期刊文献+

基于最大截面特征的病变宫颈细胞核的自动筛查 预览

Automatic screening of abnormal cervical nucleus based on maximum section feature
在线阅读 下载PDF
收藏 分享 导出
摘要 针对基于细胞图像分割的病变宫颈细胞筛查中由于细胞精细分割复杂而不能实现筛查自动化的问题,提出一种省略精细分割步骤的宫颈细胞分类算法。首先,定义一种新的用于描述像素值分布的特征--最大截面(MAXSection)特征,将该特征与反向传播(BP)神经网络和Selective Search算法结合,实现细胞核感兴趣区域(ROI)的准确提取(最高正确率100%);其次,基于最大截面特征定义了两个参数--估计长与估计宽,用于描述病变细胞核的形态变化;最后,根据宫颈细胞发生癌变时其核会绝对增大的特点,利用以上两参数实现病变细胞核(估计长与估计宽中至少一个参数大于65)与正常细胞核(估计长与估计宽均小于等于65)的分类。实验结果表明,该自动筛查算法的准确率为98.89%,敏感度为98.18%,特异度为99.20%。该算法可以完成从输入整幅巴氏涂片到输出最终筛查结果的全部过程,实现病变宫颈细胞筛查的自动化。 Aiming at the problem that the complexity of cervical cell image fine segmentation makes it difficult to achieve automatic abnormal cell screening based on cell image segmentation,a cervical cell classification algorithm without fine segmentation step was proposed.Firstly,a new feature named MAXimum Section(MAXSection)was defined for describing the distribution of pixel values,and was combined with Back Propagation(BP)neural network and Selective Search algorithm to realize the accurate extraction of nucleus Region Of Interest(ROI)(the highest accuracy was 100%).Secondly,two parameters named estimated length and estimated width were defined based on MAXSection to describe morphological changes of abnormal nucleus.Finally,according to the characteristic of absolute enlargement of cervical nucleus when cervical cancer occurs,the classification of abnormal nucleus(at least one parameter of estimated length and width is greater than 65)and normal nucleus(estimated length and width are both less than 65)can be realized by using the above two parameters.Experimental results show that the proposed algorithm has screening accuracy of 98.89%,sensitivity of 98.18%,and specificity of 99.20%.The proposed algorithm can complete the total process from the input of whole Pap smear image to the output of final screening results,realizing the automation of abnormal cervical cell screening.
作者 韩颖 赵萌 陈胜勇 王照锡 HAN Ying;ZHAO Meng;CHEN Shengyong;WANG Zhaoxi(School of Electrical and Electronic Engineering,Tianjin University of Technology,Tianjin 300384,China;Key Laboratory of Computer Vision and System,Ministry of Education(Tianjin University of Technology),Tianjin 300384,China;School of Computer Science and Engineering,Tianjin University of Technology,Tianjin 300384,China)
出处 《计算机应用》 CSCD 北大核心 2019年第4期1189-1195,共7页 journal of Computer Applications
基金 国家自然科学基金资助项目(61703304,U1509207)。
关键词 病变宫颈细胞筛查 精细分割 反向传播神经网络 SELECTIVE Search算法 abnormal cervical cell screening fine segmentation Back Propagation(BP)neural network Selective Search algorithm
作者简介 韩颖(1994-),女,河北秦皇岛人,硕士研究生,主要研究方向:图像处理、机器学习;赵萌(1988-),女,河北保定人,讲师,博士,CCF会员,主要研究方向:图像处理、机器学习;陈胜勇(1973-),男,浙江温州人,教授,博士,主要研究方向:计算机视觉;王照锡(1991-),男,山东日照人,硕士研究生,CCF会员,主要研究方向:机器学习、医学图像分析。
  • 相关文献

参考文献11

二级参考文献21

  • 1陈明立,谭远发.我国东中西部三大区域人口竞争力实证比较研究[J].经济学家,2007(2):53-63. 被引量:5
  • 2FERLAY J, SOERJOMATARAM I, DIKSHIT R, et al. Cancer in cidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012 EJ/OL~. International Journal of Cancer, 2015, 136 (5): E359- E386. http: / / onlinelibary, wiley.com/ doi/10.l OO2 / ijc.29 210 / abstract. 被引量:1
  • 3JENSEN B. Neuro-Fuzzy Classification of Cells in Cervical Smears [D~. Denmark: Technical University of Denmark, 1999. 被引量:1
  • 4NIKOLAOS A, GEORGE D, JAN J. Pap-Smear classification using efficient second order neural network training algorithmsEM~//GEORGE A V, THEMISTOKLIS P. Methods and Applications of Aritificial Intelligence: Berlin Heidelberg: Springer Verlag 2004 : 230-245. 被引量:1
  • 5YANNIS M, GEORGIOS D, JAN J. Pap smear diagnosis using a hybrid intelligent scheme focusing on genetic algorithm based feature selection and nearest neighbor classification[J~. Computers in Biology and Medicine,2009, 39 (I) :69-78. 被引量:1
  • 6CHEN Yungfu, HUANG Pochi, Lin Kercheng, et al. Semi-Automatic segmentation and classification of pap smear cellsEJ3. IEE Journal of Biomedical and health informatics, 2014, 18 (1) : 94-108. 被引量:1
  • 7WANG Ruihu. AdaBoost for feature selection, classification and its relation with SVM, A Review[J]. Physics Procedia, 2012,25 : 800-807. 被引量:1
  • 8ABID S, VINOD S, RAJEEV G, Hybrid ensemble learning technique for screening of cervical cancer using Papanicolaou smear image analysis[J~. Personalized Medicine Universe, 2015, 4:54-62. 被引量:1
  • 9NORUP J. Classification of pap-smear data by transductive neuro-fuzzy methods[D~. Denmark: Technical University of Denmark, 2005. 被引量:1
  • 10CHANKONG T, THEERA-UMPON N, AUEPHANWIRIYAKUL S. Automatic cervical cell segmentation and classification in Pap smearsl-J]. Computer Methods and Programs in Biomedicine,2014, 113(2):539-556. 被引量:1

共引文献308

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈