Automatic segmentation of the articular cartilage in knee MRI using a hierarchical multi-class classification scheme

Authors:
Jenny Folkesson;Erik Dam;Ole Fogh Olsen;Paola Pettersen;Claus Christiansen
Affiliations:
Image Analysis Group, IT University of Copenhagen, Denmark;Image Analysis Group, IT University of Copenhagen, Denmark;Image Analysis Group, IT University of Copenhagen, Denmark;Center for Clinical and Basic Research, Ballerup, Denmark;Center for Clinical and Basic Research, Ballerup, Denmark
Venue:
MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2005

Citing 1
Cited 5

An optimal algorithm for approximate nearest neighbor searching

SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms

An automatic diagnosis method for the knee meniscus tears in MR images

Expert Systems with Applications: An International Journal
Inter and intra-modal deformable registration: continuous deformations meet efficient optimal linear programming

IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Primal/dual linear programming and statistical atlases for cartilage segmentation

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Combining binary classifiers for automatic cartilage segmentation in knee MRI

CVBIA'05 Proceedings of the First international conference on Computer Vision for Biomedical Image Applications
Segmentation of the cartilage in the rib cage in 3d MRI

MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Osteoarthritis is characterized by the degeneration of the articular cartilage in joints. We have developed a fully automatic method for segmenting the articular cartilage in knee MR scans based on supervised learning. A binary approximate kNN classifier first roughly separates cartilage from background voxels, then a three-class classifier assigns one of three classes to each voxel that is classified as cartilage by the binary classifier. The resulting sensitivity and specificity are 90.0% and 99.8% respectively for the medial cartilage compartments. We show that an accurate automatic cartilage segmentation is achievable using a low-field MR scanner.