{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T14:03:35Z","timestamp":1790949815538,"version":"4.1.0"},"reference-count":0,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":149,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep learning models have achieved remarkable success in segmenting brain white matter lesions in multiple sclerosis (MS), becoming integral to both research and clinical workflows. While brain lesions have gained significant attention in MS research, the involvement of spinal cord lesions in MS is relatively understudied. This is largely owed to the variability in spinal cord magnetic resonance imaging (MRI) acquisition protocols, high individual anatomical differences, the complex morphology and size of spinal cord lesions - and lastly, the scarcity of labeled datasets required to develop robust segmentation tools. As a result, automatic segmentation of spinal cord MS lesions remains a significant challenge. Although some segmentation tools exist for spinal cord lesions, most have been developed using sagittal T2-weighted (T2w) sequences primarily focusing on cervical spines. With the growing importance of spinal cord imaging in MS, axial T2w scans are becoming increasingly relevant due to their superior sensitivity in detecting lesions compared to sagittal acquisition protocols. However, most existing segmentation methods struggle to effectively generalize to axial sequences due to differences in image characteristics caused by the highly anisotropic spinal cord scans. To address these challenges, we developed a robust, open-source lesion segmentation tool tailored specifically for axial T2w scans covering the whole spinal cord. We investigated key factors influencing lesion segmentation, including the impact of stitching together individually acquired spinal regions, straightening the spinal cord, and comparing the effectiveness of 2D and 3D convolutional neural networks (CNNs). Drawing on these insights, we trained a multi-center model using an extensive dataset of 582 MS patients, resulting in a dataset comprising an entirety of 2,167 scans. We empirically evaluated the model\u2019s segmentation performance across various spinal segments for lesions with varying sizes. Our model significantly outperforms the current state-of-the-art methods, providing consistent segmentation across cervical, thoracic and lumbar regions. To support the broader research community, we integrate our model into the widely-used Spinal Cord Toolbox (v7.0 and above), making it accessible via the command sct_deepseg lesion_ms_axial_t2 -i &amp;lt;path-to-image.nii.gz&amp;gt;.<\/jats:p>","DOI":"10.1162\/imag.a.45","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T15:15:28Z","timestamp":1748618128000},"update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["Automatic segmentation of spinal cord lesions in MS: A robust tool for axial T2-weighted MRI scans"],"prefix":"10.1162","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2940-5514","authenticated-orcid":false,"given":"Enamundram","family":"Naga Karthik","sequence":"first","affiliation":[{"name":"NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada"},{"name":"Mila - Quebec AI Institute, Montreal, QC, Canada"},{"name":"Chair for AI in Healthcare and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2224-7600","authenticated-orcid":false,"given":"Julian","family":"McGinnis","sequence":"additional","affiliation":[{"name":"Chair for AI in Healthcare and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"},{"name":"Department of Neurology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2039-3685","authenticated-orcid":false,"given":"Ricarda","family":"Wurm","sequence":"additional","affiliation":[{"name":"Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Ruehling","sequence":"additional","affiliation":[{"name":"Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6656-3680","authenticated-orcid":false,"given":"Robert","family":"Graf","sequence":"additional","affiliation":[{"name":"Chair for AI in Healthcare and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"},{"name":"Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7398-4990","authenticated-orcid":false,"given":"Jan","family":"Valosek","sequence":"additional","affiliation":[{"name":"NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada"},{"name":"Mila - Quebec AI Institute, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3122-1957","authenticated-orcid":false,"given":"Pierre-Louis","family":"Benveniste","sequence":"additional","affiliation":[{"name":"NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada"},{"name":"Mila - Quebec AI Institute, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5711-0054","authenticated-orcid":false,"given":"Markus","family":"Lauerer","sequence":"additional","affiliation":[{"name":"Department of Neurology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3943-5530","authenticated-orcid":false,"given":"Jason","family":"Talbott","sequence":"additional","affiliation":[{"name":"Department of Radiology and Biomedical Imaging, Zuckerberg San Francisco General Hospital, University of California, San Francisco, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8601-5534","authenticated-orcid":false,"given":"Rohit","family":"Bakshi","sequence":"additional","affiliation":[{"name":"Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahamat","family":"Tauhid","sequence":"additional","affiliation":[{"name":"Brigham and Women\u2019s Hospital, Harvard Medical School, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0232-1636","authenticated-orcid":false,"given":"Timothy","family":"Shepherd","sequence":"additional","affiliation":[{"name":"NYU Langone Medical Center, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9650-6222","authenticated-orcid":false,"given":"Achim","family":"Berthele","sequence":"additional","affiliation":[{"name":"Department of Neurology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-9103","authenticated-orcid":false,"given":"Claus","family":"Zimmer","sequence":"additional","affiliation":[{"name":"Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5985-6784","authenticated-orcid":false,"given":"Bernhard","family":"Hemmer","sequence":"additional","affiliation":[{"name":"Department of Neurology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5683-5889","authenticated-orcid":false,"given":"Daniel","family":"Rueckert","sequence":"additional","affiliation":[{"name":"Chair for AI in Healthcare and Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"},{"name":"Department of Computing, Imperial College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2963-7772","authenticated-orcid":false,"given":"Benedikt","family":"Wiestler","sequence":"additional","affiliation":[{"name":"AI for Image-Guided Diagnosis and Therapy, School of Medicine and Health, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7557-0003","authenticated-orcid":false,"given":"Jan S.","family":"Kirschke","sequence":"additional","affiliation":[{"name":"Department of Diagnostic and Interventional Neuroradiology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-9532","authenticated-orcid":false,"given":"Julien","family":"Cohen-Adad","sequence":"additional","affiliation":[{"name":"NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada"},{"name":"Mila - Quebec AI Institute, Montreal, QC, Canada"},{"name":"Functional Neuroimaging Unit, CRIUGM, Universit\u00e9 de Montr\u00e9al, Montreal, QC, Canada"},{"name":"Centre de Recherche du CHU Sainte-Justine, Universit\u00e9 de Montr\u00e9al, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9545-2709","authenticated-orcid":false,"given":"Mark","family":"M\u00fchlau","sequence":"additional","affiliation":[{"name":"Department of Neurology, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2025,5,30]]},"container-title":["Imaging Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/IMAG.a.45\/2528780\/imag.a.45.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/IMAG.a.45\/2528780\/imag.a.45.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T15:15:28Z","timestamp":1748618128000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/imag\/article\/doi\/10.1162\/IMAG.a.45\/131129\/Automatic-segmentation-of-spinal-cord-lesions-in"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":0,"URL":"https:\/\/doi.org\/10.1162\/imag.a.45","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2025.01.22.25320959","asserted-by":"object"}]},"ISSN":["2837-6056"],"issn-type":[{"value":"2837-6056","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]}}}