Improving Segmentation of the Left Ventricle Using a Two-Component Statistical Model
Quality of segmentations obtained by 3D Active Appearance Models (AAMs) crucially depends on underlying training data. MRI heart data, however, often come noisy, incomplete, with respiratory-induced motion, and do not fulfill necessary requirements for building an AAM. Moreover, AAMs are known to fail when attempting to model local variations. Inspired by the recent work on split models  we propose an alternative to the methods based on pure 3D AAM segmentation. We interconnect a set of 2D AAMs by a 3D shape model. We show that our approach is able to cope with imperfect data and improves segmentations by 11% on average compared to 3D AAMs.
KeywordsPapillary Muscle Shape Model Independent Component Analysis Active Appearance Model Statistical Shape Model
- 1.Langs, G., Peloschek, P., Donner, R., Bischof, H.: A clique of active appearance models by minimum description length. In: British Machine Vision Conference (BMVC), vol. 2, pp. 859–868 (2005)Google Scholar
- 3.Stegmann, M.B., Pedersen, D.: Bi-temporal 3D active appearance models with applications to unsupervised ejection fraction estimation. In: International Symposium on Medical Imaging, vol. 5747 (2005)Google Scholar
- 7.Beichel, R., Bischof, H., Leberl, F., Sonka, M.: Robust active appearance models and their application to medical image analysis. IEEE Transactions on Medical Imaging 24(9) (2005)Google Scholar
- 9.Üzümcü, M., Frangi, A., Reiber, J., Lelieveldt, B.: The use of independent component analysis in statistical shape models. In: SPIE Medical Imaging, vol. 5032, pp. 375–383 (2003)Google Scholar
- 10.Suinesiaputra, A., Frangi, A.F., Üzümcü, M., Reiber, J.H.C., Lelieveldt, B.P.F.: Extraction of myocardial contractility patterns from short-axes MR images using independent component analysis. In: ECCV Workshops CVAMIA and MMBIA, pp. 75–86 (2004)Google Scholar