CVD (cardiovascular disease) is one of the biggest threats to human beings nowadays. An early and quantitative diagnosis of CVD is important in extending lifespan and improving people's life quality. Coronary artery stenosis can prevent CVD. To diagnose the degree of stenosis, the inner diameter of coronary artery needs to be measured. To achieve such measurement, the coronary artery is segmented by using a method that is based on morphology and the continuity between computed tomography image slices. A centerline extraction method based on mechanical simulation is proposed. This centerline extraction method can figure out a basic framework of the coronary artery by simulating pixel dots of the artery image into mass points. Such mass points have tensile forces, with which the outer pixel dots can be drawn to the center. Subsequently, the centerline of the coronary artery can be outlined by using the local line-fitting method. Finally, the nearest point method is adopted to measure the inner diameter. Experimental results showed that the methods proposed in this paper can precisely extract the centerline of the coronary artery and can accurately measure its inner diameter, thereby providing a basis for quantitative diagnosis of coronary artery stenosis.

Tetralogy of Fallot (TOF) is the most common complex congenital heart disease (CHD) of the cyanotic type. Studies on ventricular functions have received an increasing amount of attention as the development of diagnosis and treatment technology for CHD continues to advance. Reasonable options for imaging examination and accurate assessment of preoperative and postoperative left ventricular functions of TOF patients are important in improving the cure rate of TOF radical operation, therapeutic evaluation, and judgment prognosis. Therefore, with the aid of dual-source computed tomography (DSCT), cardiac images with high temporal resolution and high definition, we measured the left ventricular time-volume curve using image data and calculating the left ventricular function parameters to conduct the preliminary evaluation on TOF patients. To comprehensively evaluate the cardiac function, the segmental ventricular wall function parameters were measured, and the measurement results were mapped to a bull's eye diagram to realize the standardization of segmental ventricular wall function evaluation. Finally, we introduced a new clustering method based on auto-regression model parameters and combined this method with Euclidean distance measurements to establish an intelligent diagnosis of TOF. The results of this experiment show that the TOF evaluation and the intelligent diagnostic methods proposed in this article are feasible.

No abstract

No abstract