Segmentation of the left ventricle is important in assessment of cardiac functional parameters. Currently, manual segmentation is the gold standard for acquiring these parameters and can be time-consuming. Therefore, accuracy and automation are two important criteria in improving cardiac image segmentation methods. In this paper, we present a comprehensive approach that utilizes various features of cine MR images and combines multiple image processing methods including thresholding, edge detection, mathematical morphology, deformable model as well as image filtering. The segmentation is performed automatically with minimized interaction to optimize segmentation results. This approach provides cardiac radiologists a practical method for accurate segmentation of the left ventricle.
An Image-Based Comprehensive Approach for Automatic Segmentation of Left Ventricle from Cardiac Short Axis Cine MR Images
