Related Experiment Video
Updated: Sep 30, 2025
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
Stratification of multiple sclerosis patients using unsupervised machine learning: a single-visit MRI-driven approach
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.
Objectives:
To stratify patients with multiple sclerosis (pwMS) based on brain MRI-derived volumetric features using unsupervised machine learning.
Methods:
The 3-T brain MRIs of relapsing-remitting pwMS including 3D-T1w and FLAIR-T2w sequences were retrospectively collected, along with Expanded Disability Status Scale (EDSS) scores and long-term (10 ± 2 years) clinical outcomes (EDSS, cognition, and progressive course). From the MRIs, volumes of demyelinating lesions and 116 atlas-defined gray matter regions were automatically segmented and expressed as z-scores referenced to external populations. Following feature selection, baseline MRI-derived biomarkers entered the Subtype and Stage Inference (SuStaIn) algorithm, which estimates subgroups characterized by distinct patterns of biomarker evolution and stages within subgroups. The trained model was then applied to longitudinal MRIs. Stability of subtypes and stage change over time were assessed via Krippendorf's α and multilevel linear regression models, respectively. The prognostic relevance of SuStaIn classification was assessed with ordinal/logistic regression analyses.
Results:
We selected 425 pwMS (35.9 ± 9.9 years; F/M: 301/124), corresponding to 1129 MRI scans, along with healthy controls (N = 148; 35.9 ± 13.0 years; F/M: 77/71) and external pwMS (N = 80; 40.4 ± 11.9 years; F/M: 56/24) as reference populations. Based on 11 biomarkers surviving feature selection, two subtypes were identified, designated as "deep gray matter (DGM)-first" subtype (N = 238) and "cortex-first" subtype (N = 187) according to the atrophy pattern. Subtypes were consistent over time (α = 0.806), with significant annual stage increase (b = 0.20; p < 0.001). EDSS was associated with stage and DGM-first subtype (p ≤ 0.02). Baseline stage predicted long-term disability, transition to progressive course, and cognitive impairment (p ≤ 0.03), with the latter also associated with DGM-first subtype (p = 0.005).
Conclusions:
Unsupervised learning modelling of brain MRI-derived volumetric features provides a biologically reliable and prognostically meaningful stratification of pwMS.
Key Points:
• The unsupervised modelling of brain MRI-derived volumetric features can provide a single-visit stratification of multiple sclerosis patients. • The so-obtained classification tends to be consistent over time and captures disease-related brain damage progression, supporting the biological reliability of the model. • Baseline stratification predicts long-term clinical disability, cognition, and transition to secondary progressive course.
Insights
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.
