What question did this study set out to answer?

March 28, 2026Open Access

Explainable MRI radiomics of the basal ganglia and ventral midbrain distinguishes Parkinson’s disease, SWEDD, and healthy controls

Key Points

The research aims to differentiate Parkinson's disease, SWEDD, and healthy controls using MRI-derived radiomic features.
Extracted 1,285 radiomic features from T1/T2-weighted MRI of subcortical regions
Used nested cross-validation for feature selection and classifier training
Evaluated five supervised models with performance metrics based on AUC scores
Achieved an overall macro-AUC of 0.85 for classifying PD, SWEDD, and controls
Class-wise AUCs were 0.93 for PD, 0.79 for SWEDD, and 0.79 for controls
Identified 14 key features from the ventral midbrain and thalamus that contribute to classification

Abstract

• Explainable radiomics of T1/T2 MRI distinguishes PD, SWEDD, and controls. • Fourteen key features are located to ventral midbrain, thalamus, and striatum. • Spatial SHAP maps reveal patterns consistent with nigrostriatal organization. • Radiomic heterogeneity may capture imaging correlates to subcortical integrity. Distinguishing scans without evidence of dopaminergic deficit (SWEDD) from Parkinson’s disease (PD) remains challenging on routine MRI. We extracted 1,285 radiomic features from T1- and T2-weighted MRI within six a priori subcortical regions of interest in the PPMI cohort. A nested cross-validation framework (inner: univariate ANOVA or Kruskal–Wallis with BH-FDR correction, mRMR, and LASSO; outer: 10-fold) was used for feature selection and classifier training. Five supervised models were evaluated, and performance was summarized by outer-fold micro- and macro-averaged AUCs with bootstrap 95% confidence intervals. Fourteen non-redundant features, primarily from the ventral midbrain, thalamus, putamen, and nucleus accumbens, were retained. The XGBoost classifier achieved a macro-AUC of 0.85 (0.76-0.91), with class-wise AUCs of 0.93 for PD, 0.79 for SWEDD, and 0.79 for healthy controls. SHAP analysis identified ventral midbrain texture heterogeneity and thalamic contrast as dominant contributors to PD prediction, while nucleus accumbens texture and putaminal shape were most informative for SWEDD. Radiomic heterogeneity on standard MRI thus captures disease-relevant patterns along a PD–SWEDD–HC continuum. Although these features are indirect surrogates of microstructure, their spatial profiles align with iron- and connectivity-related alterations reported with quantitative susceptibility and diffusion MRI. This explainable radiomics framework enables biologically coherent, multi-class discrimination between PD and SWEDD, supporting low-burden stratification and hypothesis generation for quantitative MRI studies, with planned external validation in independent cohorts to confirm generalizability.

Read Full Paperexternally

KI fragen

Bookmark

View Full Paper