Unified Brain Surface and Volume Registration

2025-12-22

AI Summary

Traditional brain MRI registration decouples volumetric alignment from cortical surface registration, leading to anatomical inconsistencies. To address this, we propose NeurAlign—a deep learning framework that jointly optimizes cortical surface topology and volumetric deformation for the first time. Its core innovation is a unified spherical-coordinate intermediate representation that tightly couples differentiable spherical parameterization, spherical resampling, and regularized volumetric deformation modeling, thereby ensuring geometric consistency across cortical and subcortical structures. The method operates end-to-end directly on raw T1-weighted MRI volumes, requiring no prior anatomical knowledge or manual annotations. Experiments demonstrate substantial improvements: Dice scores for subcortical structures increase by up to 7.0%, while inference speed accelerates by two to three orders of magnitude over conventional methods. NeurAlign thus achieves significant gains in both registration accuracy and computational efficiency.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Segmentation
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Accurate registration of brain MRI scans is fundamental for cross-subject analysis in neuroscientific studies. This involves aligning both the cortical surface of the brain and the interior volume. Traditional methods treat volumetric and surface-based registration separately, which often leads to inconsistencies that limit downstream analyses. We propose a deep learning framework, NeurAlign, that registers $3$D brain MRI images by jointly aligning both cortical and subcortical regions through a unified volume-and-surface-based representation. Our approach leverages an intermediate spherical coordinate space to bridge anatomical surface topology with volumetric anatomy, enabling consistent and anatomically accurate alignment. By integrating spherical registration into the learning, our method ensures geometric coherence between volume and surface domains. In a series of experiments on both in-domain and out-of-domain datasets, our method consistently outperforms both classical and machine learning-based registration methods -- improving the Dice score by up to 7 points while maintaining regular deformation fields. Additionally, it is orders of magnitude faster than the standard method for this task, and is simpler to use because it requires no additional inputs beyond an MRI scan. With its superior accuracy, fast inference, and ease of use, NeurAlign sets a new standard for joint cortical and subcortical registration.

Problem

• Unifies brain surface and volume registration
• Ensures consistent cortical and subcortical alignment
• Improves accuracy and speed over traditional methods

Innovation

• Deep learning framework jointly aligns cortical and subcortical regions
• Uses spherical coordinate space to unify volume and surface registration
• Integrates spherical registration for geometric coherence between domains