Texture analysis for automatic segmentation of intervertebral disks of scoliotic spines from MR images

  • Authors:

  • Claudia Chevrefils;Farida Cheriet;Carl-Éric Aubin;Guy Grimard

  • Affiliations:

  • Institute of Biomedical Engineering, Ecole Polytechnique de Montreal and Sainte-Justine University Hospital Center, Montreal, QC, Canada;Department of Computer Engineering and Software, Biomedical Engineering Institute, Ecole Polytechnique de Montreal and Sainte-Justine University Hospital Center, Montreal, QC, Canada;Department of Mechanical Engineering and Biomedical Engineering Institute, Ecole Polytechnique de Montreal and Sainte-Justine University Hospital Center, Montreal, QC, Canada;Department of Orthopaedics, Sainte-Justine Hospital, Montreal, QC, Canada

  • Venue:
  • IEEE Transactions on Information Technology in Biomedicine - Special section on biomedical informatics
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a unified framework for automatic segmentation of intervertebral disks of scoliotic spines from different types of magnetic resonance (MR) image sequences. The method exploits a combination of statistical and spectral texture features to discriminate closed regions representing intervertebral disks from background in MR images of the spine. Specific texture features are evaluated for three types of MR sequences acquired in the sagittal plane: 2-D spin echo, 3-D multiecho data image combination, and 3-D fast imaging with steady state precession. A total of 22 texture features (18 statistical and 4 spectral) are extracted from every closed region obtained from an automatic segmentation procedure based on the watershed approach. The feature selection step based on principal component analysis and clustering process permit to decide among all the extracted features which ones resulted in the highest rate of good classification. The proposed method is validated using a supervised k-nearest-neighbor classifier on 505 MR images coming from three different scoliotic patients and three differentMRacquisition protocols. Results suggest that the selected texture features and classification can contribute to solve the problem of oversegmentation inherent to existing automatic segmentation methods by successfully discriminating intervertebral disks from the background on MRI of scoliotic spines.