Deep Learning to Differentiate Parkinsonian Syndromes Using Multimodal Magnetic Resonance Imaging : A Proof‐of‐Concept Study
Open Access
- 24 July 2025
- journal article
- Published by Wiley in Movement Disorders
- Vol. 40 (10) , 2139-2148
Abstract
Background: The differentiation between multiple system atrophy (MSA) and Parkinson's disease (PD) based on clinical diagnostic criteria can be challenging, especially at an early stage. Leveraging deep learning methods and magnetic resonance imaging (MRI) data has shown great potential in aiding automatic diagnosis. Objective: The aim was to determine the feasibility of a three‐dimensional convolutional neural network (3D CNN)–based approach using multimodal, multicentric MRI data for differentiating MSA and its variants from PD. Methods: MRI data were retrospectively collected from three MSA French reference centers. We computed quantitative maps of gray matter density (GD) from a T1‐weighted sequence and mean diffusivity (MD) from diffusion tensor imaging. These maps were used as input to a 3D CNN, either individually (“monomodal,” “GD” or “MD”) or in combination (“bimodal,” “GD‐MD”). Classification tasks included the differentiation of PD and MSA patients. Model interpretability was investigated by analyzing misclassified patients and providing a visual interpretation of the most activated regions in CNN predictions. Results: The study population included 92 patients with MSA (50 with MSA‐P, parkinsonian variant; 33 with MSA‐C, cerebellar variant; 9 with MSA‐PC, mixed variant) and 64 with PD. The best accuracies were obtained for the PD/MSA (0.88 ± 0.03 with GD‐MD), PD/MSA‐C&PC (0.84 ± 0.08 with MD), and PD/MSA‐P (0.78 ± 0.09 with GD) tasks. Patients misclassified by the CNN exhibited fewer and milder image alterations, as found using an image‐based z score analysis. Activation maps highlighted regions involved in MSA pathophysiology, namely the putamen and cerebellum. Conclusions: Our findings hold promise for developing an efficient, MRI‐based, and user‐independent diagnostic tool suitable for differentiating parkinsonian syndromes in clinical practice. © 2025 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.Keywords
Funding Information
- Agence Nationale de la Recherche (Projet‐ANR‐20‐CE17‐0028)
- Chugiak-Eagle River Foundation
This publication has 41 references indexed in Scilit:
- Automated Imaging Differentiation for ParkinsonismJAMA Neurology, 2025
- Houston, We Have AI Problem! Quality Issues with Neuroimaging‐Based Artificial Intelligence in Parkinson's Disease: A Systematic ReviewMovement Disorders, 2024
- Contribution of MRI for the Early Diagnosis of Parkinsonism in Patients with Diagnostic UncertaintyMovement Disorders, 2024
- The Movement Disorder Society Criteria for the Diagnosis of Multiple System AtrophyMovement Disorders, 2022
- Automated Categorization of Parkinsonian Syndromes Using Magnetic Resonance Imaging in a Clinical SettingMovement Disorders, 2020
- Automated Analysis of Diffusion‐Weighted Magnetic Resonance Imaging for the Differential Diagnosis of Multiple System Atrophy from Parkinson's DiseaseMovement Disorders, 2020
- MRI supervised and unsupervised classification of Parkinson's disease and multiple system atrophyMovement Disorders, 2018
- Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classificationMovement Disorders, 2016
- Multimodal MRI assessment of nigro‐striatal pathway in multiple system atrophy and Parkinson diseaseMovement Disorders, 2015
- Conventional magnetic resonance imaging in confirmed progressive supranuclear palsy and multiple system atrophyMovement Disorders, 2012