Lumbar disc localization and labeling with a probabilistic model on both pixel and object features

Med Image Comput Comput Assist Interv. 2008;11(Pt 1):202-10. doi: 10.1007/978-3-540-85988-8_25.


Repeatable, quantitative assessment of intervertebral disc pathology requires accurate localization and labeling of the lumbar region discs. To that end, we propose a two-level probabilistic model for such disc localization and labeling. Our model integrates both pixel-level information, such as appearance, and object-level information, such as relative location. Utilizing both levels of information adds robustness to the ambiguous disc intensity signature and high structure variation. Yet, we are able to do efficient (and convergent) localization and labeling with generalized expectation-maximization. We present accurate results on 20 normal cases (96%) and a promising extension to a pathology case.

Publication types

  • Evaluation Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Artificial Intelligence*
  • Computer Simulation
  • Data Interpretation, Statistical
  • Image Enhancement / methods*
  • Image Interpretation, Computer-Assisted / methods*
  • Intervertebral Disc / pathology*
  • Intervertebral Disc Displacement / pathology*
  • Lumbar Vertebrae / pathology*
  • Models, Biological
  • Models, Statistical
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Sensitivity and Specificity