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

廖欣; 郑欣; 邹娟; 冯敏; 孙亮; 杨开选

doi:10.3788/YJYXS20183306.0528

您当前的位置：

首页 >

文章列表页 >

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

图像处理 | 更新时间：2020-07-06

- 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
- Intelligent auxiliary diagnosis method of cervical cytopathology based on deep convolutional neural networks
- 液晶与显示 2018年33卷第6期页码：528-537
- 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" ]
  [ "杨开选(1953-)，女，教授，博士后，主要研究方向为妇产科肿瘤病理及人工智能在疾病诊断中的应用。E-mail：huaxipath@aliyun.com" ]
- 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/YJYXS20183306.0528
  中图分类号： TP394.1;TH691.9
- 收稿日期：2018-03-16，
  
  录用日期：2018-4-17，
  
  纸质出版日期：2018-06
- 稿件说明：
移动端阅览
廖欣, 郑欣, 邹娟, 等. 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[J]. 液晶与显示, 2018,33(6):528-537.

Xin LIAO, Xin ZHENG, Juan ZOU, et al. Intelligent auxiliary diagnosis method of cervical cytopathology based on deep convolutional neural networks[J]. Chinese journal of liquid crystals and displays, 2018, 33(6): 528-537.
廖欣, 郑欣, 邹娟, 等. 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[J]. 液晶与显示, 2018,33(6):528-537. DOI： 10.3788/YJYXS20183306.0528.

Xin LIAO, Xin ZHENG, Juan ZOU, et al. Intelligent auxiliary diagnosis method of cervical cytopathology based on deep convolutional neural networks[J]. Chinese journal of liquid crystals and displays, 2018, 33(6): 528-537. DOI： 10.3788/YJYXS20183306.0528.

摘要

针对宫颈细胞病理自动筛查问题，提出一种基于深度卷积神经网络的智能辅助诊断方法。首先采用基于改进UNet深度卷积神经网络模型的语义分割方法，检测出宫颈细胞病理涂片扫描图像中的细胞（粘连簇团）区域。接着，利用VGG 16深度卷积神经网络模型，结合迁移学习技术，对检测出的细胞（粘连簇团）区域进行精确识别。为了提高深度卷积神经网络模型的性能，在进行细胞（粘连簇团）区域检测、识别的过程中，采用了数据增强技术。同时，针对该领域相关研究缺乏宫颈细胞病理液基涂片扫描图像数据集的问题，我们收集四川大学华西附二院的典型LCT筛查病例，建立了宫颈细胞病理图像HXLCT数据集，并由资深病理医生完成数据标注。实验表明，本文方法能够较好地完成宫颈细胞病理涂片扫描图像中的细胞（粘连簇团）区域检测（正确率为91.33%），并能对检测出的区域完成正常、疑似病变二分类识别（正确率为91.6%，召回率为92.3%，ROC曲线线下面积为0.914）。本文工作将有助于宫颈细胞病理自动筛查系统的开发，对于宫颈癌早期防治具有重要意义。

Abstract

Aiming to the automatic screening of cervical cytology

an intelligent auxiliary diagnosis method was proposed. At first

semantic segmentation method based on the improved UNet deep convolution neural network model was applied to detect the region of cells (cell clusters) on the scanning image of cervical cytology. Secondly

VGG 16 deep convolution neural network model combined with transfer learning was utilized for the exact diagnosis of the detected region of cells (cell clusters). The data augmentation technique was applied in the process of cells (cell clusters) detection and diagnosis to improve the performance of deep convolution neural network model. Meanwhile

considering the deficiency of scanning image datasets for the cervical cytology in the research of relevant fields

we collected the typical cases of liquid based cytology (LCT) for cervical cytological screening in West China Second Hospital of Sichuan University

set up HXLCT dataset of cervical cytological images

which were labeled by the experienced pathologists. The result of the experiment showed that

the cells (cell clusters) in the scanning images of cervical cytology could be effectively detected by the proposed method (accuracy rate was 91.6%

recall rate was 92.3%

and the area under ROC was 0.914). This method may assist in the development of automatic screening system of cervical cytology

which could be of great significance for the early prevention and treatment of endocervical carcinoma.

关键词

Keywords

references

HUTCHINSON M, SHERMAN M R, ALFARO M, et al. Utility of liquid-based cytology for cervical carcinoma screening:results of a population-based study conducted in a region of costa rica with a high incidence of cervical carcinoma.[J]. Cancer , 1999, 87(2):48-55.

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 & Midwifery , 2017, 5(2):188-195.

BIBBO M, HAWTHORNE C. Performance of the autopap primary screening system at jefferson university hospital[J]. Acta Cytologica , 1999, 43(1):27-29.

THOMAS F K M D. The focalpoint system[J]. Cancer Cytopathology , 2004, 102(6):334-339.

MARINAKIS Y, MARINAKI M, DOUNIAS G. Particle swarm optimization for pap-smear diagnosis[J]. Expert Systems with Applications , 2008, 35(4):1645-1656.

MARINAKIS Y, DOUNIAS G, JANTZEN J. Pap smear diagnosis using a hybrid intelligent scheme focusing on genetic algorithm based feature selection and nearest neighbor classification[J]. Computers in Biology & Medicine , 2009, 39(1):69-78.

CHANKONG T, THEERAUMPON N, AUEPHANWIRIYAKUL S. Automatic cervical cell segmentation and classification in pap smears[J]. Computer Methods and Programs in Biomedicine , 2014, 113(2):539-556.

BORA K, CHOWDHURY M, MAHANTA L B, et al. Automated classification of pap smear images to detect cervical dysplasia[J]. Computer Methods & Programs in Biomedicine , 2017, 138(1):31-47.

JANTZEN J, NORUP J, DOUNIAS G, et al. Pap-smear benchmark data for pattern classification[J]. Nisis , 2005, 32(1):1-9.

Zhang L, Lu L, Nogues I, et al. DeepPap:deep convolutional networks for cervical cell classification[J]. IEEE Journal of Biomedical & Health Informatics , 2017, 21(6):1633-1643.

刘智, 黄江涛, 冯欣.构建多尺度深度卷积神经网络行为识别模型[J].光学精密工程, 2017, 25(3):799-805.

Liu Z, HUANG J T, FENG X. Action recognition model construction based on multi-scale deep convolution neural network[J]. Optics and precision Engineering , 2017, 25(3):799-805. (in Chinese)

LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis , 2017, 42(9):60-88.

SHIN H C, ROTH H R, GAO M, et al. Deep convolutional neural networks for computer-aided detection:cnn architectures, dataset characteristics and transfer learning[J]. IEEE Transactions on Medical Imaging , 2016, 35(5):1285-1298.

MARON H, GALUN M, AIGERMAN N, et al. Convolutional neural networks on surfaces via seamless toric covers[J]. Acm Transactions on Graphics , 2017, 36(4):71-95.

LISKOWSKI P, KRAWIEC K. Segmenting retinal blood vessels with deep neural networks[J]. IEEE Transactions on Medical Imaging , 2016, 35(11):2369-2380.

CHOUGRAD H, ZOUAKI H, ALHEYANE O. Deep convolutional neural networks for breast cancer screening[J]. Computer Methods & Programs in Biomedicine , 2018, 157(2):19-30.

周同雪, 朱明.视频图像中的运动目标检测[J].液晶与显示, 2017, 32(1):40-47.

ZHOU T X, ZHU M. Moving target detection of the video images[J]. Chinese Journal of Liquid Crystals Displays , 2017, 32(1):40-47. (in Chinese)

LATSUZBAIA A, HEBETTE G, FISHER M, et al. Introduction of liquid-based cytology and human papillomavirus testing in cervical cancer screening in luxembourg[J]. Diagnostic Cytopathology , 2017, 45(5):384-390.

BITLER M P, CARPENTER C S. Effects of state cervical cancer insurance mandates on pap test rates[J]. Health Services Research , 2017, 52(1):156-175.

RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham, Switzerland, Springer, 2015: 234-241.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science , 2014, 52(3):1-14.

HAN D, LIU Q, FAN W. A new image classification method using cnn transfer learning and web data augmentation[J]. Expert Systems with Applications , 2018, 95(2):43-56.

余镇, 吴凌云, 倪东, 等.基于深度学习的胎儿颜面部超声标准切面自动识别[J].中国生物医学工程学报, 2017, 36(3):267-275.

YU Z, W L Y, NI D, et al. Fetal facial standard plane recognition via deep convolutional neural networks[J]. Chinese Journal of Biomedical Engineering , 2017, 36(3):267-275. (in Chinese)

RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision , 2015, 115(3):211-252.

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

基于神经网络集成模型的宫颈细胞病理计算机辅助诊断方法

基于多尺度上下文提取的小样本野生动物检测

结合双注意力和结构相似度量的图像超分辨率重建网络

基于笔划三维深度特征的签名识别

基于深度学习的乳液泵缺陷检测算法