Deep Learning Modeling to Differentiate Multiple Sclerosis From MOG Antibody-Associated Disease.
Authors
Affiliations (44)
Affiliations (44)
- Department of Medicine, Surgery and Neuroscience, University of Siena, Siena, Italy.
- Siena Imaging SRL, 53100 Siena, Italy.
- Department NEUROFARBA, University of Florence, Italy.
- IRCCS Fondazione Don Carlo Gnocchi, Florence, Italy.
- Departamento de Neurologia, Faculdade de Medicina, Universidade de São Paulo, São Paulo SP, Brazil.
- Neurology-Neuroimmunology Department Multiple Sclerosis Centre of Catalonia (Cemcat), Vall d'Hebron Barcelona Hospital Campus. Universitat Autònoma de Barcelona, Barcelona, Spain.
- Institute of Neuroradiology, St. Josef Hospital, Ruhr University Bochum, Germany.
- Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, London, United Kingdom.
- Department of Advanced Medical and Surgical Sciences, University of Campania "Luigi Vanvitelli", Naples, Italy.
- Sorbonne Université, Paris Brain Institute, CNRS, Inserm, France.
- AP-HP, Hôpital Universitaire Pitié-Salpêtrière, Paris, France.
- Neurology Section of Department of Neuroscience, Biomedicine and Movement, University of Verona, Italy.
- Department of Neurology, Oslo University Hospital and Faculty of Medicine, University of Oslo, Norway.
- Departamento de Radiologia e Oncologia, Faculdade de Medicina, Universidade de São Paulo, São Paulo SP, Brazil.
- Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Service de Neurologie, Sclérose en Plaques, Pathologies de la Myéline et Neuro-inflammation, Hôpital Neurologique Pierre Wertheimer, Hospices Civils de Lyon, France.
- Neuroimaging Research Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Neurology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Neurorehabilitation Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Neurophysiology Service, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Vita-Salute San Raffaele University, Milan, Italy.
- Department of Neurosciences, S. Camillo-Forlanini Hospital, Rome, Italy.
- Translational Imaging in Neurology (ThINk) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Switzerland.
- Multiple Sclerosis Centre, Departments of Neurology, Clinical Research and Biomedicine, University Hospital and University Basel, Switzerland.
- Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Switzerland.
- Department of Neurology, University Medical Center of the Johannes Gutenberg University Mainz, Germany.
- Department of Neurology, University Medicine of Greifswald, Germany.
- Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health (DiNOGMI), University of Genoa, Italy.
- IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
- NMO Clinical Service at the Walton Centre, Liverpool, United Kingdom.
- Department of Neurology, Cleveland Clinic, AbuDhabi, UAE.
- Neuroimmunology and Multiple Sclerosis Unit and Laboratory of Advanced Imaging in Neuroimmunological Diseases (ImaginEM), Hospital Clinic and Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), University of Barcelona, Spain.
- Department of Neurology, St. Josef Hospital, Ruhr University Bochum, Germany.
- Department of Clinical Neurology, John Radcliffe Hospital, Oxford, United Kingdom.
- Careggi University Hospital of Florence, Italy.
- Experimental and Clinical Research Center, Max Delbrueck Center for Molecular Medicine and Charité - Universitaetsmedizin Berlin, Germany.
- UCL Hawkes Institute, London, United Kingdom.
- E-Health Center Universitat Oberta de Catalunya, Barcelona, Spain.
- Section of Neuroradiology, Department of Radiology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Spain.
- Pontifícia Universidade Católica do Rio Grande do Sul, School of Medicine, Porto Alegre RS, Brazil.
- Division of Radiology and Nuclear Medicine, Oslo University Hospital, Norway.
- Department of Radiology & Nuclear Medicine, Amsterdam UMC, Vrije Universiteit, the Netherlands.
- Queen Square Institute of Neurology and Centre for Medical Image Computing, University College, London, United Kingdom; and.
- National Institute for Health Research (NIHR) University College London Hospitals (UCLH) Biomedical Research Centre, London, United Kingdom.
Abstract
Multiple sclerosis (MS) is common in adults while myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD) is rare. Our previous machine-learning algorithm, using clinical variables, ≤6 brain lesions, and no Dawson fingers, achieved 79% accuracy, 78% sensitivity, and 80% specificity in distinguishing MOGAD from MS but lacked validation. The aim of this study was to (1) evaluate the clinical/MRI algorithm for distinguishing MS from MOGAD, (2) develop a deep learning (DL) model, (3) assess the benefit of combining both, and (4) identify key differentiators using probability attention maps (PAMs). This multicenter, retrospective, cross-sectional MAGNIMS study included scans from 19 centers. Inclusion criteria were as follows: adults with non-acute MS and MOGAD, with high-quality T2-fluid-attenuated inversion recovery and T1-weighted scans. Brain scans were scored by 2 readers to assess the performance of the clinical/MRI algorithm on the validation data set. A DL-based classifier using a ResNet-10 convolutional neural network was developed and tested on an independent validation data set. PAMs were generated by averaging correctly classified attention maps from both groups, identifying key differentiating regions. We included 406 MRI scans (218 with relapsing remitting MS [RRMS], mean age: 39 years ±11, 69% F; 188 with MOGAD, age: 41 years ±14, 61% F), split into 2 data sets: a training/testing set (n = 265: 150 with RRMS, age: 39 years ±10, 72% F; 115 with MOGAD, age: 42 years ±13, 61% F) and an independent validation set (n = 141: 68 with RRMS, age: 40 years ±14, 65% F; 73 with MOGAD, age: 40 years ±15, 63% F). The clinical/MRI algorithm predicted RRMS over MOGAD with 75% accuracy (95% CI 67-82), 96% sensitivity (95% CI 88-99), and specificity 56% (95% CI 44-68) in the validation cohort. The DL model achieved 77% accuracy (95% CI 64-89), 73% sensitivity (95% CI 57-89), and 83% specificity (95% CI 65-96) in the training/testing cohort, and 70% accuracy (95% CI 63-77), 67% sensitivity (95% CI 55-79), and 73% specificity (95% CI 61-83) in the validation cohort without retraining. When combined, the classifiers reached 86% accuracy (95% CI 81-92), 84% sensitivity (95% CI 75-92), and 89% specificity (95% CI 81-96). PAMs identified key region volumes: corpus callosum (1872 mm<sup>3</sup>), left precentral gyrus (341 mm<sup>3</sup>), right thalamus (193 mm<sup>3</sup>), and right cingulate cortex (186 mm<sup>3</sup>) for identifying RRMS and brainstem (629 mm<sup>3</sup>), hippocampus (234 mm<sup>3</sup>), and parahippocampal gyrus (147 mm<sup>3</sup>) for identifying MOGAD. Both classifiers effectively distinguished RRMS from MOGAD. The clinical/MRI model showed higher sensitivity while the DL model offered higher specificity, suggesting complementary roles. Their combination improved diagnostic accuracy, and PAMs revealed distinct damage patterns. Future prospective studies should validate these models in diverse, real-world settings. This study provides Class III evidence that both a clinical/MRI algorithm and an MRI-based DL model accurately distinguish RRMS from MOGAD.