An Unsupervised Image Segmentation Workflow for Extraction of Left Coronary Artery from X-Ray Coronary Angiography

Abstract

Coronary heart disease (CHD) is a serious cardiovascular illness that is among the top causes of death worldwide. Using X-ray coronary angiography, it is possible to detect and monitor CHD by visualizing coronary vessels. One of the most important steps in analyzing angiographic images is image segmentation, where the coronary arteries are separated from the background. In this work, we propose an unsupervised image segmentation workflow that uses different filters in order to minimize the limitations of X-ray coronary angiography and achieve satisfactory segmentation of the left coronary artery. During the preprocessing step, the X-ray angiographic image of coronary artery is processed with CLAHE, the Wiener filter and gamma correction in order to overcome the shortcomings of the X-ray imaging data. These preprocessing steps greatly reduce the background noise and improve the separation of the artery from the rest of the image. The preprocessed image is then segmented using Otsu’s thresholding method, which results in a binarized image. This image has left coronary artery successfully segmented, but unfortunately a lot of non-vessel segments have been wrongly labeled as well. In the postprocessing step, connected components are obtained, and then using information about their size the largest connected component represents a segmented left coronary artery, while the rest is marked as background.