• 《工程索引》(EI)刊源期刊
  • 中文核心期刊(综合性理工农医类)
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于深度学习的宫颈癌异常细胞快速检测方法

姚超 赵基淮 马博渊 李莉 马莹 班晓娟 姜淑芳 邵炳衡

姚超, 赵基淮, 马博渊, 李莉, 马莹, 班晓娟, 姜淑芳, 邵炳衡. 基于深度学习的宫颈癌异常细胞快速检测方法[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.12.001
引用本文: 姚超, 赵基淮, 马博渊, 李莉, 马莹, 班晓娟, 姜淑芳, 邵炳衡. 基于深度学习的宫颈癌异常细胞快速检测方法[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.12.001
YAO Chao, ZHAO Ji-huai, MA Bo-yuan, LI Li, MA Ying, BAN Xiao-juan, JIANG Shu-fang, SHAO Bing-heng. Fast detection method for cervical cancer abnormal cells based on deep learning[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.12.001
Citation: YAO Chao, ZHAO Ji-huai, MA Bo-yuan, LI Li, MA Ying, BAN Xiao-juan, JIANG Shu-fang, SHAO Bing-heng. Fast detection method for cervical cancer abnormal cells based on deep learning[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.12.001

基于深度学习的宫颈癌异常细胞快速检测方法

doi: 10.13374/j.issn2095-9389.2021.01.12.001
基金项目: 海南省财政科技计划资助项目(ZDYF2019009);国家自然科学基金资助项目(61873299,61902022,61972028,6210020684);中央高校基本科研业务费资助项目(FRF-TP-19-015A1,FRF-TP-20-061A1Z,FRF-TP-19-043A2,00007467);佛山市科技创新专项资金资助项目(BK19AE034,BK20AF001,BK21BF002)
详细信息
    通讯作者:

    E-mail: jsf0912@aliyun.com

  • 中图分类号: TP391

Fast detection method for cervical cancer abnormal cells based on deep learning

More Information
  • 摘要: 宫颈癌是严重危害妇女健康的恶性肿瘤,威胁着女性的生命,而通过基于图像处理的细胞学筛查是癌前筛查的最为广泛的检测方法。近年来,随着以深度学习为代表的机器学习理论的发展,卷积神经网络以其强有效的特征提取能力取得了图像识别领域的革命性突破,被广泛应用于宫颈异常细胞检测等医疗影像分析领域。但由于病理细胞图像具有分辨率高和尺寸大的特点,且其大多数局部区域内都不含有细胞簇,深度学习模型采用穷举候选框的方法进行异常细胞的定位和识别时,经过穷举候选框获得的子图大部分都不含有细胞簇。当子图数量逐渐增加时,大量不含细胞簇的图像作为目标检测网络输入会使图像分析过程存在冗余时长,严重减缓了超大尺寸病理图像分析时的检测速度。本文提出一种新的宫颈癌异常细胞检测策略,针对使用膜式法获得的病理细胞图像,通过基于深度学习的图像分类网络首先判断局部区域是否出现异常细胞,若出现则进一步使用单阶段的目标检测方法进行分析,从而快速对异常细胞进行精确定位和识别。实验表明,本文提出的方法可提高一倍的宫颈癌异常细胞检测速度。

     

  • 图  1  本文提出的加速策略的技术路线流程图(图中红色框代表异常细胞)

    Figure  1.  Flow chart of the proposed acceleration strategy (The red box indicates an abnormal cell)

    图  2  “滑动交叠裁剪”示例

    Figure  2.  Example of “sliding overlap clipping”

    图  3  YoloV5网络结构

    Figure  3.  YoloV5 network structure

    图  4  数据集中部分细胞簇的识别示例。(a,b)正确识别结果;(c)“过检”识别结果;(d)“漏检”识别结果

    Figure  4.  Examples of the identification of some cell clusters in datasets: (a,b) correct recognition results; (c) recognition results of "over inspection"; (d) recognition results of "over inspection"

    表  1  图像标注情况

    Table  1.   Image annotation

    CategoryNumber
    ASC-US2032
    ASC-H1156
    LSIL4387
    HSIL1389
    Total8964
    下载: 导出CSV

    表  2  细胞簇图像分类实验

    Table  2.   Cell cluster image classification experiment

    ModelAccuracy/%True negative rate/%True positive rate/%Average time consumption/sParams/MBMemory Cost/GB
    Resnet5089.0196.09%86.93%0.01722.514.12
    Resnet10189.6289.39%91.46%0.02742.507.85
    SE-Resnext5084.59%96.09%79.90%0.01627.564.28
    SE-Resnext10182.50%91.62%79.90%0.03348.968.05
    Efficientnet-b475.71%98.88%57.29%0.02719.435.12
    Efficientnet-b783.41%98.88%68.84%0.04366.5225.32
    Resnext50_32X4d88.25%94.41%88.44%0.01225.034.29
    Resnext101_32X4d87.20%89.94%91.46%0.02544.188.03
    SE-Resnet10182.50%92.18%79.40%0.02349.337.63
    SE-Resnet5085.11%88.83%86.43%0.01128.093.9
    Nasnet85.37%99.44%72.36%0.03888.7524.04
    Shufflenetv281.46%099.50%0.0107.390.60
    Inceptionv481.72%99.44%00.02442.6812.31
    Xception78.85%99.44%99.50%0.01522.868.42
    Densenet12180.58%94.41%56.28%0.0217.982.88
    下载: 导出CSV

    表  3  模型推理时间对比实验

    Table  3.   Comparison experiment for model reasoning time

    Single stage modelTime consumption/sParam/MB Double stage modelsTime consumption/sParam/MB
    Faster RCNN277540.1 Resnet50+Faster RCNN108962.61
    Cascade RCNN287765.9 Resnet50+Cascade RCNN117888.41
    Libra RCNN311841.6 Resnet50+Libra RCNN149664.11
    Tridentnet446933.1 Resnet50+Tridentnet210655.61
    Foveabox243736.0 Resnet50+Foveabox118958.51
    ATSS301431.2 Resnet50+ATSS145053.71
    YoloV5138645.7 Resnet50+YoloV569568.21
    下载: 导出CSV

    表  4  模型识别精度对比实验

    Table  4.   Comparison experiment for model recognition accuracy

    Single stage modelAP50/%Double stage modelsAP50/%
    Faster RCNN70.1Resnet50+Faster RCNN66.8
    Cascade RCNN69.2Resnet50+Cascade RCNN65.7
    Libra RCNN68.3Resnet50+Libra RCNN67.0
    Tridentnet65.7Resnet50+Tridentnet59.7
    Foveabox67.3Resnet50+Foveabox61.9
    ATSS63.8Resnet50+ATSS63.5
    YoloV575.3Resnet50+YoloV570.1
    下载: 导出CSV
  • [1] Ma D, Xi L. Special discussion on cervical cancer: Research Progress in epidemiology and etiology of cervical cancer. J Pract Obstet Gynecol, 2001, 17(2): 61 doi: 10.3969/j.issn.1003-6946.2001.02.001

    马丁, 奚玲. 宫颈癌专题讨论——宫颈癌流行病学及病因学研究进展. 实用妇产科杂志, 2001, 17(2):61 doi: 10.3969/j.issn.1003-6946.2001.02.001
    [2] Li C C, Zhu L. The cause of cervical cancer and the status of cervical cancer vaccine. J Mod Oncol, 2018, 26(20): 3333 doi: 10.3969/j.issn.1672-4992.2018.20.040

    李聪聪, 朱莉. 宫颈癌的病因及宫颈癌疫苗现状. 现代肿瘤医学, 2018, 26(20):3333 doi: 10.3969/j.issn.1672-4992.2018.20.040
    [3] Wu S C. Significance of gynecological census in prevention of cervical cancer. Guide China Med, 2011, 9(27): 91 doi: 10.3969/j.issn.1671-8194.2011.27.065

    吴三春. 妇科普查对预防宫颈癌的意义. 中国医药指南, 2011, 9(27):91 doi: 10.3969/j.issn.1671-8194.2011.27.065
    [4] Zhang W H, Li N, Wu L Y. Attention should be paid on the trend of carcinoma of the cervix in young women. Zhejiang Cancer J, 2000, 6(2): 112

    章文华, 李楠, 吴令英. 重视宫颈癌患者年轻化的趋势. 浙江肿瘤, 2000, 6(2):112
    [5] Lin Y X. Clinical Pathological Features and Prognosis Analysis of Cervical Cancer [Dissertation]. Nanning: Guangxi Medical University, 2013

    林泳秀. 宫颈癌的临床病理特点与预后分析[学位论文]. 南宁: 广西医科大学, 2013
    [6] Wang L, Zhao W X, Zhao X L, et al. A comparative study of two methods of smear-making: Membrane-based and sedimentation in liquid-based cervical cytology. Med Pharm J Chin Peoples Liberation Army, 2011, 23(4): 6 doi: 10.3969/j.issn.2095-140X.2011.04.003

    王力, 赵稳兴, 赵玺龙, 等. 膜式和沉降式宫颈液基细胞学制片方法的比较研究. 解放军医药杂志, 2011, 23(4):6 doi: 10.3969/j.issn.2095-140X.2011.04.003
    [7] Zhao C Q, Zhou X R, Sui L, et al. Cervical Cancer Screening and Clinical Management (Cytology, Histology, Colposcopy). Beijing: Beijing Science and Technology Press, 2017

    赵澄泉, 周先荣, 隋龙, 等. 宫颈癌筛查及临床处理(细胞学、组织学和阴道镜学). 北京: 北京科学技术出版社, 2017
    [8] Wei L H. Standardized Training Materials for Colposcopy and Cervical Cytopathology. Beijing: People’s Medical Publishing House, 2020

    魏丽惠. 阴道镜及宫颈细胞病理学规范化培训教材. 北京: 人民卫生出版社, 2020
    [9] Wang Y Y, Wang Y, Qiao Y L, et al. The future of cervical cancer screening in China‒Abandonment or conservation of cytological primary screening. Chin J Pract Gynecol Obstet, 2017, 33(3): 324

    王轶英, 王悦, 乔友林, 等. 中国宫颈癌筛查未来之路——细胞学初筛的弃或守. 中国实用妇科与产科杂志, 2017, 33(3):324
    [10] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436 doi: 10.1038/nature14539
    [11] Szeliski R. Computer Vision. London: Springer London Press, 2011
    [12] Zhang Y Z. Image Engineering. 4th Ed. Beijing: Tsinghua University Press, 2018

    章毓晋. 图像工程. 4版. 北京: 清华大学出版社, 2018
    [13] Shi Y H. Study of Machine Learning Techniques and Applications in Med-Ical Image Analysis [Dissertation]. Nanjing: Nanjing University, 2013

    史颖欢. 医学图像处理中的机器学习方法及其应用研究[学位论文]. 南京: 南京大学, 2013
    [14] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533 doi: 10.1038/323533a0
    [15] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 770
    [16] Cai W B. Study on Detection Techniques of Pathological Images of Cancer Cells [Dissertation]. Taiyuan: North University of China, 2018

    蔡武斌. 癌细胞病理图像的检测技术研究[学位论文]. 太原: 中北大学, 2018
    [17] Kermany D S, Goldbaum M, Cai W J, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 2018, 172(5): 1122 doi: 10.1016/j.cell.2018.02.010
    [18] Cong M, Wu T, Liu D, et al. Prostate MR/TRUS image segmentation and registration methods based on supervised learning. Chin J Eng, 2020, 42(10): 1362

    丛明, 吴童, 刘冬, 等. 基于监督学习的前列腺MR/TRUS图像分割和配准方法. 工程科学学报, 2020, 42(10):1362
    [19] Zhang L, Le L, Nogues I, et al. DeepPap: deep convolutional networks for cervical cell classification. IEEE J Biomed Heal Inform, 2017, 21(6): 1633 doi: 10.1109/JBHI.2017.2705583
    [20] Wu M, Yan C B, Liu H Q, et al. Automatic classification of cervical cancer from cytological images by using convolutional neural network. Biosci Rep, 2018, 38(6): BSR20181769 doi: 10.1042/BSR20181769
    [21] Jia D Y, Li Z Y, Zhang C W. Detection of cervical cancer cells based on strong feature CNN-SVM network. Neurocomputing, 2020, 411: 112 doi: 10.1016/j.neucom.2020.06.006
    [22] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell, 2017, 39(6): 1137 doi: 10.1109/TPAMI.2016.2577031
    [23] Chen X H. The Bethesda System for Reporting Cervical Cytology (Definitions, Criteria, and Explanatory Notes). 3rd Ed. Beijing: Science press, 2019

    陈小槐. 子宫颈细胞学Bethesda报告系统(中文翻译版, 原书第3版). 北京: 科学出版社, 2019
    [24] He Y E, Wang Y F, Lang J H, et al. The evaluation of computer cytological test with colposcopy for the diagnosis of cervical lesions. Chin J Obstet Gynecol, 1998, 33(5): 265 doi: 10.3760/j.issn:0529-567X.1998.05.002

    贺又娥, 王友芳, 郎景和, 等. 计算机辅助细胞检测系统配合阴道镜检查对子宫颈病变的诊断价值. 中华妇产科杂志, 1998, 33(5):265 doi: 10.3760/j.issn:0529-567X.1998.05.002
    [25] Stoler M H. Advances in cervical screening technology. Mod Pathol, 2000, 13(3): 275 doi: 10.1038/modpathol.3880048
    [26] Zhou L P. Cervical Smears Automatic Auxiliary System Related to Image Interpretation Techniques [Dissertation]. Qingdao: Ocean University of China, 2009

    周立平. 宫颈涂片自动辅助判读系统中相关图像技术的研究[学位论文]. 青岛: 中国海洋大学, 2009
    [27] Zheng K, Zhang S, Tang J Q. Application of Thinprep computer-assisted imaging system in cervical cytology. Chin J Diagn Pathol, 2015, 22(6): 364 doi: 10.3969/j.issn.1007-8096.2015.06.013

    郑珂, 张声, 唐坚清. 计算机辅助阅片系统在宫颈细胞学筛查中的应用. 诊断病理学杂志, 2015, 22(6):364 doi: 10.3969/j.issn.1007-8096.2015.06.013
    [28] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: common objects in context // Computer Vision – ECCV 2014. Zurich, 2014: 740
    [29] Paszke A, Gross S, Massa F, et al. Pytorch: An imperative style, high-performance deep learning library[J/OL]. arXiv preprint (2019-12-3) [2021-6-24]. https://arxiv.org/abs/1912.01703
    [30] Mao X Y, Leng X F. Introduction to Opencv3 programming. Beijing: Electronics industry publishing house, 2015

    毛星云, 冷雪飞. Opencv3编程入门. 北京: 电子工业出版社, 2015
    [31] Huang G, Liu Z, Pleiss G, et al. Convolutional networks with dense connectivity. IEEE Trans Pattern Anal Mach Intell, 2019, doi: 10.1109/TPAMI.2019.2918284
    [32] Hu J, Shen L, Sun G. Squeeze-and-excitation networks // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 7132
    [33] Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks // International Conference on Machine Learning. Long Beach, 2019: 6105
    [34] Xie S N, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 5987
    [35] Zoph B, Vasudevan V, Shlens J, et al. Learning transferable architectures for scalable image recognition // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 8697
    [36] Ma N N, Zhang X Y, Zheng H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design // Computer Vision – ECCV 2018. Munich, 2018: 122
    [37] Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning // Proceedings of the AAAI Conference on Artificial Intelligence. San Francisco, 2017(31): 1
    [38] Chollet F. Xception: deep learning with depthwise separable convolutions // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 1800
    [39] Cai Z W, Vasconcelos N. Cascade R-CNN: Delving into high quality object detection // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 6154
    [40] Pang J M, Chen K, Shi J P, et al. Libra R-CNN: Towards balanced learning for object detection // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, 2019: 821
    [41] Li Y H, Chen Y T, Wang N Y, et al. Scale-aware trident networks for object detection // 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, 2019: 6053
    [42] Kong T, Sun F C, Liu H P, et al. FoveaBox: beyound anchor-based object detection. IEEE Trans Image Process, 2020, 29: 7389 doi: 10.1109/TIP.2020.3002345
    [43] Zhang S F, Chi C, Yao Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 9756
    [44] Ultralytics. YoloV5[EB/OL]. Github(2020-10-12)[2021-06-24]. https://github.com/ultralytics/YoloV5
  • 加载中
图(4) / 表(4)
计量
  • 文章访问数:  61
  • HTML全文浏览量:  19
  • PDF下载量:  20
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-01-12
  • 网络出版日期:  2021-06-18

目录

    /

    返回文章
    返回