基于测地线活动轮廓模型的图像联合分割算法

Image joint segmentation method based on geodesic active contour model

为了辅助医生对肿瘤治疗方案和靶区形状的设计,我们研究了PET/CT图像联合自动分割,将计算机自动分割的结果作为一个较客观的依据。传统的测地线活动轮廓模型(GAC)具有边缘演化迅速,对弱边界也能准确分割的优点,但是该算法只能利用一种模态的图像信息进行分割。本研究算法在传统的测地线活动轮廓模型基础上进行改进,重新设计其边缘函数,综合利用了CT信息与PET信息,使算法利用两种模态的医学图像信息进行联合分割。由于边缘函数中结合了两种信息,所以算法的演化收敛速度有一定的提升,分割出的边缘也更加合理,较单一PET图像分割算法具有更准确的边界。

In order to assist doctors to design better tumor treatment plan and target area,to study the automatic segmentation of PET/CT images,regard it as an objective basis.The traditional Geodesic Active Contour model(GAC)has the advantage of rapid edge evolution and accurate segmentation for the weak boundary.However,the algorithm only uses one kind of image modal to segment.Our algorithm was improved based on traditional Geodesic Active Contour model.Its edge function was redesigned based on both gradient information of CT image and PET image.The algorithm did the combined segmentation using two modes of medical image information.Because two kinds of information are both combined in the edge function,the convergence speed of the algorithm has been improved,and the edge of the segmentation area is also more reasonable and the boundary is more accurate compared with segmentation method based on the single PET image.