Automatic segmentation of human tibial cartilage

Authors:
J. Cheong;N. Faggian;D. Suter;F. Cicuttini
Affiliations:
Dept. of Electrical and Computer Systems Engineering, Monash University, Australia;Clayton School of Information Technology, Monash University, Australia;Dept. of Electrical and Computer Systems Engineering, Monash University, Australia;Dept. of Epidemiology and Preventive Medicine, Monash University, Australia
Venue:
SPPR'07 Proceedings of the Fourth conference on IASTED International Conference: Signal Processing, Pattern Recognition, and Applications
Year:
2007

Citing 4
Cited 0

Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Quantification of Articular Cartilage from MR Images Using Active Shape Models

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume II - Volume II
A Non-Linear Gray-Level Appearance Model Improves Active Shape Model Segmentation

MMBIA '01 Proceedings of the IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA'01)
Representation and Detection of Deformable Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Osteoarthritis is a chronic and crippling disease affecting an increasing number of people each year. With no known cure, it is expected to reach epidemic proportions in the near future. Accurate segmentation of knee cartilage from magnetic resonance imaging (MRI) scans facilitates the measurement of cartilage volume present in a patient's knee, thus enabling medical clinicians to detect the onset of osteoarthritis and also crucially, to study its effects. This paper presents a fully automated method for segmenting and measuring human tibial cartilage volume from MRI scans. The method uses a global search technique developed by Felzenszwalb [1], involving triangulated polygons as deformable templates to initialise a patch-based active appearance model (PAAM) [2]. The cartilage volume obtained from our automatic method is benchmarked against the current "gold standard" (cartilage volume measured using manual segmentation) as well as other semi-automatic methods. The results obtained are comparable to human manual segmentation.