The AI lesion detection and labeling platform applied to cardiac angiography is to help the diagnosis of coronary artery obstruction. Through cardiac catheterization or computed tomography coronary angiography, it is possible to clearly see whether the blood vessels are blocked. However, due to the complex distribution and network of blood vessels in cardiovascular imaging, and the high variability of individual’s structure and the different locations of obstruction, professional physicians are time-consuming and labor-intensive to identify and label, and also the number of cases is high and the load is heavy. In order to speed up the diagnosis of symptoms by cardiologists, the AI lesion detection and labeling system for cardiac angiography has been developed. With the development of algorithm modules and the assistance of AI functions, the number, location and severity of lesions can be quickly identified. It can also reduce errors caused by human beings, and reduce the workload of medical professionals. The detection results can be further provided for cardiologists to plan the follow-up urgical treatment is necessary or not and to establish the key indicators of preoperative evaluation.