Active appearance models for segmentation of cardiac MRI data

We describe the method for segmentation of Left Ventricle (LV) in short axis cardiac MR Images in order to visibly identify the LV, and its outer wall. Segmentation of medical data is extremely time-consuming if done manually. Model based techniques represent one very promising approach. A model representing the object of interest is matched with unknown data. During the matching process the model´s shape and additional properties are varied in order to iteratively improve the match. As soon as the model fits sufficiently well to the data, the properties of the model can be mapped to the data and so the segmentation is derived. The objective of this study is to show clearly the LV in particular so that any deviation from the standard dimensions in terms of shape, size or texture, can be unmistakably identified. The training set is prepared from the data obtained from a reputed hospitals and medical colleges in Pune, India. For segmentation of the Cardiac MRI, Principal Component Analysis (PCA) is used in the Active Appearance Model (AAM) building process. The AAM method shows high promise for successful application to MR image analysis in a clinical setting.