Enabling new insights from old scans by repurposing clinical MRI archives for multiple sclerosis research
Magnetic resonance imaging (MRI) biomarkers are vital for multiple sclerosis (MS) clinical research and trials but quantifying them requires multi-contrast protocols and limits the use of abundant single-contrast hospital archives. We developed MindGlide, a deep learning model to extract brain region and white matter lesion volumes from any single MRI contrast. We trained MindGlide on 4247 brain MRI scans from 2934 MS patients across 592 scanners, and externally validated it using 14,952 scans from 1,001 patients in two clinical trials (primary-progressive MS and secondary-progressive MS trials) and a routine-care MS dataset. The model outperformed two state-of-the-art models when tested against expert-labelled lesion volumes. In clinical trials, MindGlide detected treatment effects on T2-lesion accrual and cortical and deep grey matter volume loss. In routine-care data, T2-lesion volume increased with moderate-efficacy treatment but remained stable with high-efficacy treatment. MindGlide uniquely enables quantitative analysis of archival single-contrast MRIs, unlocking insights from untapped hospital datasets.
Authors
- Jeremy Chataway (ORCID: https://orcid.org/0000-0001-7286-6901)
- Geoff J.M. Parker (ORCID: https://orcid.org/0000-0003-2934-2234)
- Jonathan Stutters (ORCID: https://orcid.org/0000-0002-9151-0844)
- Owain Kenway
- Yael Hacohen (ORCID: https://orcid.org/0000-0001-8490-9657)
- Philipp Goebl (ORCID: https://orcid.org/0000-0002-4970-2340)
- Daniel C. Alexander (ORCID: https://orcid.org/0000-0003-2439-350X)
- Jed Wingrove (ORCID: https://orcid.org/0000-0002-0454-1299)
- Arman Eshaghi (ORCID: https://orcid.org/0000-0002-6652-3512)
- Sridar Narayanan (ORCID: https://orcid.org/0000-0002-6283-150X)
- Juan Eugenio Iglesias (ORCID: https://orcid.org/0000-0001-7569-173X)
- D. Louis Collins (ORCID: https://orcid.org/0000-0002-8432-7021)
- Cheryl Hemingway (ORCID: https://orcid.org/0000-0002-3899-3015)
- Thomas Rossor (ORCID: https://orcid.org/0000-0001-5472-1813)
- Frederik Barkhof (ORCID: https://orcid.org/0000-0003-3543-3706)
- Alan J. Thompson (ORCID: https://orcid.org/0000-0002-4333-8496)
- Douglas Lorne Arnold (ORCID: https://orcid.org/0000-0003-4266-0106)
- Silvia Da Graca Ramos
- Olga Ciccarelli (ORCID: https://orcid.org/0000-0001-7485-1367)
- Neil P. Oxtoby (ORCID: https://orcid.org/0000-0003-0203-3909)
- Barbara Brito Vega (ORCID: https://orcid.org/0000-0002-0476-7220)
- Evangeline Wassmer (ORCID: https://orcid.org/0000-0002-2446-1106)
- Declan Chard (ORCID: https://orcid.org/0000-0003-3076-2682)
- Omar Abdelmannan
Institutions
- Montreal Neurological Institute and Hospital (CA)
- Harvard University (US)
- Queen Mary University of London (GB)
- Aston University (GB)
- Guy's and St Thomas' NHS Foundation Trust (GB)
- Great Ormond Street Hospital (GB)
- School of Advanced Study (GB)
- National Institute for Health and Care Research (GB)
- Massachusetts General Hospital (US)
- Birmingham Children's Hospital (GB)
- Athinoula A. Martinos Center for Biomedical Imaging (US)
- The London College (GB)
- Amsterdam University Medical Centers (NL)
- University College London (GB)
- Massachusetts Institute of Technology (US)
- Vrije Universiteit Amsterdam (NL)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-04-07
- DOI
- https://doi.org/10.1038/s41467-025-58274-8
- Citations
- 11
- Primary Topic
- Multiple Sclerosis Research Studies
- Type
- article
- Field-Weighted Citation Impact
- 16.19
Funders
- International Progressive MS Alliance
- National Institute for Health and Care Research
- Department of Health and Social Care
- University College London
- National Institutes of Health