Authors:
J. Cheong
1
;
N. Faggian
2
;
G. Langs
3
;
D. Suter
1
and
F. Cicuttini
1
Affiliations:
1
Monash University, Australia
;
2
Clayton School of Information Technology, Monash University, Australia
;
3
Institute for Computer Graphics and Vision, Graz University of Technology; Pattern Recognition and Image Processing Group, Vienna University of Technology, Austria
Keyword(s):
Segmentation, Model-based, Cartilage, Osteoarthritis.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Medical Image Analysis
;
Segmentation and Grouping
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 compares four model-based segmentation methods popular for medical data segmentation, namely Active Shape Models (ASM) (Cootes et al., 1995), Active Appearance Models (AAM) (Cootes et al., 2001), Patch-based Active Appearance Models (PAAM) (Faggian et al., 2006), and Active Feature Models (AFM) (Langs et al., 2006). A comprehensive analysis of how accurately these methods segment human tibial cartilage is presented. The results obtained were benchmarked against the current “gold standard” (cartilage segmented manually by
trained clinicians) and indicate that modeling local texture features around each landmark provides the best results for segmenting human tibial cartilage.
(More)