Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.
Authors
Affiliations (42)
Affiliations (42)
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada; Mila-Quebec AI Institute, Montreal, QC, Canada.
- Centre de Recherche du Centre Hospitalier de l'Université de Montréal (CHUM), Montréal, QC, Canada.
- McConnell Brain Imaging Center, McGill, Montréal, QC, Canada.
- The Neuro-Montreal Neurological Institute and Hospital, McGill University, Montreal, QC, Canada; Department of Neuroradiology, Sorbonne Université, Institut du Cerveau-Paris Brain Institute-ICM, AP-HP, CNRS, Inserm, Hôpital de la Pitié Salpêtrière, Paris, France.
- McConnell Brain Imaging Center, McGill University, Montréal, QC, Canada; NeuroRx, A Clario Company, Montréal, QC, Canada; 7T MRI MS Working Group, North American Imaging in MS, MNI, Montréal, QC, Canada.
- Department of Radiology, Toho University Omori Medical Center, Tokyo, Japan.
- Department of Radiology, Mayo Clinic College of Medicine and Science, Rochester, MN, USA.
- Department of Neurology, University Hospital Basel, University of Basel, Basel, Switzerland; National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
- Aix-Marseille Univ, CNRS, CRMBM, Marseille, France; AP-HM, Hôpital Universitaire Timone, CEMEREM, Marseille, France; Neurology Department, AP-HM, Hôpital Universitaire Timone, Marseille, France.
- Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
- Univ Rennes, Inria, CNRS, Inserm, IRISA UMR 6074, Visages U1128, Rennes, France; Radiology Department, CHU Rennes, Rennes, France.
- Departments of Radiology and Biomedical Engineering, Mayo Clinic College of Medicine and Science, Rochester, MN, USA.
- Brisset JC Ph.D.-Medical Imaging Consulting, Sophia Antipolis, Valbonne, France.
- Aix-Marseille Univ, CNRS, CRMBM, Marseille, France; AP-HM, Hôpital Universitaire Timone, CEMEREM, Marseille, France.
- Departments of Neurology & Radiology, NYU Langone Medical Center, New York, NY, USA.
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.
- Queen Square MS Centre, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, London, UK.
- Neurology Department, AP-HM, Hôpital Universitaire Timone, Marseille, France.
- Neuroimaging Research Unit, Division of Neuroscience, 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 Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden; Department of Neuroradiology, Karolinska University Hospital, Stockholm, Sweden.
- Department of Neurology, University Hospital Basel, University of Basel, Basel, Switzerland.
- Departments of Neurology, University of Massachusetts Memorial Medical Center and University of Massachusetts Chan Medical School, Worcester, MA, USA.
- Department of Neurology, Mayo Clinic College of Medicine and Science, Rochester, MN, USA.
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, TUM School of Medicine and Health, Munich, Germany.
- Departments of Medicine (Neurology), Physics, Radiology, University of British Columbia, Vancouver, BC, Canada.
- MS Unit, Department of Neurology, University Hospital of Montpellier, Montpellier, France.
- Department of Medicine (Neurology), University of Toronto, Toronto, ON, Canada; BARLO Multiple Sclerosis Centre and Keenan Research Centre, St. Michael's Hospital, Toronto, ON, Canada.
- Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, China; Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, USA.
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, TUM School of Medicine and Health, Munich, Germany; Institute for AI in Medicine, Technical University of Munich, Munich, Germany.
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada; Mila-Quebec AI Institute, Montreal, QC, Canada; Aix-Marseille Univ, CNRS, CRMBM, Marseille, France; AP-HM, Hôpital Universitaire Timone, CEMEREM, Marseille, France.
- Department of Neurology, School of Medicine and Health, Technical University of Munich, Munich, Germany; TUM-Neuroimaging Center, School of Medicine and Health, Technical University of Munich, Munich, Germany.
- National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA.
- Vanderbilt University Institute of Imaging Science, Nashville, TN, USA.
- Department of Neuroscience, Université de Montréal, Montreal, QC, Canada; Neuroimmunology Research Laboratory, University of Montreal Hospital Research Centre (CRCHUM), Montreal, QC, Canada.
- Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Neurology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
- Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
- Department of Radiology and Biomedical Imaging, Zuckerberg San Francisco General Hospital, University of California, San Francisco, CA, USA.
- School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada.
- Neuroimaging Research Unit, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
- Mila-Quebec AI Institute, Montreal, QC, Canada; Polytechnique Montréal, Montreal, QC, Canada.
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada; Mila-Quebec AI Institute, Montreal, QC, Canada; Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada; Centre de Recherche du CHU Sainte-Justine, Université de Montréal, Montreal, QC, Canada.
Abstract
Characterizing spinal cord multiple sclerosis (MS) lesions in MRI is critical for diagnosis, monitoring, and treatment evaluation. However, current automated approaches for lesion detection and segmentation are typically designed for specific MRI contrasts or acquisition sites, limiting their generalizability in real-world clinical settings where imaging protocols vary widely. This work proposes a robust multi-site, multi-contrast segmentation framework for spinal cord lesions. The segmentation model was trained and evaluated on a large-scale dataset comprising 4428 annotated images from 1849 persons with MS across 23 imaging centers, encompassing six MRI contrasts (T1w, T2w, T2*w, PSIR, STIR, and UNIT1) acquired at 1.5 tesla (T), 3 T, and 7 T. Likert-type assessment performed by neuroradiologist ratings demonstrated superior generalization of the model compared to existing contrast-specific pipelines (<i>p</i> < 0.01). Additional experiments evaluated robustness across spinal levels, acquisition resolutions, binarization thresholds, and quantitative evaluation on external labeled datasets. The proposed model can achieve accurate and reliable spinal cord MS lesion segmentation across heterogeneous MRI data, addressing a key barrier to clinical translation. The model is available in the Spinal Cord Toolbox v7.2 and higher.<b>Code repository:</b> https://github.com/ivadomed/seg-sc-ms-lesion-multicontrast.