AN AUTOMATIC CONTOUR EXTRACTION ALGORITHM FOR SHORT-AXIS CARDIAC MAGNETIC-RESONANCE IMAGES

In this article an automatic process is presented for the extraction o f the left ventricular contours. The only operator-supplied informatio n is the location of a single point within the left ventricle. The raw data for processing are short-axis cardiac MR images, obtained using various MRI protocols. In this study we considered only protocols for which the blood appears dark. The proposed algorithm performs smoothin g and thresholding of the original MR images, and uses the segmented i mages to form edge images. From those edge images the endocardial curv e is extracted using a modified contour following approach. The algori thm can accommodate moderate noise and small gaps in the contour. A sm ooth curve that approximates the epicardium is then obtained using a m ethod combining radial search and FFT based smoothing. The quality of the obtained contours was visually assessed by three observers. Their evaluation shows that the algorithm is successful when images of reaso nable quality are processed. Further evaluation work is required in or der to fully assess the performance and limitation of the suggested me thod. (C) 1996 American Association of Physicists in Medicine.