Skip to main content
 

Multi-Atlas Segmentation with Joint Label Fusion of Compression Fractured Vertebrae on CT

Friday, September 18, 2015 — Poster Session IV

12:00 p.m. – 1:30 p.m.
FAES Terrace
CC
BIOENG-24

Authors

  • Y Wang
  • J Yao
  • HR Roth
  • J Liu
  • JE Burns
  • RM Summers

Abstract

The precise and accurate segmentation of the vertebral column is essential in the diagnosis and treatment of various orthopedic, neurological, and oncological traumas and pathologies. Segmentation is especially challenging in the presence of pathology such as vertebral compression fractures. In this poster, we propose a method to produce segmentations for osteoporotic compression fractured vertebrae by applying a multi-atlas joint label fusion technique for clinical CT images. A total of 170 thoracic and lumbar vertebrae were evaluated using atlases from five patients with varying degrees of spinal degeneration. In an osteoporotic cohort of bundled atlases, registration provided an average Dice coefficient of 92.7±4.5% for osteoporotic vertebrae and 90.9±3.0% for compression fractured vertebrae.

Category: Biomedical Engineering and Biophysics