ASM Driven Snakes in Rheumatoid Arthritis Assessment
In this paper a method is proposed that combines active shape models (ASM) and active contours (snakes) in order to identify fine structured contours with high accuracy and stability. Based on an estimate of the contour position by an active shape model the accuracy of the landmarks and the contour in between is enhanced by applying an iterative active contour algorithm to a set of gray value profiles extracted orthogonally to the interpolation obtained by the ASM. The active shape model is trained with a set of training shapes, whereas the snake detects the contour with fewer constraints. This is of particular importance for the assessment of pathological changes of bones like erosive destructions caused by rheumatoid arthritis.
KeywordsActive Contour Active Shape Model Landmark Position Hand Radiograph Bone Contour
- 3.Timothy F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham. Training models of shape from sets of examples. In Proc. British Machine Vision Conference, pages 266–275, Berlin, 1992. Springer.Google Scholar
- 4.Daniel Cremers, Timo Kohlberger, and Christoph Schnorr. Nonlinear shape statistics in mumford-shah based segmentation. In ECCV (2), pages 93–108, 2002.Google Scholar
- 5.G. Hamarneh and T. Gustavsson. Combining snakes and active shape models for segmenting the human left ventricle in echocardiographic images. IEEE Computers in Cardiology, 27:115–118, 2000.Google Scholar
- 7.Georg Langs, Philipp Peloschek, and Horst Bischof. Locating joints in hand radiographs. In Proceedings of Computer Vision Winter Workshop, 2003.Google Scholar
- 9.T. Nopola, A. Järvi, E. Svedström, and O. Nevalainen. Segmenting bones from wristhand radiographs. Technical Report TUCS Technical Report No. 371, Turku Centre for Computer Science, 2000.Google Scholar