Coronary Artery Automatic Positioning And Display Research Based On Cardiac CT Images

With the economic development,people's eating habits have also changed a lot compared with the past,high-fat,high-calorie food intake increased significantly,The resulting incidence of cardiovascular disease increased year by year.In recent years,cardiovascular disease has became a major threat to the health and safety of the elderly in our country,morbidity and mortality have rank first in all kinds of diseases.The number of people with cardiovascular diseases in our country has exceeded 150 million,every year,the number of deaths from related diseases accounts for about half of the deaths due to various diseases,nearly 4 million,and this figure shows a clear upward trend.The best way to prevent cardiovascular disease is early diagnosis,early prevention and early treatment,but the traditional method of image diagnosis is limited by many reasons and conditions,which lead doctors to grasp the limitations of the image information,and even determine incorrectly.If the early detection of the patient's lesion and identify the nature of the disease,can be very well to reduce the disease further damage to the patient.On the other hand,computer technology and image processing technologies have also made great strides in recent years,computer-aided diagnosis systems can be used to process and analyze patient images,at the same time,the pathological data of the patients are matched and compared,and the diagnosis information is provided to the doctor for reference.This paper mainly studies the key issues involved in the automatic coronary artery positioning and display technology based on cardiac CT images,as follows:(1)Coronary centerlines extraction in cardiac CT images.Extraction of the centerline of the coronary artery converts the three-dimensional image into a two-dimensional image sequence for processing and subsequent 3D reconstruction,so the accuracy of this step is crucial throughout the algorithm.At the part of coronary centerlines extraction,this article will list several commonly used centerlines extraction algorithms.Through theoretical research and experimental comparison,draw the center line extraction algorithm suitable for this application scenario,the validity of model-based automatic coronary artery centerlines extraction method for the shortest path of coronary artery centerlines extraction was verified.(2)Accurate segmentation of the coronary area from cardiac CT images.Because of the poor quality of cardiac CT images relative to other images and the large amount of noise,this makes the traditional image segmentation algorithm in dealing with this type of image is difficult to achieve the desired effect.On this issue,this article mainly experiment in the acquisition of cardiac CT images.Through experimental comparison,the effect of using the Levelset algorithm to segment the cardiac CT image has been verified.In order to further improve the accuracy of segmentation,this paper propose an adaptive fusion using two kinds of image enhancement information.The Levelset algorithm is then used to segment the target area by evolving the fused image area.Experiments show that this method can ensure the accuracy of coronary artery segmentation in cardiac CT images.(3)Displaying the segmented coronary area clearly.Because of the high resolution and high dynamic range of a standard DICOM format medical image file,high quality display of images becomes a challenge.In order to facilitate the doctor's observation of the lesions as much as possible,this article through the integration of ITK,VTK and Qt,to achieve the hierarchical display of coronary heart area and given the auxiliary diagnostic information.The practical application shows that this method can greatly reduce the doctor's workload and diagnosis difficulty.