Flexible Background-Texture Analysis for Coronary Artery Extraction Based on Digital Subtraction Angiography

Image subtraction makes it possible to enhance the visibility of the difference between two images. This technique has been used in digital subtraction angiography (DSA) that is a well established modality for the visualization of coronary arteries. DSA involves the subtraction of a mask image – an image of the heart before injection of contrast medium – from live image. A serious disadvantage of this method, inherent to the subtraction operation, is sensitivity to distortion and variance of background gray-level intensity. Among the causes of these distortions are mean gray-level shift, and motions of heart and lung. In this paper, by choosing the image that has the minimum distortion through similarity analysis of background texture, we suggest the way to solve fundamental problems caused by background distortion, and then how to segment vessel from colony angiography through local gray-level correction of selected image.