Multi-contrast deep-learning segmentation of the choroid plexus using self-configuring nnU-Net

Motivation: Recent studies have emphasized the relevance of accurate measures of the choroid plexus (ChP), which operates at the blood-cerebrospinal fluid (CSF) barrier and plays a fundamental role in CSF production, circulation, and neuro-immune surveillance. Goal(s): To improve the existing ChP segmentation by leveraging the complementary nature of multi-contrast MRI together with a self-configuring deep-learning framework. Approach: Multi-contrast segmentation is assessed by comparing a previous single-contrast implementation with the novel multi-contrast approach and gold-standard neuroradiologist manual segmentation. Results: The Dice-Sørensen increased by 5.2 points using multi-contrast ChP segmentation, demonstrating that T1-weighted, T2-weighted, and T2-FLAIR can be used together to provide improved, complementary segmentation accuracy. Impact: This study evaluates multi-contrast MRIs as inputs to a self-configuring deep learning framework to provide a new tool for segmentation of the choroid plexus, which has gained much recent interest as the most proximal structure in the neurofluid circuit.