Leveraging Hand-Crafted Radiomics on Multicenter FLAIR MRI for Predicting Disability Worsening in People with Multiple Sclerosis

Hamza Khan^1,2Diana L. Giraldo³Henry C Woodruff⁴Lorin Werthen-Brabants⁵Shruti Atul Mali⁴Sina Amirrajab⁴Edward De Brouwer⁶Veronica Popescu¹Bart Van Wijmeersch¹Oliver Gerlach⁷Jan Sijbers³Liesbet M Peeters^1*Philippe Lambin⁴

• ¹University of Hasselt, Hasselt, Limburg, Belgium
• ²Maastricht University, Maastricht, Netherlands
• ³University of Antwerp, Antwerp, Antwerp, Belgium
• ⁴GROW School for Oncology & Reproduction, Faculty of Health, Medicine and Life Sciences, Maastricht University, Maastricht, Netherlands, Netherlands
• ⁵Ghent University, Ghent, East Flanders, Belgium
• ⁶KU Leuven, Leuven, Belgium
• ⁷Zuyderland Medical Centre, Sittard, Netherlands

Multiple sclerosis (MS) is an autoimmune disease of the central nervous system, leading to varying degrees of functional impairment. Conventional tools, such as the Expanded Disability Status Scale (EDSS), lack sensitivity to subtle disease worsening. Radiomics provides a quantitative imaging approach to address this limitation. This study applied machine learning (ML) and radiomics features from T2-weighted Fluid-Attenuated Inversion Recovery (FLAIR) magnetic resonance image (MRI) to predict disability worsening in MS. A retrospective analysis was performed on real-world data from 247 PwMS across two centers. Disability worsening was defined using EDSS changes over two years. FLAIR MRIs underwent preprocessing and super-resolution reconstruction to enhance low-resolution images. White matter lesions (WML) were segmented using the Lesion Segmentation Toolbox (LST), and tissue segmentation was performed using sequence Adaptive Multimodal SEGmentation. Radiomics features from WML and normal-appearing white matter (NAWM) were extracted using PyRadiomics, harmonised with Longitudinal ComBat, followed by recursive feature elimination for feature selection. Elastic Net, Balanced Random Forest (BRFC), and Light Gradient-Boosting Machine (LGBM) models were trained and evaluated. The LGBM model with harmonised radiomics and clinical features outperformed the clinical only model, achieving a test area under the precision recall curve (PR AUC) of 0.20 and a receiver operating characteristic area under the curve (ROC AUC) of 0.64. Key predictive features, among others, included Gray-level co-occurrence matrix (GLCM) maximum probability (WML), Gray-level dependence matrix (GLDM) dependence non uniformity (NAWM). However, short-term longitudinal changes showed limited predictive power (PR AUC = 0.11, ROC AUC = 0.69). These findings highlight the potential of ML-driven radiomics in predicting disability worsening, warranting validation in larger, balanced datasets and exploration of advanced deep learning approaches.