摘要
针对传统的分割方法难以实现医学图像自动分割和准确分割的问题,提出了一种基于GVF Snake模型的医学图像分割方法。该方法采用Canny算子的边缘检测结果作为GVF扩散方程计算的边缘映射图,提高了GVF Snake模型的抗噪性能;用分水岭算法自动获取的轮廓作为GVF Snake模型分割的初始轮廓,降低了GVF力场计算的复杂性和分割时轮廓线的迭代次数。分析和实验结果表明,采用该方法对脑部肿瘤MR图像进行分割时,能自动准确地分割出肿瘤区域。
Traditional segmentation methods can not segment the medical image automatically and accurately,this paper presents a medical image segmentation method based on GVF Snake model.The method obtains the edge map based on Canny operator for computing the diffusion equation of GVF, and it improves GVF Snake model＇s anti-noise ability; the edges produced automatically through watershed algorithm will be the initial contours of GVF Snake model, it reduces computational complexity of GVF and the number of iterations for segmentation. The analysis and experiment results show that this method can segment the brain tumor automatically and accurately.
出处
《电子设计工程》
2014年第10期50-52,56,共4页
Electronic Design Engineering
基金
国家自然科学基金资助项目(40976060)
