SuD-CoTAN: Sulcal Depth-guided Anatomically Consistent Fetal Cortical Surface Reconstruction

Irina Grigorescu, Jiaxin Xiao, Yourong Guo, Vanessa Kyriakopoulou, Alena Uus, Vyacheslav Karolis, Kaili Liang, Mohamed A. Suliman, Qiang Ma, Daniel Rueckert, Bernhard Kainz, A. David Edwards, Joseph V. Hajnal, Mary Rutherford, Maria Deprez, Emma C. Robinson
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:3374-3396, 2026.

Abstract

Accurate and anatomically consistent fetal cortical surface reconstruction is essential for studying early brain development, yet existing methods often lack reliable vertex-wise correspondence and fail to harmonise their outputs across heterogeneous magnetic resonance imaging (MRI) datasets. We introduce Sulcal Depth-guided CoTAN (SuD-CoTAN), a learning-based framework that fits anatomically and topologically consistent cortical meshes directly to T2-weighted MRI and performs alignment to age-matched templates in one single step. All models are trained exclusively on normative samples from the developing Human Connectome Project (dHCP) and evaluated within-sample and on a different acquisition protocol. Results show that SuD-CoTAN generalises to new datasets in ways that harmonise global morphometric properties by better capturing the surface geometry of individual cases; its template fitting is precise, delivering vertex-wise anatomical correspondences that result in sharp weekly averages of sulcal depth and curvature maps in template space. This supports direct vertex-wise Gaussian Process regression of neurodevelopmental trends without a need for any additional registration. Collectively, this whole pipeline runs in $\sim$3 seconds. This suggests that SuD-CoTAN offers promise as a screening tool for cortical malformations during fetal development.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-grigorescu26a, title = {SuD-CoTAN: Sulcal Depth-guided Anatomically Consistent Fetal Cortical Surface Reconstruction}, author = {Grigorescu, Irina and Xiao, Jiaxin and Guo, Yourong and Kyriakopoulou, Vanessa and Uus, Alena and Karolis, Vyacheslav and Liang, Kaili and Suliman, Mohamed A. and Ma, Qiang and Rueckert, Daniel and Kainz, Bernhard and Edwards, A. David and Hajnal, Joseph V. and Rutherford, Mary and Deprez, Maria and Robinson, Emma C.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {3374--3396}, 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/grigorescu26a/grigorescu26a.pdf}, url = {https://proceedings.mlr.press/v315/grigorescu26a.html}, abstract = {Accurate and anatomically consistent fetal cortical surface reconstruction is essential for studying early brain development, yet existing methods often lack reliable vertex-wise correspondence and fail to harmonise their outputs across heterogeneous magnetic resonance imaging (MRI) datasets. We introduce Sulcal Depth-guided CoTAN (SuD-CoTAN), a learning-based framework that fits anatomically and topologically consistent cortical meshes directly to T2-weighted MRI and performs alignment to age-matched templates in one single step. All models are trained exclusively on normative samples from the developing Human Connectome Project (dHCP) and evaluated within-sample and on a different acquisition protocol. Results show that SuD-CoTAN generalises to new datasets in ways that harmonise global morphometric properties by better capturing the surface geometry of individual cases; its template fitting is precise, delivering vertex-wise anatomical correspondences that result in sharp weekly averages of sulcal depth and curvature maps in template space. This supports direct vertex-wise Gaussian Process regression of neurodevelopmental trends without a need for any additional registration. Collectively, this whole pipeline runs in $\sim$3 seconds. This suggests that SuD-CoTAN offers promise as a screening tool for cortical malformations during fetal development.} }
Endnote
%0 Conference Paper %T SuD-CoTAN: Sulcal Depth-guided Anatomically Consistent Fetal Cortical Surface Reconstruction %A Irina Grigorescu %A Jiaxin Xiao %A Yourong Guo %A Vanessa Kyriakopoulou %A Alena Uus %A Vyacheslav Karolis %A Kaili Liang %A Mohamed A. Suliman %A Qiang Ma %A Daniel Rueckert %A Bernhard Kainz %A A. David Edwards %A Joseph V. Hajnal %A Mary Rutherford %A Maria Deprez %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-grigorescu26a %I PMLR %P 3374--3396 %U https://proceedings.mlr.press/v315/grigorescu26a.html %V 315 %X Accurate and anatomically consistent fetal cortical surface reconstruction is essential for studying early brain development, yet existing methods often lack reliable vertex-wise correspondence and fail to harmonise their outputs across heterogeneous magnetic resonance imaging (MRI) datasets. We introduce Sulcal Depth-guided CoTAN (SuD-CoTAN), a learning-based framework that fits anatomically and topologically consistent cortical meshes directly to T2-weighted MRI and performs alignment to age-matched templates in one single step. All models are trained exclusively on normative samples from the developing Human Connectome Project (dHCP) and evaluated within-sample and on a different acquisition protocol. Results show that SuD-CoTAN generalises to new datasets in ways that harmonise global morphometric properties by better capturing the surface geometry of individual cases; its template fitting is precise, delivering vertex-wise anatomical correspondences that result in sharp weekly averages of sulcal depth and curvature maps in template space. This supports direct vertex-wise Gaussian Process regression of neurodevelopmental trends without a need for any additional registration. Collectively, this whole pipeline runs in $\sim$3 seconds. This suggests that SuD-CoTAN offers promise as a screening tool for cortical malformations during fetal development.
APA
Grigorescu, I., Xiao, J., Guo, Y., Kyriakopoulou, V., Uus, A., Karolis, V., Liang, K., Suliman, M.A., Ma, Q., Rueckert, D., Kainz, B., Edwards, A.D., Hajnal, J.V., Rutherford, M., Deprez, M. & Robinson, E.C.. (2026). SuD-CoTAN: Sulcal Depth-guided Anatomically Consistent Fetal Cortical Surface Reconstruction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:3374-3396 Available from https://proceedings.mlr.press/v315/grigorescu26a.html.

Related Material