EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data

Functional magnetic resonance imaging (fMRI) of the spinal cord is relevant for studying sensation, movement, and autonomic function. Preprocessing of spinal cord fMRI data involves segmentation of the spinal cord on gradient-echo echo planar imaging (EPI) images. Current automated segmentation methods do not work well on these data, due to the low spatial resolution, susceptibility artifacts causing distortions and signal drop-out, ghosting, and motion-related artifacts. Consequently, this segmentation task demands a considerable amount of manual effort which takes time and is prone to user bias. In this work, we (i) gathered a multi-center dataset of spinal cord gradient-echo EPI with ground-truth segmentations and shared it on OpenNeuro https://openneuro.org/datasets/ds005143/versions/1.3.1 and (ii) developed a deep learning-based model, EPISeg, for the automatic segmentation of the spinal cord on gradient-echo EPI data. We observe a significant improvement in terms of segmentation quality compared with other available spinal cord segmentation models. Our model is resilient to different acquisition protocols as well as commonly observed artifacts in fMRI data. The training code is available at https://github.com/sct-pipeline/fmri-segmentation/, and the model has been integrated into the Spinal Cord Toolbox as a command-line tool.

Authors

Institutions

Publication Details

Journal
Imaging Neuroscience
Published
2025-01-01
DOI
https://doi.org/10.1162/imag.a.98
Citations
3
Primary Topic
Medical Imaging and Analysis
Type
article
Field-Weighted Citation Impact
2.02

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data

Sean Mackey, Shahabeddin Vahdat, Dimitri Van De Ville, Jürgen Finsterbusch et al.
3 citations
Imaging Neuroscience
Medical Imaging and Analysis
2.02
article

EPISeg: Automated segmentation of the spinal cord on echo planar images using open-access multi-center data

Sean Mackey, Shahabeddin Vahdat, Dimitri Van De Ville, Jürgen Finsterbusch, Véronique Marchand‐Pauvert, Gary H. Glover, Julien Cohen‐Adad, J.C. Brooks, Fauziyya Muhammad, Simon Schading‐Sassenhausen, Dario Pfyffer, Molly G. Bright, Benjamin De Leener, Jan Haaker, Kimberly J. Hemmerling, Christine Law, Christian Büchel, Merve Kaptan, Mahdi Mobarak-Abadi, Stephen B. McMahon, Patrick Freund, Kenneth A. Weber, Alice Dabbagh, Grace Haynes, Yufen Chen, Falk Eippert, Zachary A. Smith, Gergely Dávid, Olivia S. Kowalczyk, Alexandra Tinnermann, Ali Khatibi, Katherine T. Martucci, Mark A. Hoggarth, David J. Lythgoe, Nawal Kinany, Robert Barry, Dimitra Tsivaka, Christian W. Kündig, Matthew A. Howard, Todd Parish, Rohan Banerjee
article en
3 citations

Abstract

Functional magnetic resonance imaging (fMRI) of the spinal cord is relevant for studying sensation, movement, and autonomic function. Preprocessing of spinal cord fMRI data involves segmentation of the spinal cord on gradient-echo echo planar imaging (EPI) images. Current automated segmentation methods do not work well on these data, due to the low spatial resolution, susceptibility artifacts causing distortions and signal drop-out, ghosting, and motion-related artifacts. Consequently, this segmentation task demands a considerable amount of manual effort which takes time and is prone to user bias. In this work, we (i) gathered a multi-center dataset of spinal cord gradient-echo EPI with ground-truth segmentations and shared it on OpenNeuro https://openneuro.org/datasets/ds005143/versions/1.3.1 and (ii) developed a deep learning-based model, EPISeg, for the automatic segmentation of the spinal cord on gradient-echo EPI data. We observe a significant improvement in terms of segmentation quality compared with other available spinal cord segmentation models. Our model is resilient to different acquisition protocols as well as commonly observed artifacts in fMRI data. The training code is available at https://github.com/sct-pipeline/fmri-segmentation/, and the model has been integrated into the Spinal Cord Toolbox as a command-line tool.

Imaging NeuroscienceVol. 3
Northwestern University (US), University of Geneva (CH), Montreal Neurological Institute and Hospital (CA), Centre National de la Recherche Scientifique (FR), Harvard University (US), University of Thessaly (GR), University of Liverpool (GB), Inserm (FR), Universität Hamburg (DE), Queen Mary University of London (GB), King's College London (GB), University of Zurich (CH), Centre Hospitalier Universitaire Sainte-Justine (CA), University of Florida (US), Sorbonne Université (FR), Massachusetts General Hospital (US), Harvard–MIT Division of Health Sciences and Technology (US), McCormick (United States) (US), University Medical Center Hamburg-Eppendorf (DE), Laboratoire d’Imagerie Biomédicale (FR), Universitätsklinik Balgrist (CH), Duke Medical Center (US), Institut Universitaire de Gériatrie de Montréal (CA), Athinoula A. Martinos Center for Biomedical Imaging (US), Max Planck Institute for Human Cognitive and Brain Sciences (DE), National Hospital for Neurology and Neurosurgery (GB), Duke University Hospital (US), Mila - Quebec Artificial Intelligence Institute (CA), University College London (GB), North Central College (US), Polytechnique Montréal (CA), University of Oklahoma Health Sciences Center (US), McGill University (CA), École Polytechnique Fédérale de Lausanne (CH), Massachusetts Institute of Technology (US), Université de Montréal (CA), University of Birmingham (GB), University of Oklahoma (US), Stanford University (US)
National Science Foundation, Craig H. Neilsen Foundation, Polytechnique Montréal, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Canada First Research Excellence Fund, Institut de Valorisation des Données, National Institutes of Health, Natural Sciences and Engineering Research Council of Canada
Openalex Percentile: Top 13%
Medical Imaging and Analysis
2.02
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.