Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation

Xiaoran Zhang, Yan Li, Yicun Liu, Shu Xia Tang, Xiaoguang Liu, Kumaradevan Punithakumar, Dawei Shi

Research output: Contribution to journalArticlepeer-review

Abstract

Accurate positioning of the responsible segment for patients with cervical spondylotic myelopathy (CSM) is clinically important not only to the surgery but also to reduce the incidence of surgical trauma and complications. Spinal cord segmentation is a crucial step in the positioning procedure. This study proposed a fully automated approach for spinal cord segmentation from 2D axial-view MRI slices of patients with CSM. The proposed method was trained and tested using clinical data from 20 CSM patients (359 images) acquired by the Peking University Third Hospital, with ground truth labeled by professional radiologists. The accuracy of the proposed method was evaluated using quantitative measures, the reliability metric as well as visual assessment. The proposed method yielded a Dice coefficient of 87.0%, Hausdorff distance of 9.7 mm, root-mean-square error of 5.9 mm. Higher conformance with ground truth was observed for the proposed method in comparison to the state-of-the-art algorithms. The results are also statistically significant with p-values calculated between state-of-the-art methods and the proposed methods.

Original languageEnglish
Article number104345
JournalComputers in Biology and Medicine
Volume132
DOIs
StatePublished - May 2021

Keywords

  • 2D magnet resonance imaging
  • Cervical spondylotic myelopathy
  • Convolutional neural network
  • Level set evolution
  • Spinal cord segmentation

Fingerprint

Dive into the research topics of 'Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation'. Together they form a unique fingerprint.

Cite this