Abstract #0961
EPISeg: Automatic Segmentation of Spinal Cord fMRI Data
Rohan Banerjee1,2,3, Merve Kaptan4, Alexandra Tinnermann5, Ali Khatibi6,7,8, Alice Dabbagh9, Christian Buechel5, Christian Kündig10, Christine Law4, Dario Pfyffer4,10, David Lythgoe11, Dimitra Tsivaka11,12, Dimitri Van De Ville13,14, Falk Eippert9, Fauziyya Muhammad15, Gary Glover16, Gergely David10, Grace Haynes17, Jan Haaker5, Jonathan C. W. Brooks18, Julien Doyon6,7, Jürgen Finsterbusch5, Katherine T. Martucci19, Kimberly J. Hemmerling20,21, Mahdi Mobarak-Abadi7, Mark A Hoggarth20,22, Matthew Howard11, Molly Bright20,21, Nawal Kinany13,14, Olivia Kowalczyk11,23, Ovidiu Lungu6,7,24, Patrick Freund10,25,26, Rangaprakash Deshpande27,28, Robert L. Barry27,28,29, Sean Mackey4, Shahabeddin Vahdat6,7,30, Simon Schading10, Sonia Medina11, Stephen McMahon31, Steven C. R. Williams11, Todd B. Parrish21,32, Véronique Marchand-Pauvert33, Yasin Dhaher34, Yufen Chen32, Zachary Smith15, Kenneth A. Weber II4, Benjamin De Leener1,3,35, and Julien Cohen-Adad2,3,35,36
1Department of Computer Science, Polytechnique Montreal, Montreal, QC, Canada, 2Mila, Quebec AI Institute, Montreal, QC, Canada, 3NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada, 4Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States, 5Department of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, Hamburg, Germany, 6McConnell Brain Imaging Center, Montreal Neurological Institute, McGill University, Montreal, QC, Canada, 7Centre de recherche de l’Institut Universitaire de Geriatrie de Montreal, Montreal, QC, Canada, 8Centre of Precision Rehabilitation for Spinal Pain (CPR Spine), University of Birmingham, Birmingham, United Kingdom, 9Max Planck Research Group Pain Perception, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany, 10Spinal Cord Injury Center, Balgrist University Hospital, University of Zürich, Zürich, Switzerland, 11Department of Neuroimaging, Institute of Psychology, Psychiatry & Neuroscience, King's College London, London, United Kingdom, 12Medical Physics Department, Medical School, University of Thessaly, Larisa, Greece, 13Department of Radiology and Medical Informatics, University of Geneva, Geneva, Switzerland, 14Neuro-X Institute, Ecole Polytechnique Fédérale de Lausanne (EPFL), Geneva, Switzerland, 15Department of Neurological Surgery, University of Oklahoma Health Sciences Center, Oklahoma City, OK, United States, 16Radiological Sciences Laboratory, Department of Radiology, Stanford University School of Medicine, Palo Alto, CA, United States, 17Stephenson School of Biomedical Engineering, University of Oklahoma Health Sciences Center, Norman, OK, United States, 18Department of Psychology, University of Liverpool, Liverpool, United Kingdom, 19Human Affect and Pain Neuroscience Lab, Department of Anesthesiology, Duke University Medical Center, Durham, NC, United States, 20Department of Physical Therapy and Human Movement Sciences, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States, 21Department of Biomedical Engineering, McCormick School of Engineering, Northwestern University, Evanston, IL, United States, 22Department of Physical Therapy, North Central College, Naperville, IL, United States, 23Functional Imaging Labora- tory, Department of Imaging Neuroscience , Queen Square Institute of Neurology, University College London, London, United Kingdom, 24Department of psychiatry and addictology, University of Montreal, Montreal, QC, Canada, 25Department of Neurophysics, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany, 26Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London, London, United Kingdom, 27Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States, 28Department of Radiology, Harvard Medical School, Boston, MA, United States, 29Harvard-Massachusetts Institute of Technology Health Sciences & Technology, Cambridge, MA, United States, 30Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, United States, 31Wolfson Centre for Age Related Diseases, King's College London, London, United Kingdom, 32Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States, 33Sorbonne Université, Inserm, CNRS, Laboratoire d'Imagerie Biomédicale, Paris, France, 34Department of Physical Medicine and Rehabilitation, University of Texas Southwestern Medical Center, Dallas, TX, United States, 35Functional Neuroimaging Unit, CRIUGM, University of Montreal, Montreal, QC, Canada, 36Research Center, Ste-Justine Hospital University Centre, Montreal, QC, Canada
Synopsis
Keywords: AI/ML Software, AI/ML Software
Motivation: Spinal cord fMRI holds promise for somatosensory and motor research, but challenges in data acquisition and preprocessing limit its potential.
Goal(s): Develop an automated segmentation tool for spinal cord fMRI data that minimizes manual intervention and improves segmentation accuracy which is important for data analysis.
Approach: We introduce EPISeg, a deep learning-based segmentation method trained on an open-source multi-site dataset of 406 subjects using active learning with human-in-the-loop feedback.
Results: EPISeg outperformed established methods like PropSeg, DeepSeg, and a Contrast-agnostic model, achieving a Dice score of 0.88.
Impact: EPISeg significantly enhances spinal fMRI research by enabling automated, accurate segmentations of EPI data, overcoming limitations of manual segmentation. Its integration into SCT broadens accessibility and reproducibility, facilitating robust group-level analyses essential for advancing studies of spinal processes and disorders.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Click here for more information on becoming a member.
