摘要
提出一种改进的混合水平集方法提取乳腺肿瘤图像.首先利用最大类间方差法与区域生长法将乳腺初始轮廓从乳腺MRI图像中提取出来,然后将此乳腺初始轮廓曲线作为水平集的初始轮廓曲线进行演化,进而找到肿瘤的边界.应用本方法对福建肿瘤医院提供的临床数据进行了实验验证分析.实验结果表明,该方法对于复杂的乳腺MRI序列图的肿瘤分割具有较好的效果.
This paper propose a hybrid level set for segmentation of breast tumor. At first, the outline of breast is extracted by the use of the combination method of Otsu and region growing and the outline curve is used as the initial evolution curve of the hybrid level set for breast tumor extraction. The experimental results show that the method is useful for the breast MRI of Cancer Hospital of Fujian.
出处
《福州大学学报(自然科学版)》
CAS
CSCD
北大核心
2012年第4期464-470,共7页
Journal of Fuzhou University(Natural Science Edition)
基金
福建省自然科学基金资助项目(2009J01282)
福建省科技平台建设资助项目(2008J1005)