Segmentation Of The Coronary Artery Region In The Cardiac Mri Images Using Fuzzy C-Means Model

摘要

Image segmentation plays an important role in computer vision and image analysis. The segmentation results can be used to identify regions of interest and objects in the scene. That too, in the field of medical imagery, cardiac is the most complex organ in the human body and is susceptible to various pathologies. Cardiac magnetic resonance (CMR) is a widely accepted imaging modality for detecting a disease of cardiac structures images which is prone to noise, varying anatomical structures, on-homogeneity, volumetric data and sometimes deviation. So, the accurate segmentation of cardiac structures and substructures is a very tedious task. The fuzzy c-means (FCM) algorithm is one of the most used techniques for image segmentation. The accuracy of FCM is due to the employment of fuzziness for the clustering of each image pixel. In this project, we present a new approach of Magnetic Resonance Imaging (MRI) for cardiac images known as tissue segmentation, which consists of three main phases: (1) Noise removal using median filter, (2) Clustering based on the FCM, and (3) Segmentation using the fuzzy level set method. The results depict that the segmentation accuracy is 85% when tested on 50 samples of MRI cardiac image dataset.