Segmentation of anterior cruciate ligament in knee MR images using graph cuts with patient-specific shape constraints and label refinement
Lists
Only you see this
Abstract
Highlights•We propose an anterior cruciate ligament segmentation method in knee MRI.•Patient-specific shape constraints for graph cuts are proposed to avoid leakage.•Label refinement with superpixels is proposed to recover inhomogeneous region.•Superpixel refinement significantly improves the accuracy of tibia-attached ACL.•Experiments show that the proposed method improves the Boykov model by 15% in DSC.
BibTeX
@article{lee2014segmentation,
author = {Hansang Lee and Helen Hong and Junmo Kim},
title = {{Segmentation of anterior cruciate ligament in knee MR images using graph cuts with patient-specific shape constraints and label refinement}},
journal = {Computers in Biology and Medicine},
year = {2014},
doi = {10.1016/j.compbiomed.2014.09.004},
}Loading related content...