SimCortex v2: Joint Cortical Surface Reconstruction with Near-Zero Collisions and Self-Intersections

2026-10-05

AI Summary

This study addresses geometric artifacts in cortical surface reconstruction, such as mesh self-intersections and collisions between inner and outer surfaces, by proposing SimCortex v2, a deep learning framework for high-precision, collision-free joint reconstruction of white matter and pial surfaces across both hemispheres. The method introduces a novel ribbon-structure-conditioned U-Net that jointly optimizes the deformation of four cortical surfaces through T1-weighted MRI segmentation, topologically correct initialization, and multi-scale stationary velocity field prediction. Evaluated on 560 subjects, the framework achieves a reconstruction accuracy of 0.253 mm, with 92.14% of cases free from surface collisions and a self-intersection rate of only 0.044%, comprehensively outperforming existing baseline methods.

Abstract

Reconstructing cortical WM and pial surfaces from structural magnetic resonance imaging (MRI) is a prerequisite for surface-based neuroanatomical analysis, yet remains challenging because the cortex is thin and tightly folded. Reconstruction methods can produce geometric artifacts such as mesh self-intersections and collisions between cortical surfaces, and although recent deep learning methods have reduced reconstruction time from hours to minutes, these artifacts persist. We propose SimCortex v2, a deep learning framework for simultaneous reconstruction of the left and right WM and pial surfaces from T1-weighted MRI. SimCortex v2 estimates topologically correct initial surfaces from a volumetric segmentation and refines all four jointly using multi-scale stationary velocity fields predicted by a ribbon-conditioned, U-Net-like network. We evaluated SimCortex v2 on 560 cases from 14 cohorts, thirteen of them unseen during training, spanning ages 6-89, healthy and clinical populations, and scanners from three vendors. SimCortex v2 matched the surface-distance accuracy of the strongest baseline (average symmetric surface distance 0.253 mm) while showing no detected inter-surface collision in 92.14% of cases and the lowest self-intersection fraction (0.044%) among learning-based methods, whereas every baseline produced at least one collision in every case. Source code, configuration files, pretrained weights, preprocessed data, and the exact evaluation splits are publicly released.

Problem

• cortical surface reconstruction
• mesh self-intersections
• surface collisions
• structural MRI
• geometric artifacts

Innovation

• cortical surface reconstruction
• stationary velocity fields
• joint refinement
• self-intersection
• deep learning