电子测量与仪器学报

刘莹,李筠,杨海马,刘瑾,陈嘉慈,付玏.结合区域生长与水平集算法的宫颈癌图像分割[J].电子测量与仪器学报,2020,34(9):146-152

结合区域生长与水平集算法的宫颈癌图像分割

Cervical cancer image segmentation based on region growth and level set algorithm

DOI：

英文关键词:cervical cancer CT images segmentation level set model

基金项目:上海理工大学医工交叉项目(USST-GD40)、上海市自然科学基金(17ZR1443500)、上海航天科技创新基金( SAST2017- 062) 资助项目

作者	单位
刘莹	1. 上海理工大学光电信息计算机工程学院
李筠	1. 上海理工大学光电信息计算机工程学院
杨海马	1. 上海理工大学光电信息计算机工程学院
刘瑾	2. 上海工程技术大学电子工程学院
陈嘉慈	1. 上海理工大学光电信息计算机工程学院
付玏	3. 上海市第一妇婴保健院

Author	Institution
Liu Ying	1. School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology
Li Jun	1. School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology
Yang Haima	1. School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology
Liu Jin	2. School of Electronic and Electrical Engineering,Shanghai University of Engineering Science
Chen Jiaci	1. School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology
Fu Le	3. Shanghai First Maternal and Infant Health Hospital

摘要点击次数: 640

全文下载次数: 961

中文摘要:

针对宫颈图像病灶分割时的初始轮廓敏感问题和图像灰度不明显问题,提出一种新的改进的水平集算法。首先利用各向异性滤波算法等进行图像的去噪;然后在二值图像上使用区域生长算法,提取出粗糙的宫颈病灶区域;最后建立一种基于新的符号压力函数的水平集模型,对初始分割进行细化。该算法可以将局部信息与全局信息结合起来并自动分配局部信息与全局信息的比例。以 3 种统计指标为标准对该方法进行了评估,该方法在准确性、敏感性和特异性上可分别达到 81. 11%、 63. 97%和 78. 64%,分别比传统水平集算法高 30. 69%、15. 15%和 4. 37%。因而,这种改进的水平集算法在实际应用中有一定的价值和意义。

英文摘要:

A new improved level set algorithm is proposed to solve the problem of initial contour sensitivity in cervical image segmentation and the problem of unclear image gray level. Firstly, the image is denoised by anisotropic filtering algorithm. Then the region growth algorithm was used on the binary image to extract the rough cervical lesion area. Finally, a level set model based on the new symbolic pressure function is established to refine the initial segmentation. The algorithm can combine local information with global information and automatically allocate the proportion between them. The accuracy, sensitivity and specificity of this method can reach 81. 11%, 63. 97% and 78. 64% respectively, which are 30. 69%, 15. 15% and 4. 37% higher than the traditional level set algorithm. Therefore, this improved level set algorithm has some value and significance in practical application.

查看全文查看/发表评论下载PDF阅读器