This work evaluates the reliability of radiomic features in healthy controls and patients with multiple sclerosis using MR Quantitative Susceptibility Mapping (QSM), to guide the identification of future potential biomarkers. To ensure reproducibility, we assessed the non-lesioned parenchyma. Feature robustness was evaluated against the number of grey levels and echo times, measuring the Intraclass Correlation Coefficient (ICC). More than 65% of features were robust; different outcomes between regions were interpreted considering their anatomical characteristics (e.g. fibres’ orientation), confirmed by radiomic measurements (e.g. entropy). In future work, we are going to assess characterization and classification potential of those measurements.
No takes yet. Share an insight, caveat, or question.
Fiscone et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: