基于自适应区域增长与四维曲线的CT图像中血管分割算法分析-计算机科学与技术专业论文.docxVIP

哈尔滨工业大学工学硕士学位论文 哈尔滨工业大学工学硕士学位论文 - - II - Abstract Vascular disease is attracting more and more peoples attention. With the development of modern science and technology, the detection methods of these diseases have become more mature. The emergence of medical imaging technology， which is a milestone in the history of disease detection，provides people with an efficient detection method. In order to be able to further improve the efficiency of this method, many researchers put a lot of efforts in this regard and utilize current computer technology, so that many vessel segmentation algorithms appear. Vessel segmentation in CT images is different from that in general image, and the development is very challenging because of the characteristics of CT image and the complexity of blood vessels. In order to improve the practicality of vessel segmentation algorithms in CT images, this thesis focuses on research on the following two aspects: (1) Finding the deficiencies of the existing algorithms and analyzing the reasons of their problems. (2) Proposing improvements to existing algorithms, solving problems for engineering applications, designing rational data structures to enable finishing improvements, dealing the problem of large amount of data, reducing time and space consuming, achieving better human-computer interaction, reducing the effects of human factors, meeting the requirements of actual clinical applications. The details are： Analysis of existing algorithms, including 3D locally adaptive region growing algorithm, 4D Curves based on active contour and competitive regional growing algorithm. These three methods are all based on statistical thesis. By evaluating the results of vessel segmentation on legs, neck and abdominal CT images, we find out all these algorithms have good anti-noise ability. Besides, we identify the strengths and weaknesses of these algorithms according to their results. The 3D locally adaptive region growing algorithm can de