Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SCIsegV2: A Universal Tool for Segmentation of Intramedullary Lesions in Spinal Cord Injury

Enamundram Naga Karthik, Jan Valošek, Lynn Farner, Dario Pfyffer, Simon Schading-Sassenhausen, Anna Lebret, Gergely David, Andrew C. Smith, Kenneth A. Weber, Maryam Seif, RHSCIR Network Imaging Group, Patrick Freund, Julien Cohen-Adad

TL;DR

SCIsegV2 delivers a universal, open-source solution for automatic segmentation of intramedullary SCI lesions across diverse etiologies and stages, coupled with an automatic midsagittal tissue-bridge quantification method. Built on an nnUNet backbone, the model explores single- versus two-channel inputs (with a spinal cord mask) and shows improved generalization across sites, surpassing prior etiology-specific approaches in most settings. The automated tissue-bridge measurements closely match manual assessments, suggesting practical usefulness for prognosis, rehabilitation planning, and clinical trial stratification, and the work is integrated into Spinal Cord Toolbox for broad adoption.

Abstract

Spinal cord injury (SCI) is a devastating incidence leading to permanent paralysis and loss of sensory-motor functions potentially resulting in the formation of lesions within the spinal cord. Imaging biomarkers obtained from magnetic resonance imaging (MRI) scans can predict the functional recovery of individuals with SCI and help choose the optimal treatment strategy. Currently, most studies employ manual quantification of these MRI-derived biomarkers, which is a subjective and tedious task. In this work, we propose (i) a universal tool for the automatic segmentation of intramedullary SCI lesions, dubbed \texttt{SCIsegV2}, and (ii) a method to automatically compute the width of the tissue bridges from the segmented lesion. Tissue bridges represent the spared spinal tissue adjacent to the lesion, which is associated with functional recovery in SCI patients. The tool was trained and validated on a heterogeneous dataset from 7 sites comprising patients from different SCI phases (acute, sub-acute, and chronic) and etiologies (traumatic SCI, ischemic SCI, and degenerative cervical myelopathy). Tissue bridges quantified automatically did not significantly differ from those computed manually, suggesting that the proposed automatic tool can be used to derive relevant MRI biomarkers. \texttt{SCIsegV2} and the automatic tissue bridges computation are open-source and available in Spinal Cord Toolbox (v6.4 and above) via the \texttt{sct\_deepseg -task seg\_sc\_lesion\_t2w\_sci} and \texttt{sct\_analyze\_lesion} functions, respectively.

SCIsegV2: A Universal Tool for Segmentation of Intramedullary Lesions in Spinal Cord Injury

TL;DR

SCIsegV2 delivers a universal, open-source solution for automatic segmentation of intramedullary SCI lesions across diverse etiologies and stages, coupled with an automatic midsagittal tissue-bridge quantification method. Built on an nnUNet backbone, the model explores single- versus two-channel inputs (with a spinal cord mask) and shows improved generalization across sites, surpassing prior etiology-specific approaches in most settings. The automated tissue-bridge measurements closely match manual assessments, suggesting practical usefulness for prognosis, rehabilitation planning, and clinical trial stratification, and the work is integrated into Spinal Cord Toolbox for broad adoption.

Abstract

Spinal cord injury (SCI) is a devastating incidence leading to permanent paralysis and loss of sensory-motor functions potentially resulting in the formation of lesions within the spinal cord. Imaging biomarkers obtained from magnetic resonance imaging (MRI) scans can predict the functional recovery of individuals with SCI and help choose the optimal treatment strategy. Currently, most studies employ manual quantification of these MRI-derived biomarkers, which is a subjective and tedious task. In this work, we propose (i) a universal tool for the automatic segmentation of intramedullary SCI lesions, dubbed \texttt{SCIsegV2}, and (ii) a method to automatically compute the width of the tissue bridges from the segmented lesion. Tissue bridges represent the spared spinal tissue adjacent to the lesion, which is associated with functional recovery in SCI patients. The tool was trained and validated on a heterogeneous dataset from 7 sites comprising patients from different SCI phases (acute, sub-acute, and chronic) and etiologies (traumatic SCI, ischemic SCI, and degenerative cervical myelopathy). Tissue bridges quantified automatically did not significantly differ from those computed manually, suggesting that the proposed automatic tool can be used to derive relevant MRI biomarkers. \texttt{SCIsegV2} and the automatic tissue bridges computation are open-source and available in Spinal Cord Toolbox (v6.4 and above) via the \texttt{sct\_deepseg -task seg\_sc\_lesion\_t2w\_sci} and \texttt{sct\_analyze\_lesion} functions, respectively.
Paper Structure (18 sections, 3 figures, 2 tables)

This paper contains 18 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Dataset
  4. SCIsegV2
  5. Automatic Quantification of Tissue Bridges
  6. Experiments
  7. Inputs
  8. Data augmentation
  9. SCI Etiology-specific models
  10. SCIseg
  11. Tissue Bridges
  12. Evaluation Metrics
  13. Results
  14. Discussion
  15. Limitations and Future Work
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Representative axial and sagittal T2w MRI scans of the lesion in various SCI etiologies/types.
  • Figure 2: Illustration of tissue bridges. A) Volumetric T2w image of a spinal cord injury (SCI) with chronic intramedullary lesion. B) Midsagittal slice used to compute the tissue bridges. C) Ventral and dorsal tissue bridges are defined as the width of spared tissue at the minimum distance from the intramedullary lesion edge to the boundary between the SC and cerebrospinal fluid.
  • Figure 3: Comparison of Dice scores for different SCI models. Each bar plot shows the test Dice scores averaged across 5 folds (the error bar represents the standard deviation).