3D Classification of Paramagnetic Rim Lesions in Multiple Sclerosis via Asymmetric QSM-FLAIR Modeling
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a computer program that uses MRI scans to automatically find special spots in the brain called paramagnetic rim lesions, which signal ongoing inflammation in Multiple Sclerosis (MS). Their method looks at two types of MRI images together, focusing mainly on one type that shows magnetic properties and using the other to add structural details. They trained their program with smart techniques to work well even with limited data. When tested on real patient scans, their system did better than previous methods at identifying these lesions.
Multiple SclerosisParamagnetic Rim LesionsQuantitative Susceptibility MappingFLAIR MRIDeep LearningMultimodal ImagingSelf-Supervised LearningLesion ClassificationContrastive Regularization
Authors
Veronica Pignedoli, Giacomo Boffa, Nicoletta Noceti, Matilde Inglese, Francesca Odone, Matteo Moro
Abstract
Paramagnetic rim lesions (Rim$^+$) identified on susceptibility-sensitive MRI have recently emerged as a specific biomarker of chronic active inflammation in Multiple Sclerosis (MS) and are associated with long-term disability progression. However, susceptibility imaging and expert interpretation remain limited to specialized centers, visual assessment is time-consuming and variable, and the low prevalence of Rim$^+$ lesions poses severe class imbalance challenges for automated analysis. We propose a 3D multimodal deep learning framework for lesion-level Rim$^+$/Rim$^-$ classification from Quantitative Susceptibility Mapping (QSM) and FLAIR MRI. The architecture explicitly models modality asymmetry by treating QSM as the primary susceptibility-driven signal and conditioning it with FLAIR-derived structural context. To improve robustness under limited data, we employ self-supervised multimodal pretraining followed by supervised fine-tuning with contrastive regularization. The method was evaluated on a clinically acquired cohort of 88 people with MS with expert lesion annotations as reference standard. Results highlight improved performance compared to prior architectures, supporting the effectiveness of asymmetric multimodal modeling for automated chronic active lesion identification.