The Vessel Segmentation System For Cerebralvascular Images Based On Spatial Feature Point Set Of Multi-Angle

Cerebrovascular pathema is one of the main fatal diseases which seriously affects the human health. The DSA (Digital Subtraction Angiography) Image authentically reflects the form and the structure of cerebrovascular, so that currently, the DSA Image is one of the most essential methods to exam the cerebrovascular vascular. The cerebrovascular segmentation is a prerequisite for a quantitative description of the shape of cerebrovascular vessels, extracting the accurate images of vascular tissue is the key point of the clinical diagnosis of vascular.However, because of the motion artifacts caused by the movement of patients and the chiasmic projection of different organs, the equality of the DSA Image is seriously influenced, so that the diagnosis of the doctor is affected, and there would be the missed diagnosis or misdiagnosis. Therefore the cerebrovascular must be segregated from the DSA Image. The segregation of vascular can accurately measure the degree of the disease. The current study of cerebrovascular segmentation mostly use the prior knowledge, and the contextual information is not utilized.The present thesis has a close study on clinical problems of the vascular segregation in DSA Image. Based on the multi-angle set of feature points, the cerebrovascular segmentation is carried forth:Firstly, to eliminate the motion artifacts, a coarse registration for the live image and the mask image is implemented. And then, the SIFT algorithm is utilized to detect geometrical feature points in the serialized subtraction images. After that, a spatial model of rotating coordinate system and a calculative strategy of contextual information are designed to eliminate the error feature points. Finally, based on a dynamic threshold method and region growing, a hybrid algorithm is put forward to segment the blood vessel image. In the system design process, we use some optimization strategies to accelerate the running speed of the algorithm. The method this thesis put forward can provide accurate image of vascular tissue. Therefore, it lays a firmer foundation for the iterative reconstruction, and provides technical supports to the clinical operation.