Segmentation of Pulmonary Vascular Trees from Thoracic 3D CT Images Using Level-Set
The accurate segmentation of vessels is an important prerequisite for creating oncologic surgery planning tools as well as medical visualization applications.In this paper,a novel approach is presented to pulmonary vessel segmentation based on a Canny edge detection segmentation concept,combining the strengths of both threshold and seed point based methods.Our method provides the possibility to adjust the sensitivity/specificity of the segmentation result a posteriori according to application-specific requirements,through adjusting threshold and multiscales of pulmonary vessels so as to belonging to the vascular tree. The method has been evaluated on thoracic CT angiograms scans from clinical pulmonary nodule cases and demonstrates overall promising results.Although we focus on chest CT angiograms data,the method can be generalized to other regions of the body as well as to different imaging modalities.
Qixin Gao HuaiAn Li QunXi Zhu Juan Wang
Center of Compution,Northeast University at QiHuangDao,China The No One Hospital at QinHuangDao
国际会议
秦皇岛
英文
39-43
2010-11-05（万方平台首次上网日期，不代表论文的发表时间）