Improved Segmentation of Cardiac MRI Using Efficient Pre-Processing Techniques

Abstract

Cardiac magnetic resonance imaging is a popular non-invasive technique used for assessing the cardiac performance. Automating the segmentation helps in increased diagnosis accuracy in considerably less time and effort. In this paper, a novel approach has been proposed to improve the automated segmentation process by increasing the accuracy of segmentation and laying focus on efficient pre-processing of the cardiac magnetic resonance (MR) image. The pre-processing module in the proposed method includes noise estimation and efficient denoising of images using discrete total variation-based non-local means method. Segmentation accuracy is evaluated using measures such as average perpendicular distance and dice similarity coefficient. The performance of all the segmentation techniques is improved. Further segmentation comparison has also been performed using other state-of-the art noise removal techniques for pre-processing, and it was observed that the proposed pre-processing technique outperformed other noise removal techniques in improving the segmentation accuracy.