SCIseg: Automatic segmentation of T2-weighted intramedullary lesions in spinal 
cord injury

Karthik, Enamundram Naga; Valosek, Jan; Smith, Andrew C.; Pfyffer, Dario; Schading-Sassenhausen, Simon; Farner, VLynn; Weber II, Kenneth A.; Freund, Patrick; Cohen-Adad, Julien

doi:10.1101/2024.01.03.24300794

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Preprint

SCIseg: Automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury

MPS-Authors

/persons/resource/persons188373

Freund, Patrick
Department Neurophysics (Weiskopf), MPI for Human Cognitive and Brain Sciences, Max Planck Society;

External Resource

https://github.com/ivadomed/model_seg_sci
(Research data)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

Karthik_pre.pdf
(Preprint), 7MB

Supplementary Material (public)

There is no public supplementary material available

Citation

Karthik, E. N., Valosek, J., Smith, A. C., Pfyffer, D., Schading-Sassenhausen, S., Farner, V., et al. (2024). SCIseg: Automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury. medRxiv. doi:10.1101/2024.01.03.24300794.

Cite as: https://hdl.handle.net/21.11116/0000-000F-365B-F

Abstract

Purpose To develop a deep learning tool for the automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury (SCI).

Material and Methods This retrospective study included a cohort of SCI patients from three sites enrolled between July 2002 and February 2023. A deep learning model, SCIseg, was trained in a three-phase process involving active learning for the automatic segmentation of intramedullary SCI lesions and the spinal cord. The data consisted of T2-weighted MRI acquired using different scanner manufacturers with heterogeneous image resolutions (isotropic/anisotropic), orientations (axial/sagittal), lesion etiologies (traumatic/ischemic/hemorrhagic) and lesions spread across the cervical, thoracic and lumbar spine. The segmentations from the proposed model were visually and quantitatively compared with other open-source baselines. Wilcoxon signed-rank test was used to compare quantitative MRI biomarkers (lesion volume, lesion length, and maximal axial damage ratio) computed from manual lesion masks and those obtained automatically with SCIseg predictions.

Results MRI data from 191 SCI patients (mean age, 48.1 years ± 17.9 [SD]; 142 males) were used for model training and evaluation. SCIseg achieved the best segmentation performance for both the cord and lesions. There was no statistically significant difference between lesion length and maximal axial damage ratio computed from manually annotated lesions and those obtained using SCIseg.

Conclusion Automatic segmentation of intramedullary lesions commonly seen in SCI replaces the tedious manual annotation process and enables the extraction of relevant lesion morphometrics in large cohorts. The proposed model segments lesions across different etiologies, scanner manufacturers, and heterogeneous image resolutions. SCIseg is open-source and accessible through the Spinal Cord Toolbox.

Summary Automatic segmentation of the spinal cord and T2-weighted lesions in spinal cord injury on MRI scans across different treatment strategies, lesion etiologies, sites, scanner manufacturers, and heterogeneous image resolutions.