Computer-aided diagnosis via model-based shape analysis: cardiac MR and echo

Abstract

We have previously reported on 2D and 3D Active Appearance Models (AAMs) for automated segmentation of cardiac MR and transthoracic ultrasound. Segmentation of object borders might not be the only benefit of AAMs. An AAM represents objects as a linear combination of shape and texture variations applied to a mean object via Principal Component Analysis (PCA) to form a compact model. Our current work demonstrates that separate analysis of the AAM coefficients may prove beneficial for the classification of disease abnormalities.