Machine learning-based classification of multiple sclerosis lesion activity using multi-sequence MRI radiomics: a complete analysis of T1, T2, FLAIR, DWI, and SWI features

This integration of SWI with conventional sequences in a unified radiomic model offers a promising contrast-free alternative for MS lesion classification, achieving promising accuracy comparable to radiologist performance on an internal test set (<i>n</i> = 28 lesions), pending external validation. External validation is needed to confirm the generalisability, but this approach could reduce gadolinium reliance in clinical practice.