NC-Reg : Neural Cortical Maps for Rigid Registration

2026-01-26

AI Summary

This work proposes Neural Cortical Maps, a novel approach that introduces continuous neural representations to cortical surface registration, thereby eliminating reliance on discrete mesh structures inherent in traditional rigid alignment methods. By operating directly on the spherical domain, the method enables efficient optimization of cortical features without resolution constraints. Leveraging a hybrid strategy of gradient descent and simulated annealing, it achieves rapid iterative rigid registration. Evaluated in subject-to-template alignment, the approach attains sub-degree accuracy (<1°) and demonstrates a 30-fold acceleration over conventional barycentric interpolation, substantially improving both computational efficiency and robustness. This advancement offers a highly effective strategy for preclinical cortical alignment tasks.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

We introduce neural cortical maps, a continuous and compact neural representation for cortical feature maps, as an alternative to traditional discrete structures such as grids and meshes. It can learn from meshes of arbitrary size and provide learnt features at any resolution. Neural cortical maps enable efficient optimization on the sphere and achieve runtimes up to 30 times faster than classic barycentric interpolation (for the same number of iterations). As a proof of concept, we investigate rigid registration of cortical surfaces and propose NC-Reg, a novel iterative algorithm that involves the use of neural cortical feature maps, gradient descent optimization and a simulated annealing strategy. Through ablation studies and subject-to-template experiments, our method demonstrates sub-degree accuracy ($<1^\circ$ from the global optimum), and serves as a promising robust pre-alignment strategy, which is critical in clinical settings.

Problem

• rigid registration
• cortical surfaces
• neural representation
• pre-alignment
• computational efficiency

Innovation

• Neural Cortical Maps
• Rigid Registration
• Continuous Neural Representation
• Simulated Annealing
• Cortical Surface Alignment