Abstract—Cardiovascular diseases are the major cause of death in the developed world. The high death rate caused by coronary artery diseases increases the need for early detection. Magnetic resonance imaging has turned out to be very promising for this purpose. Currently Gadolinium (contrast agent) is injected intravenously to visualize the accurate myocardial abnormalities. The extent of non-viable tissue in the left ventricle (LV) of the heart is a direct indicator of patient survival rate. The main objective of this paper is to make a review and propose a methodology to segment the non-viable tissue before injecting gadolinium (Contrast agent) in Cardiac MRI by computer vision techniques. The proposed work consists of four stages for an automatic segmentation approach: Data Acquisition, Preprocessing & motion artifact suppression, Segmentation of the myocardium by healthy and dead area from LV and RV and Classification. This paper investigates and compares the patterns of contrast enhanced and non-contrast enhanced cardiac MRI which causes myocardial abnormalities
—Myocardium, left and right ventricles, contrast agent, region of interest, segmentation and classification.
Valliappan Raman and Patrick Then are with the Swinburne University of Technology Sarawak (e-mail: vraman@ Swinburne.edu.my, firstname.lastname@example.org).
Annuar Rapaee is with the Tropicana Medical Centre (e-mail: email@example.com).
Cite: Valliappan Raman, Patrick Then, and Annuar Rapaee, "A Brief Study on Automated Non Contrast Cardiac MRI Segmentation by Machine Vision Techniques," International Journal of Engineering and Technology
vol. 4, no. 5, pp. 504-507, 2012.