TY - UNPB
T1 - EPISeg
T2 - Automated segmentation of the spinal cord on echo planar images using open-access multi-center data
AU - Banerjee, Rohan
AU - Kaptan, Merve
AU - Tinnermann, Alexandra
AU - Khatibi, Ali
AU - Dabbagh, Alice
AU - Büchel, Christian
AU - Kündig, Christian W.
AU - Law, Christine S.W.
AU - Pfyffer, Dario
AU - Lythgoe, David J.
AU - Tsivaka, Dimitra
AU - Ville, Dimitri Van De
AU - Eippert, Falk
AU - Muhammad, Fauziyya
AU - Glover, Gary H.
AU - David, Gergely
AU - Haynes, Grace
AU - Haaker, Jan
AU - Brooks, Jonathan C. W.
AU - Finsterbusch, Jürgen
AU - Martucci, Katherine T.
AU - Hemmerling, Kimberly J.
AU - Mobarak-Abadi, Mahdi
AU - Hoggarth, Mark A.
AU - Bright, Molly G.
AU - Kinany, Nawal
AU - Kowalczyk, Olivia S.
AU - Freund, Patrick
AU - Barry, Robert L.
AU - Mackey, Sean
AU - Vahdat, Shahabeddin
AU - Schading, Simon
AU - McMahon, Stephen B.
AU - Parish, Todd
AU - Marchand-Pauvert, Véronique
AU - Chen, Yufen
AU - Smith, Zachary A.
AU - Kenneth A. Weber, II
AU - Leener, Benjamin De
AU - Cohen-Adad, Julien
PY - 2025/1/10
Y1 - 2025/1/10
N2 - 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/1.3.0, 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 to 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.
AB - 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/1.3.0, 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 to 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.
U2 - 10.1101/2025.01.07.631402
DO - 10.1101/2025.01.07.631402
M3 - Preprint
BT - EPISeg
PB - bioRxiv
ER -