K-means clustering based angiographic image analysis to measure coronary stenosis

ABSTRACT: Medical imaging uses techniques or processes which use human body images for clinical or medical science. Medical imaging has a wide range of applications in the field of radiology, angiography and angiogram imaging. Nowadays, angiography and computerized tomography (CT) scans are two common methods that are used by doctors for the detection of coronary artery stenosis (artery blockage) in medical imaging. Most of the detection processes in medical imaging are performed by analyzing digital images generated through angiography and CT scan processes. 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 thesis 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. 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 to extract the vessel of interest. The extracted vessel is analyzed for the calculation of the stenosis in percentage. The second method utilizes segmentation 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. The performance of the proposed methods is compared with the manually measured objective results and doctor’s opinion which can be considered a subjective score. The results indicate that the proposed methods are reliable alternatives to aid the doctors in deciding reliable stenosis scores. K-means based method produces the best average performance on the evaluated vessels with stenosis. A new metric, Maximum Percentage Error Ratio (MPER), in decibels is proposed to indicate the quality of the decisions regarding the generated stenosis (%) using different methods. K-means based method generates the highest performance in terms of MPER. Keywords: Medical image processing, X-ray angiography, angiography imaging, segmentation, thresholding, K-means clustering, stenosis in heart vessels. …………………………………………………………………………………………………………………………………………………………………………………………………………