Design And Implementation Of Centerline Extraction Software For Coronary Artery Imaging

With the rapid development of the economy and society,the aging of the population and the acceleration of urbanization,the number of cardiovascular patients in China has increasedPwhich has become a major public health problem.Cardiovascular disease is preventable and treatable.The key lies in "early detection,early prevention,early treatment".Medical imaging is one of the key ways to screen and diagnose such diseases.With the rapid development of science and technology,the proportion of medical imaging in clinical applications has also increased.Coronary artery angiography(CTCA)can clearly show the structure of the coronary artery.Combined with image reconstruction technology,the coronary artery image can be stereoscopically restored by computer.It can perform quantitative analysis,diagnosis,localization of tissue lesions,study of tissue structure,and planning treatment.As well as guiding surgery.The main research object of this study is coronary CT angiography(CTCA).Firstly,the coronary artery vascular segmentation and vascular centerline extraction algorithm are investigated and tested,and then the coronary artery vascular centerline extraction software is developed.The specific work content and results are as follows:(1)For the needs of cardiovascular imaging development medical imaging platform,the architecture design of the coronary artery centerline extraction software proposed in this thesis is designed.The platform is designed as four layers:data layer,algorithm layer,interface layer,and application layer.The data layer is the first layer of the architecture,providing data to the upper layers.The algorithm layer is built using MITK,open source algorithms,and self-developed algorithms.The interface layer is located in the third layer,and the algorithm provided by the second layer is used for encapsulation,combination,and the like for the upper layer to call.The application layer provides interactive functions and results presentation through a graphical interactive interface.(2)The core module of coronary artery segmentation was developed based on the theory of edge-based variable model,and a set of pipeline segmentation was realized.(3)A coronary artery centerline extraction module was developed based on the source distance field and the boundary distance field.(4)Expand the developed algorithm into the Medical Image Processing and Analysis Development Kit(MITK)algorithm library for development application software.In this thesis,coronary artery vascular segmentation,coronary artery centerline extraction and surface mapping principles were studied,and an algorithm suitable for extracting coronary artery centerline was selected.At the same time,this thesis makes a detailed study on the MITK algorithm platform,and uses the MITK algorithm platform to develop the application software for coronary artery centerline extraction.The work of this thesis is a successful attempt on the practicality of the MITK algorithm platform,and it can further expand its functions and explore different algorithms in the future.