基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法

廖欣; 郑欣; 邹娟; 冯敏; 孙亮; 杨帆

doi:10.3788/YJYXS20183304.0347

您当前的位置：

首页 >

文章列表页 >

基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法

图像处理 | 更新时间：2020-07-06

- 基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法
- Computer-aided diagnosis of cervical cytopathology based on neural network ensemble model
- 液晶与显示 2018年33卷第4期页码：347-356
- 作者机构：
  
  1.四川大学华西第二医院病理科, 四川成都 610041
  2.四川大学出生缺陷与相关妇儿疾病教育部重点实验室, 四川成都 610041
  3.电子科技大学计算机科学与工程学院, 四川成都 611731
- 作者简介：
  
  [ "廖欣(1981-), 女, 四川成都人, 硕士, 病理主诊医师; 研究方向:妇产科临床病理诊断; 人工智能在疾病诊断与病理分析中的应用等; E-mail:xinty927@163.com" ]
  [ "郑欣(1981-), 男, 四川绵阳人, 博士后; 研究方向:健康大数据; 人工智能在大健康及医疗领域的应用等; E-mail:1820745320@qq.com" ]
  [ "杨帆(1975-), 男, 四川南溪人, 博士, 病理副主任医师; 研究方向:妇科肿瘤及诊断; E-mail:fanyang@scu.edu.cn" ]
- 基金信息：
  
  四川省重点实验室开放基金(2017LF3008);广东省应用型研发重大专项基金(2015BD10131002);Program of Key Laboratory Open Fund in Sichuan Province(2017LF3008);The Important Special Fund for Applied R & D in Guangdong Province(2015BD10131002)
- DOI：10.3788/YJYXS20183304.0347
  中图分类号： TP394.1;TH691.9
- 收稿日期：2017-12-16，
  
  录用日期：2018-2-6，
  
  纸质出版日期：2018-04-05
- 稿件说明：
移动端阅览
廖欣, 郑欣, 邹娟, 等. 基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法[J]. 液晶与显示, 2018,33(4):347-356.

Xin LIAO, Xin ZHENG, Juan ZOU, et al. Computer-aided diagnosis of cervical cytopathology based on neural network ensemble model[J]. Chinese journal of liquid crystals and displays, 2018, 33(4): 347-356.
廖欣, 郑欣, 邹娟, 等. 基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法[J]. 液晶与显示, 2018,33(4):347-356. DOI： 10.3788/YJYXS20183304.0347.

Xin LIAO, Xin ZHENG, Juan ZOU, et al. Computer-aided diagnosis of cervical cytopathology based on neural network ensemble model[J]. Chinese journal of liquid crystals and displays, 2018, 33(4): 347-356. DOI： 10.3788/YJYXS20183304.0347.

摘要

针对宫颈细胞病理图像自动筛查问题，本文提出一种基于人工智能技术的计算机辅助诊断方法。该方法通过对宫颈细胞病理图像采用自适应双阈值法进行初步检测，再采用改进Chan-Vase模型进行精确分割，提取出细胞（粘连簇团）中的不同区域。然后，结合病理诊断专家规则，构建相应的正交特征集。在此基础上，使用神经网络集成模型进行正常、疑似病变二分类识别，完成计算机辅助诊断。实验表明，本文方法能够有效完成宫颈病理细胞（粘连簇团）的分类识别，具有较高的正确率（84%）与较低的误判率（2.1%）。满足了在保证判断正确率的条件下，尽量降低将疑似病变样本误判为正常样本的实际病理诊断要求。

Abstract

Aiming to the automatic screening of cervical cytopathological images

an artificial intelligence based automatic diagnosis-assisted method was proposed. First of all

adaptive dual threshold method was used to detect the cervical cytopathological images initially. Secondly

improved Chan-Vase model was used to precisely extract different areas of adhesive cell cluster. After that

the related feature set was built according to the diagnostic rules of pathological experts. At last

neural network ensemble was applied to normal or suspected lesions two-classification recognition. The result of the experiment showed that cervical cell lesions could be effectively distinguished according to classification with this method

which had high accuracy (84%) and low rate of misjudgment (2.1%)

meeting the practical requirement of pathological diagnosis

which is reducing the miscalculating of the suspected lesions to normal ones

meanwhile assuring the diagnostic accuracy.

关键词

Keywords

references

ASHTARIAN H, MIRZABEIGI E, MAHMOODI E, et al . Knowledge about cervical cancer and Pap smear and the factors influencing the pap test screening among women[J]. International Journal of Community Based Nursing and Midwifery , 2017, 5(2):188-195.

KIM J J, BURGER E A, SY S, et al . Optimal cervical cancer screening in women vaccinated against human papillomavirus[J]. Journal of the National Cancer Institute , 2017, 109(2):djw216.

胡佐鸿, 赵春, 包骥, 等.全片数字化图像在诊断细胞病理学中的应用[J].中华病理学杂志, 2017, 46(8):581-585.

HU Z H, ZHAO C, BAO J, et al . Application of whole slide imaging in diagnostic cytology[J]. Chinese Journal of Pathology , 2017, 46(8):581-585. (in Chinese)

JENNY J, ISENEGGER I, BOON M E, et al . Consistency of a double PAPNET scan of cervical smears[J]. Acta Cytologica , 1997, 41(1):82-87.

BIBBO M, HAWTHORNE C. Performance of the AutoPap primary screening system at Jefferson University Hospital[J]. Acta Cytologica , 1999, 43(1):27-29.

KARDOST F. The FocalPoint system:FocalPoint slide profiler and FocalPoint GS[J]. Cancer Cytopathology , 2004, 102(6):334-339.

HUTCHINSON M L, ISENSTEIN L M, GOODMAN A, et al . Homogeneous sampling accounts for the increased diagnostic accuracy using the ThinPrep TM processor[J]. American Journal of Clinical Pathology , 1994, 101(2):215-219.

高细见, 曾立波, 吴琼水, 等.一种基于显微多光谱宫颈细胞图像自动分割方法[J].数据采集与处理, 2004, 19(4):441-445.

GAO X J, ZENG L B, WU Q S, et al . Automatic segmentation method for cervical cell based on multispectral microgram[J]. Journal of Data Acquisition & Processing , 2004, 19(4):441-445. (in Chinese)

全宇, 王忠庆, 何苗.基于交叉熵的神经网络在病理图像分析中的应用[J].中国医科大学学报, 2009, 38(6):446-448.

QUAN Y, WANG Z Q, HE M. Application of neural network based on cross-entropy method in pathological image analysis[J]. Journal of China Medical University , 2009, 38(6):446-448. (in Chinese)

赵英红, 周中顺, 孙存杰, 等.一种新的用于宫颈癌粘连细胞图像分割的分水岭算法[J].军事医学, 2014, 38(12):972-975.

ZHAO Y H, ZHOU Z S, SUN C J, et al . A new modified watershed algorithm for image segmentation in cervical cancer cell adhesion[J]. Military Medical Sciences , 2014, 38(12):972-975. (in Chinese)

李光, 张海峰, 王军梅, 等.宫颈鳞状细胞癌细胞核的形态定量分析[J].山西医科大学学报, 2005, 36(4):429-431.

LI G, ZHANG H F, WANG J M, et al . Nuclear morphometrical analysis of cervix cancer[J]. Journal of Shanxi Medical University , 2005, 36(4):429-431. (in Chinese)

LIANG G M, TANG C J, LIU D H, et al . A multi-level and adaptive dual threshold segmentation algorithm base on evaluation[J]. Acta Electronica Sinica , 2009, 37(4):750-752, 763.

王相海, 王金玲, 方玲玲.灰度差能量函数引导的图像分割自适应C-V模型[J].模式识别与人工智能, 2015, 28(3):214-222.

WANG X H, WANG J L, FANG L L. An adaptive C-V image segmentation model guided by gray difference energy function[J]. Pattern Recognition and Artificial Intelligence , 2015, 28(3):214-222. (in Chinese)

赵爱罡, 王宏力, 杨小冈, 等.纹理粗糙度在红外图像显著性检测中的应用[J].光学精密工程, 2016, 24(1):220-228.

ZHAO A G, WANG H L, YANG X G, et al . Application of texture coarseness in saliency detection of infrared image[J]. Optics and Precision Engineering , 2016, 24(1):220-228. (in Chinese)

纪慧中, 贾大宇, 董恩清, 等.基于图像特征和光流场的非刚性图像配准[J].光学精密工程, 2017, 25(9):2469-2482.

JI H Z, JIA D Y, DONG E Q, et al . Non-rigid registrations based on image characteristics and optical flows[J]. Optics and Precision Engineering , 2017, 25(9):2469-2482. (in Chinese)

于萍, 步宏, 王华, 等.免疫组化结果的图像分析与人工计数方法的对比研究[J].生物医学工程学杂志, 2003, 20(2):288-290.

YU P, BU H, WANG H, et al . Comparative study on image analysis and manual counting of immunohistochemistry[J]. Journal of Biomedical Engineering , 2003, 20(2):288-290. (in Chinese)

王宇, 邹文辉, 杨晓敏, 等.基于计算机视觉的X射线图像异物分类研究[J].液晶与显示, 2017, 32(4):287-293.

WANG Y, ZOU W H, YANG X M, et al . X-ray image illegal object classification based on computer vision[J]. Chinese Journal of Liquid Crystals and Displays , 2017, 32(4):287-293. (in Chinese)

ROWEIS S. EM algorithms for PCA and SPCA[C]// Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems . Denver, Colorado, USA: ACM, 1997: 626-632.

ALFARO M E, ZOLLER S, LUTZONI F. Bayes or bootstrap? A simulation study comparing the performance of Bayesian Markov chain Monte Carlo sampling and bootstrapping in assessing phylogenetic confidence[J]. Molecular Biology and Evolution , 2003, 20(2):255-266.

ZHANG L, LU L, NOGUES I, et al . DeepPap:Deep convolutional networks for cervical cell classification[J]. IEEE Journal of Biomedical and Health Informatics , 2017, 21(6):1633-1643.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度卷积神经网络的宫颈细胞病理智能辅助诊断方法