Segmentation of the left ventricle in cardiac MRI based on convolutional neural network and level set function

Abstract

Left ventricular segmentation in cardiac magnetic resonance images is considered as the most critical method to evaluate the cardiac function. In this paper, a hybrid method has been proposed to segment the left ventricle(endocardium). In this study, first, a new method has been proposed based on deep Convolutional Neural Network (CNN) to localize the LV in cardiac MRI. Then, the segmentation is completed through the localized LV by level set function. After segmentation, for each patient end-systole volume, end-diastole volume and ejection fraction are calculated to evaluate the left ventricle function. The evaluation of segmentation is done by specificity, sensitivity, accuracy, Average Perpendicular Distance (APD), and Dice indexes. According to obtain results for the proposed method, the mean specificity, sensitivity, and accuracy were 99.35, 94.11, and 94. Based on the results, the presented method is very reliable for the segmentation of the left ventricles and evaluation of the cardiac function.