Skip to main content

BRIEF RESEARCH REPORT article

Front. Aging Neurosci.
Sec. Parkinson’s Disease and Aging-related Movement Disorders
Volume 16 - 2024 | doi: 10.3389/fnagi.2024.1425095
This article is part of the Research Topic Contribution of artificial intelligence-based tools to the study of Parkinson’s disease and other movement disorders View all 6 articles

Classification of Parkinson's Disease by Deep Learning on Midbrain MRI

Provisionally accepted
Thomas Welton Thomas Welton 1*Septian Hartono Septian Hartono 1Weiling Lee Weiling Lee 2Peik Yen Teh Peik Yen Teh 2Wenlu Hou Wenlu Hou 2Robert Chen Robert Chen 2Celeste Chen Celeste Chen 2Ee Wei Lim Ee Wei Lim 2Prakash M. Kumar Prakash M. Kumar 2Louis Tan Louis Tan 1Eng-King Tan Eng-King Tan 2Ling Ling Chan Ling Ling Chan 2
  • 1 National Neuroscience Institute (NNI), Singapore, Singapore
  • 2 Singapore General Hospital, Singapore, Singapore

The final, formatted version of the article will be published soon.

    Susceptibility map weighted imaging (SMWI), based on quantitative susceptibility mapping (QSM), allows accurate nigrosome-1 (N1) evaluation and has been used to develop Parkinson’s disease (PD) deep learning (DL) classification algorithms. Neuromelanin-sensitive (NMS) MRI could improve automated quantitative N1 analysis by revealing neuromelanin content. This study aimed to compare classification performance of four approaches to PD diagnosis: (1) N1 quantitative “QSM-NMS" composite marker, (2) DL model for N1 morphological abnormality using SMWI (“Heuron IPD”), (3) DL model for N1 volume using SMWI (“Heuron NI”), and (4) N1 SMWI neuroradiological evaluation. PD patients (n=82; aged 65±9 years; 68% male) and healthy-controls (n=107; 66±7 years; 48% male) underwent 3T midbrain MRI with T2*-SWI multi-echo-GRE (for QSM and SMWI), and NMS-MRI. AUC was used to compare diagnostic performance. We tested for correlation of each imaging measure with clinical parameters (severity, duration and levodopa dosing) by Spearman-Rho or Kendall-Tao-Beta correlation. Classification performance was excellent for the QSM-NMS composite marker (AUC=0.94), N1 SMWI abnormality (AUC=0.92), N1 SMWI volume (AUC=0.90), and neuroradiologist (AUC=0.98). Reasons for misclassification were right-left asymmetry, through-plane re-slicing, pulsation artefacts, and thin N1. In the two DL models, all 18/189 (9.5%) cases misclassified by Heuron IPD were controls with normal N1 volumes. We found significant correlation of the SN QSM-NMS composite measure with levodopa dosing (rho=-0.303, p=0.006). Our data demonstrate excellent performance of a quantitative QSM-NMS marker and automated DL PD classification algorithms based on midbrain MRI, while suggesting potential further improvements. Clinical utility is supported but requires validation in earlier stage PD cohorts.

    Keywords: machine learning, Substantia Nigra, Nigrosome-1, Parkinson's disease, susceptibility

    Received: 29 Apr 2024; Accepted: 01 Aug 2024.

    Copyright: © 2024 Welton, Hartono, Lee, Teh, Hou, Chen, Chen, Lim, Kumar, Tan, Tan and Chan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Thomas Welton, National Neuroscience Institute (NNI), Singapore, Singapore

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.