserving topological integrity as evidenced by analyses of self-intersecting faces, areal distortion, and anisotropic strain.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-saboo26a, title = {Anatomical Longitudinal Cortical Surface Registration}, author = {Saboo, Aakash and Davies, Ashleigh and Baena, Nashira and Liang, Kaili and Xiao, Jiaxin and Guo, Yourong and Basenczi, Renato and O'Muircheartaigh, Jonathan and Robinson, Emma}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3152--3173}, 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/saboo26a/saboo26a.pdf}, url = {https://proceedings.mlr.press/v315/saboo26a.html}, abstract = {Longitudinal cortical surface registration is essential for accurately characterizing developmental and neurodegenerative trajectories, thereby facilitating a mechanistic understanding of cortical growth and the identification of biomarkers. This is hindered by current registration networks, which works on spherical projections of the cortical surface. Therefore, In this work, we present a novel longitudinal registration framework that operates directly on complex anatomical geometries by integrating a learning-based network with pairwise instance optimization. This hybrid strategy leverages the network to establish a robust initial alignment, which is subsequently refined through optimization to ensure high-fidelity registration. We demonstrate that this method yields growth maps with superior smoothness compared to baselines, enhancing their clinical utility, while rigorously preserving topological integrity as evidenced by analyses of self-intersecting faces, areal distortion, and anisotropic strain.} }
Endnote
%0 Conference Paper %T Anatomical Longitudinal Cortical Surface Registration %A Aakash Saboo %A Ashleigh Davies %A Nashira Baena %A Kaili Liang %A Jiaxin Xiao %A Yourong Guo %A Renato Basenczi %A Jonathan O’Muircheartaigh %A Emma 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-saboo26a %I PMLR %P 3152--3173 %U https://proceedings.mlr.press/v315/saboo26a.html %V 315 %X Longitudinal cortical surface registration is essential for accurately characterizing developmental and neurodegenerative trajectories, thereby facilitating a mechanistic understanding of cortical growth and the identification of biomarkers. This is hindered by current registration networks, which works on spherical projections of the cortical surface. Therefore, In this work, we present a novel longitudinal registration framework that operates directly on complex anatomical geometries by integrating a learning-based network with pairwise instance optimization. This hybrid strategy leverages the network to establish a robust initial alignment, which is subsequently refined through optimization to ensure high-fidelity registration. We demonstrate that this method yields growth maps with superior smoothness compared to baselines, enhancing their clinical utility, while rigorously preserving topological integrity as evidenced by analyses of self-intersecting faces, areal distortion, and anisotropic strain.
APA
Saboo, A., Davies, A., Baena, N., Liang, K., Xiao, J., Guo, Y., Basenczi, R., O’Muircheartaigh, J. & Robinson, E.. (2026). Anatomical Longitudinal Cortical Surface Registration. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3152-3173 Available from https://proceedings.mlr.press/v315/saboo26a.html.

Related Material