JParc: Joint cortical surface parcellation with registration

TL;DR

JParc introduces a joint cortical registration and parcellation framework that significantly improves brain region mapping accuracy by leveraging registration and learned atlases, achieving over 90% Dice score on the Mindboggle dataset.

Contribution

The paper presents JParc, a novel joint registration and parcellation method that outperforms existing approaches by integrating registration with atlas learning and fine-tuning.

Findings

JParc achieves over 90% Dice score on Mindboggle dataset.

Registration and learned atlas are key to improved parcellation accuracy.

Using basic geometric features suffices for high-performance parcellation.

Abstract

Cortical surface parcellation is a fundamental task in both basic neuroscience research and clinical applications, enabling more accurate mapping of brain regions. Model-based and learning-based approaches for automated parcellation alleviate the need for manual labeling. Despite the advancement in parcellation performance, learning-based methods shift away from registration and atlas propagation without exploring the reason for the improvement compared to traditional methods. In this study, we present JParc, a joint cortical registration and parcellation framework, that outperforms existing state-of-the-art parcellation methods. In rigorous experiments, we demonstrate that the enhanced performance of JParc is primarily attributable to accurate cortical registration and a learned parcellation atlas. By leveraging a shallow subnetwork to fine-tune the propagated atlas labels, JParc achieves a Dice score greater than 90% on the Mindboggle dataset, using only basic geometric features (sulcal depth, curvature) that describe cortical folding patterns. The superior accuracy of JParc can significantly increase the statistical power in brain mapping studies as well as support applications in surgical planning and many other downstream neuroscientific and clinical tasks.