Coronary Stenosis Measurements Using K-Means Clustering

Medical imaging is one of common area that nowadays researchers uses human body images for clinical or medical science [1] [2]. Currently most of the diagnoses are performed by doctors after manual inspection of real time frames of the video generated by the respective medical imaging systems. In this paper, we propose to use digital image processing techniques in detection and categorization of the clogs in the arteries (stenosis/blockage) by using the frames generated from the X-ray angiography [3][4]. Utilized image pre-processing methods includes selecting a line of Interest (LOI) on blocked vessel and further selection of the region of interest (ROI) on that area, then automatically cropping the region of interest followed by Gaussian filtering for smoothing. In the post processing, three alternative methods are proposed to measure the stenosis in the vessel. The first method applies thresholding (Local) to extract the vessel of interest. The extracted vessel is analyzed for the calculation of the stenosis in percentage [5]. The second method utilizes segmentation (both edge-based and region-based) of the vessel tissue over the extracted pixels of ROI. The final method uses K-means clustering to differentiate between the vessel regions and non-vessel regions. Among the proposed methods K-means clustering based method outperforms the thresholding and segmentation methods.