RimSet: Quantitatively Identifying and Characterizing Chronic Active Multiple Sclerosis Lesion on Quantitative Susceptibility Maps
This work addresses the lack of quantitative analysis for rim+ lesions in multiple sclerosis, which correlate with increased disability, representing a domain-specific incremental advancement.
The authors tackled the problem of quantitatively identifying and characterizing chronic active multiple sclerosis lesions on Quantitative Susceptibility Maps, introducing RimSet, which achieved a 78.7% Dice score for segmentation and outperformed existing methods with a partial ROC AUC of 0.808 and PR AUC of 0.737.
Background: Rim+ lesions in multiple sclerosis (MS), detectable via Quantitative Susceptibility Mapping (QSM), correlate with increased disability. Existing literature lacks quantitative analysis of these lesions. We introduce RimSet for quantitative identification and characterization of rim+ lesions on QSM. Methods: RimSet combines RimSeg, an unsupervised segmentation method using level-set methodology, and radiomic measurements with Local Binary Pattern texture descriptors. We validated RimSet using simulated QSM images and an in vivo dataset of 172 MS subjects with 177 rim+ and 3986 rim-lesions. Results: RimSeg achieved a 78.7% Dice score against the ground truth, with challenges in partial rim lesions. RimSet detected rim+ lesions with a partial ROC AUC of 0.808 and PR AUC of 0.737, surpassing existing methods. QSMRim-Net showed the lowest mean square error (0.85) and high correlation (0.91; 95% CI: 0.88, 0.93) with expert annotations at the subject level.