When doctors diagnose coronary artery by CTA data, they need to look at each section layer by layer, which consumes a lot of diagnostic time. Introducing artificial intelligence technology, using CTA image computer-aided technology to extract coronary artery automatically or semi-automatically, and assisting analysis of coronary artery, can improve the efficiency of doctors, quickly make diagnosis of patients. A priori model of coronary artery centerline based on image registration is studied. A single priori model is formed by fusing multiple cardiac CTA data, which increases the generalization ability of the model and provides more accurate priori position information of main branches for unknown CTA data. According to the composition of the model, it will be divided into two parts: the cardiac cavity model and the centerline model. The implementation of the model establishment, DMP centerline extraction and coronary analysis is introduced. The methods of central line tracing were discussed, and the clinical application of central line extraction was divided into 1) radius extraction 2) calcification and stenosis analysis. Coronary CTA (Computed Tomography Angiography) technology can not only obtain the image of coronary artery, but also image the wall of coronary artery, assisting doctors in the analysis of vascular calcification and stenosis. Coronary CTA technology adds a diagnostic approach to cardiovascular disease and makes it more acceptable to patients because of the use of non-interventional techniques.

Xinlei Chen, Wei Zhong and Xiaogang Ren. Research on automatic coronary artery extraction algorithm based on CTA image and model guidance. Academic Journal of Computing & Information Science (2018) Vol. 1: 1-8.

[1] Bruijne M D, Ginneken B V, Viergever M A, et al. Interactive segmentation of abdominal aortic aneurysms in CTA images[J]. Medical Image Analysis, 2004, 8(2):127-138.
[2] Bruijne M D, Ginneken B V, Niessen W J, et al. Model-based segmentation of abdominal aortic aneurysms in CTA images[J]. Proceedings of SPIE - The International Society for Optical Engineering, 2002, 4684(2):127.
[3] Lã³Pez-Linares K, Aranjuelo N, Kabongo L, et al. Fully automatic detection and segmentation of abdominal aortic thrombus in post-operative CTA images using Deep Convolutional Neural Networks[J]. Medical Image Analysis, 2018:202-214.
[4] Bruijne M D, Ginneken B V, Niessen W J, et al. Active-shape-model-based segmentation of abdominal aortic aneurysms in CTA images[C]// Medical Imaging 2002: Image Processing. International Society for Optics and Photonics, 2002:127–138.
[5] Li Z, Liang Y, Yang W, et al. Study on improvement of coronary CTA image quality by ECG editing and(or) multi temporal reconstruction[J]. Chinese Community Doctors, 2018.
[6] Panicker R O, Soman B, Saini G, et al. A Review of Automatic Methods Based on Image Processing Techniques for Tuberculosis Detection from Microscopic Sputum Smear Images.[J]. Journal of Medical Systems, 2016, 40(1):1-13.
[7] Georgis G, Lentaris G, Reisis D. Acceleration techniques and evaluation on multi-core CPU, GPU and FPGA for image processing and super-resolution[J]. Journal of Real-Time Image Processing, 2016:1-28.
[8] Azar N A, Babakhani A, Broumandnia A, et al. A novel method for detecting and counting overlapping tracks in SSNTD by image processing techniques[J]. Radiation Measurements, 2016, 91:36-43.
[9] Qu Guangxiong. Clinical application of CT angiography in the diagnosis of coronary artery disease [J].Journal of Mathematics, Physics and Medicine, 2016, 29 (7): 1098-1099.
[10] Wang Rui, Wang Xiaoying. A brief introduction to CAD-RADS~ (TM) coronary artery disease reporting and data system [J].Chinese Medical Imaging Technology, 2016 (12): 1827-1832.
[11] Ye Yiyong.Evaluation of CT angiography in the diagnosis of coronary artery disease[J].Chinese Medical Science, 2016 (2): 150-152.