基于改进C-V模型的乳腺肿瘤超声图像分割

提出了一种改进的C-V模型,完全避免了重初始化步骤并简化了初始水平集函数的构造,大大加快了分割速度。针对乳腺肿瘤超声图像灰度分布的特点和C-V模型分段常量的假设,提出了手工勾画粗略边界,再划分子图进行分割的半自动分割流程,不仅提高了分割准确性,同时也进一步提高了分割效率。实验表明,算法能高效准确地从超声乳腺肿瘤图像中提取出肿瘤的边界,为下一步的目标特征提取、分析打下了良好的基础。

Segmentation of Breast Tumor Ultrasound Images Based on an Improved C-V Model

This paper proposes an improved C-V model, which can avoid the step of re-initialization and simplify the formation of the initial level set function, thus the speed of segmentation can be accelerated greatly. Furthermore, based on the grayscale distribution characteristics of the breast tumor ultrasound images and on the hypothesis of piecewise constant in the C-V model, a semiautomatic segmentation flow has been presented, in which the rough contour is sketched first, and then a subimage would be obtained for the refined segmentation algorithm. This flow has improved not only the accuracy, but also the efficiency of the segmentation algorithm. The experiments show that the proposed algorithm could extract the contour of the breast tumor from the ultrasound images efficiently and accurately, which is fundamentally important for the following target feature extraction and analysis.