AUTHORS: Wynen M, La Rosa F, Sellimi A, Barquero G, Perrotta G, Lolli V, Van Pesch V, Granziera C, Kober T, Sati P, Macq B, Reich DS, Absinta M, Bach Cuadra M, Maggi P
Proceedings of the 29th ISMRM & SMRT Annual Meeting, : , Online, May 2021
ABSTRACT
The automatic assessment of paramagnetic rim lesions in multiple sclerosis is important, and a deep learning-based algorithm called RimNet has recently been proposed. This work evaluates the generalizability of RimNet and its longitudinal performance on MRI data acquired at different clinical centers. We found that Rim Net’s performance was nearly as good on totally unseen data as in the original paper (receiver-operating-characteristic area-under-the-curve (AUC) 0.88 vs. 0.94, precision-recall AUC 0.69 vs. 0.70), and it made consistent predictions on longitudinal data (binary consistency 82%, probability consistency 93%).
Download PDF
BibTex
Module: SP
