关键词: 医学图像分割, 形变模型, 活动轮廓, 分水岭算法

Abstract: In this paper，we propose an algorithm for the medical image segmentation based on the live wire algorithm.We modified the traditional live wire algorithm by redefining the distance of the neighborhood，using its pixel，gray-scale mean and gray-scale variance.Then a new connected graph was constructed by the computer，which combines the over-small-regions that was caused by over-segmenting to medical image.We also presented a new method for solving the problem of model’s crossing edge based on T-snake model.While the model was in crossing edge，we used statistical features of model’s interior region in the segmented tomography image，got the interior points by using region growing segmentation and reconstructed the parametric model in order to ensure the model to be deformed to the right edge.This combined method can avoid characteristic segmentation errors when edge detection or region growing technique is adopted separately.

Key words: medical-image segmentation, deformable model, snake, live wire