<scp> segcsvd _PVS </scp> : A Convolutional Neural Network‐Based Tool for Quantification of Enlarged Perivascular Spaces ( <scp>PVS</scp> ) on <scp> T ₁ </scp> ‐Weighted Images

Enlarged perivascular spaces (PVS) are imaging markers of cerebral small vessel disease (CSVD) that are associated with age, disease phenotypes, and overall health. Quantification of PVS is challenging but necessary to expand an understanding of their role in cerebrovascular pathology. Accurate and automated segmentation of PVS on T₁-weighted images would be valuable given the widespread use of T₁-weighted imaging protocols in multisite clinical and research datasets. We introduce segcsvd_PVS, a convolutional neural network (CNN)-based tool for automated PVS segmentation on T₁-weighted images. segcsvd_PVS was developed using a novel hierarchical approach that builds on existing tools and incorporates robust training strategies to enhance the accuracy and consistency of PVS segmentation. Performance was evaluated using a comprehensive evaluation strategy that included comparison to existing benchmark methods, ablation-based validation, accuracy validation against manual ground truth annotations, correlation with age-related PVS burden as a biological benchmark, and extensive robustness testing. segcsvd_PVS achieved strong object-level performance for basal ganglia PVS (DSC = 0.78), exhibiting both high sensitivity (SNS = 0.80) and precision (PRC = 0.78). Although voxel-level precision was lower (PRC = 0.57), manual correction improved this by only ~3%, indicating that the additional voxels reflected primary boundary- or extent-related differences rather than correctable false positive error. For non-basal ganglia PVS, segcsvd_PVS outperformed benchmark methods, exhibiting higher voxel-level performance across several metrics (DSC = 0.60, SNS = 0.67, PRC = 0.57, NSD = 0.77), despite overall lower performance relative to basal ganglia PVS. Additionally, the association between age and segmentation-derived measures of PVS burden was consistently stronger and more reliable for segcsvd_PVS compared to benchmark methods across three cohorts (test6, ADNI, CAHHM), providing further evidence of the accuracy and consistency of its segmentation output. segcsvd_PVS demonstrates robust performance across diverse imaging conditions and improved sensitivity to biologically meaningful associations, supporting its utility as a T₁-based PVS segmentation tool.