Automatic atlas-based three-label cartilage segmentation from MR knee images

Published

Journal Article

This paper proposes a method to build a bone-cartilage atlas of the knee and to use it to automatically segment femoral and tibial cartilage from T1 weighted magnetic resonance (MR) images. Anisotropic spatial regularization is incorporated into a three-label segmentation framework to improve segmentation results for the thin cartilage layers. We jointly use the atlas information and the output of a probabilistic k nearest neighbor classifier within the segmentation method. The resulting cartilage segmentation method is fully automatic. Validation results on 18 knee MR images against manual expert segmentations from a dataset acquired for osteoarthritis research show good performance for the segmentation of femoral and tibial cartilage (mean Dice similarity coefficient of 78.2% and 82.6% respectively). © 2012 IEEE.

Full Text

Duke Authors

Cited Authors

  • Shan, L; Charles, C; Niethammer, M

Published Date

  • April 24, 2012

Published In

  • Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis

Start / End Page

  • 241 - 246

Digital Object Identifier (DOI)

  • 10.1109/MMBIA.2012.6164757

Citation Source

  • Scopus