A robust level set framework for medical image segmentation
Yong Yang, Pan Lin, Chong-Xun Zheng, Xiangguo Yan · 2004
In this paper, a new speed function of level set framework is presented. The region information, instead of the image gradient information, is fused into the level set fundamental model to improve the robustness of the segmentation for medical images. This new speed function is particularly well adapted to situations where edges are weak and overlap. A number of experiments on ultrasound (US), CT, MR and X-ray modalities medical images were performed to evaluate the new method. The experimental results show the proposed method is effective and robust.