Diffeomorphic Cortical Alignment via Direct Warping of Streamline Endpoints

2026-05-15

AI Summary

Traditional cortical registration methods rely on local geometric features and neglect the long-range connectivity constraints imposed by white matter fiber tracts, resulting in insufficient alignment between functional and anatomical correspondences. This work proposes a connectivity-driven cortical surface alignment approach that, for the first time, models white matter fiber endpoints as point clouds on a product manifold and directly optimizes their native distributions through diffeomorphic deformations, thereby avoiding reliance on precomputed connectivity matrices. By integrating spherical cortical representations with a geometric manifold framework, the method iteratively refines deformation fields to align major fiber bundles. Experiments on Human Connectome Project (HCP) data demonstrate that the proposed approach significantly improves fiber bundle overlap coefficients and outperforms existing methods such as ENCORE and MSMAll, particularly in cross-resolution scenarios, exhibiting superior connectivity fidelity and robustness.

Abstract

Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geometric correspondence, it neglects the long-range wiring constraints imposed by white-matter anatomy. Diffusion MRI tractography offers these crucial constraints; however, prior connectivity-informed pipelines typically align precomputed connectivity matrices, making the optimization highly sensitive to connectivity estimation and its resolution. In this paper, we introduce a novel connectivity-based surface registration method that aligns cortical surfaces by operating directly on white-matter fiber-tract endpoints. We model tract endpoints as a point cloud on the product manifold $Ω\times Ω$, where $Ω$ represents the spherical domain of the inflated cortical hemispheres. Our alignment method iteratively (i) computes a small diffeomorphic warp for $Ω$ by minimizing connectivity mismatch, and (ii) updates the endpoints based on this warp. The method relies on a geometric framework that ensures output warps are diffeomorphisms and has a final goal that optimizes the matching of well-known fiber bundles. Experiments on Human Connectome Project (HCP) data demonstrate improved tract-level correspondence, achieving higher connectivity-level overlap coefficients on major fiber bundles and stronger robustness across grid resolutions for $Ω$ compared to state-of-the-art methods such as ENCORE and MSMAll.

Problem

• cortical surface registration
• white-matter connectivity
• tractography
• diffeomorphic alignment
• connectivity constraints

Innovation

• diffeomorphic registration
• connectivity-based alignment
• streamline endpoints
• cortical surface registration
• white-matter tractography