Identification of Myocardial Infarction Tissue Based on Texture Analysis from Echocardiography Images

Texture is an important characteristic that can be used for identification and detection for surface defect or abnormalities. This research has an algorithm for identifying heart with suspected myocardial infarction problem based on texture analysis applied on echocardiography images. Texture tissue sample images taken from echocardiography sub-image (ROI). There are two tissue classes: Type 1 corresponds to normal myocardial tissue, whereas Type 2 corresponds to infarcted myocardium with small dimension. Therefore, in order to investigate possible in differences tissue between patient with infarction tissue or not, we proposed a Wavelet Extension Transform and Gray Level Co-occurrence matrix. Wavelet Extension Transform is used to form an image approximation with higher resolution. The gray level co-occurrence matrices are computed for each sub-band. The feature vector of testing image and other feature vector as normal image classified by Mahalanobis distance to decide whether the test image is infarction or not. The method is tested with real data from echocardiography images of human heart. For each patient to be analyzed tissue samples are taken from not-affected area and tissue samples are taken from image segments corresponding to the infarcted area of myocardium. The result of this experiment can detect difference image from echocardiography as normal myocardium and infarcted myocardial tissue.