Related Experiment Video
Updated: Sep 30, 2025
10:25
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
48.5K
Stratification of multiple sclerosis patients using unsupervised machine learning: a single-visit MRI-driven
Giuseppe Pontillo1,2, Simone Penna3, Sirio Cocozza4
1Department of Advanced Biomedical Sciences, University "Federico II", Via Pansini 5, 80131, Naples, Italy. giuseppe.pontillo@unina.it.
European Radiology
|March 14, 2022
Summary
Unsupervised machine learning stratified multiple sclerosis patients using brain MRI scans. This approach reliably predicts long-term disability and disease progression.
Area of Science:
- Neuroimaging
- Machine Learning
- Neurology
Background:
- Multiple sclerosis (MS) patient stratification is crucial for personalized treatment.
- Brain MRI-derived volumetric features offer potential biomarkers for disease progression.
Purpose of the Study:
- To stratify patients with multiple sclerosis (pwMS) using unsupervised machine learning on brain MRI-derived volumetric features.
- To assess the biological reliability and prognostic value of the identified patient subgroups.
Main Methods:
- Retrospective collection of 3-T brain MRIs (3D-T1w, FLAIR-T2w) from relapsing-remitting pwMS.
- Automated segmentation of demyelinating lesions and 116 gray matter regions, with feature selection.
- Application of the Subtype and Stage Inference (SuStaIn) algorithm for unsupervised clustering and longitudinal analysis.
Main Results:
- Two distinct subtypes identified: "deep gray matter (DGM)-first" (N=238) and "cortex-first" (N=187), based on atrophy patterns.
- Subtypes demonstrated consistency over time (α = 0.806) with significant annual stage increase (b = 0.20; p < 0.001).
- Baseline stratification predicted long-term disability, cognitive impairment, and transition to a progressive course (p ≤ 0.03).
Conclusions:
- Unsupervised modeling of MRI features provides a biologically reliable stratification of pwMS.
- This single-visit stratification is consistent over time and captures disease progression.
- The classification accurately predicts long-term clinical outcomes, including disability and cognition.
