EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Magnetic Resonance Imaging Preprocessing for Robust Spinal Cord Segmentation in Cervical Myelopathy

Hediyeh Toufani iD, Richard M Dansereau iD, Philippe Phan, Jefferson R Wilson, Eve C Tsai

Journal of Imaging · 17.07.2026 · 12 (7) · 323

DOI: 10.3390/jimaging12070323 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 17.07.2026. Verfasst von Hediyeh Toufani und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 1A2, Canada. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stryker Inc., Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate spinal cord segmentation is important for quantitative analysis of spinal cord magnetic resonance imaging, including measurement of cross-sectional area and diffusion-based microstructural characterization. In pathological conditions like cervical myelopathy, the shape deformation induced by cord compression is extreme, rendering automated segmentation particularly challenging. While deep learning-based methods yield good results in healthy or mildly pathological cases, their reliability suffers when anatomical assumptions fail under compression. In this work, we introduce a pathology-aware, boundary-focused preprocessing framework that directly aims to mitigate failure modes imposed by cord compression. Instead of generic preprocessing, each component aims to enhance intensity homogeneity, suppress noise and improve boundary visibility. At the core of this approach is a multi-representation input derived from a single T2*-weighted scan, whereby complementary intensity-, contrast- and edge-enhanced representations are fed to the U-Net model. The proposed framework is evaluated on spinal cord MRI data from three clinical centers (194 cervical myelopathy cases). The results demonstrate that the proposed preprocessing framework improves segmentation accuracy, robustness, and stability, particularly in anatomically challenging regions affected by compression. These findings highlight the importance of pathology-aware preprocessing for reliable spinal cord segmentation in cervical myelopathy.

Schlagwörter

Stichwörter der Autor:innen

boundary enhancementcervical myelopathydeep learning segmentationmulti-representation inputpathology-aware preprocessingspinal cord MRI

Autor:innen und Institutionen

  • Department of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 1A2, Canada.
  • Neuroscience Program, Ottawa Hospital Research Institute, The Ottawa Hospital, Ottawa, ON K1Y 4E9, Canada.
  • Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada.
  • Division of Orthopedics, Department of Surgery, Faculty of Medicine, University of Ottawa, Ottawa, ON K1H 8M5, Canada.
  • Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON M5S 1A1, Canada.
  • Division of Neurosurgery, Department of Surgery, Faculty of Medicine, University of Ottawa, Ottawa, ON K1H 8M5, Canada.

ORCID-Profile: Hediyeh Toufani, Richard M Dansereau

Förderung

  • Stryker Inc.
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Toufani, H., Dansereau, R. M., Phan, P., Wilson, J. R., & Tsai, E. C. (2026). Magnetic Resonance Imaging Preprocessing for Robust Spinal Cord Segmentation in Cervical Myelopathy. Journal of Imaging, 12(7), 323. https://doi.org/10.3390/jimaging12070323

Vancouver

Toufani H, Dansereau RM, Phan P, Wilson JR, Tsai EC. Magnetic Resonance Imaging Preprocessing for Robust Spinal Cord Segmentation in Cervical Myelopathy. Journal of Imaging. 2026;12(7):323. doi:10.3390/jimaging12070323

BibTeX
@article{Toufani2026,
  author = {Toufani, Hediyeh and Dansereau, Richard M and Phan, Philippe and Wilson, Jefferson R and Tsai, Eve C},
  title = {Magnetic Resonance Imaging Preprocessing for Robust Spinal Cord Segmentation in Cervical Myelopathy},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {7},
  pages = {323},
  doi = {10.3390/jimaging12070323}
}
Kostenlos starten →