基于卷积神经网络的肠道寄生虫虫卵识别模型研究

doi:10.12183/j.scjpm.2023.1498

华南预防医学 ›› 2023, Vol. 49 ›› Issue (12): 1498-1503.doi: 10.12183/j.scjpm.2023.1498

基于卷积神经网络的肠道寄生虫虫卵识别模型研究

殷李华^1,2, 胡建雄¹, 方悦怡³, 容祖华⁴, 黄栩滨⁴, 何冠豪¹, 江芷莹¹, 肖建鹏⁴, 刘涛¹, 马文军¹

1.暨南大学基础医学与公共卫生学院公共卫生与预防医学系,广东广州 510632;
2.广州城建职业学院信息工程学院;
3.广东省疾病预防控制中心寄生虫病预防控制所;
4.广东省疾病预防控制中心广东省公共卫生研究院

收稿日期:2023-10-20 出版日期:2023-12-20 发布日期:2024-02-05
通讯作者: 马文军,E-mail：mawj@gdiph.org.cn
作者简介:殷李华（1994—）,男,硕士研究生,研究方向：图像识别技术;胡建雄（1993—）,男,在读博士研究生,研究方向：传染病防控; 殷李华和胡建雄为共同第一作者
基金资助:
广东省自然科学基金项目（2021A1515012578）

Research on recognition model of intestinal parasite eggs based on convolutional neural network

YIN Lihua^1,2, HU Jianxiong¹, FANG Yueyi³, RONG Zuhua⁴, HUANG Xubin⁴, HE Guanhao¹, JIANG Zhiying¹, XIAO Jianpeng⁴, LIU Tao¹, MA Wenjun¹

1. Department of Public Health and Preventive Medicine, School of Medicine, Jinan University, Guangzhou 510632, China;
2. School of Information Engineering, Guangzhou City Construction College;
3. Parasitic Disease Prevention and Control Institute, Guangdong Provincial Center for Disease Control and Prevention;
4. Guangdong Provincial Institute of Public Health, Guangdong Provincial Center for Disease Control and Prevention

Received:2023-10-20 Online:2023-12-20 Published:2024-02-05

摘要/Abstract

摘要： 目的构建肠道寄生虫卵的粪检显微图像数据集,建立一个深度学习模型,为肠道寄生虫疾病辅助诊断提供技术支撑。方法利用显微镜和数码相机采集12种肠道寄生虫虫卵显微图像,经预处理后对虫卵的类别和位置进行标注,形成粪检显微图像数据集。以掩膜区域卷积神经网络深度学习模型作为框架,对标定框回归、分类、掩膜进行训练,并评估其性能。结果构建的图像数据集共6 299张图片,涵盖了10 944个虫卵图像。经测试建立的深度学习模型总体识别准确率为90.20%,12种虫卵的准确率为58.65%（曼氏迭宫绦虫卵）~100.00%（蛲虫卵）。结论构建肠道寄生虫卵的显微图像数据集和利用卷积神经网络建立肠道寄生虫卵显微图像的识别模型可为寄生虫相关疾病的辅助诊断提供技术支撑。

关键词: 图像数据集, 肠道寄生虫, 肠道寄生虫卵, 深度学习

Abstract: Objective To construct a fecal microscopy image dataset of intestinal parasite eggs and establish a corresponding deep learning image recognition model, so as to provide technical support for the auxiliary diagnosis of intestinal parasitic diseases. Methods Microscopic images of 12 intestinal parasite eggs were collected using a microscope and a digital camera, pre-processed and labelled with the categories and locations of the eggs to form an image dataset. A masked region convolutional neural network deep learning model was used as a framework to train the bounding box regression, classification, and mask generation, and its performance was evaluated. Results The fecal microscopy image dataset was constructed with a total of 6 299 images, including 10 944 egg images. After testing, the deep learning model achieved an overall recognition accuracy of 90.20%. The recognition accuracy for the 12 types of eggs ranged from 58.65% （Spirometra mansoni egg） to 100.00% （Pinworm egg）. Conclusion Constructing a microscopy image dataset of intestinal parasite eggs and establishing an image recognition model using convolutional neural networks provide technical support for the auxiliary diagnosis of parasitic diseases.

Key words: Image dataset, Intestinal parasites, Intestinal parasite eggs, Deep learning

中图分类号:

R183.9

殷李华, 胡建雄, 方悦怡, 容祖华, 黄栩滨, 何冠豪, 江芷莹, 肖建鹏, 刘涛, 马文军. 基于卷积神经网络的肠道寄生虫虫卵识别模型研究[J]. 华南预防医学, 2023, 49(12): 1498-1503.

YIN Lihua, HU Jianxiong, FANG Yueyi, RONG Zuhua, HUANG Xubin, HE Guanhao, JIANG Zhiying, XIAO Jianpeng, LIU Tao, MA Wenjun. Research on recognition model of intestinal parasite eggs based on convolutional neural network[J]. South China Journal of Preventive Medicine, 2023, 49(12): 1498-1503.

参考文献

[1] Hailegebriel T.Prevalence of intestinal parasitic infections and associated risk factors among students at Dona Berber primary school,Bahir Dar,Ethiopia[J].BMC Infect Dis,2017,17(1):362.
[2] Yadav SS,Jadhav SM.Deep convolutional neural network based medical image classification for disease diagnosis[J].J Big Data,2019,6(1):1-18.
[3] Li Q,Li S,Liu X,et al.FecalNet:Automated detection of visible components in human feces using deep learning[J].Med Phys,2020,47(9):4212-4222.
[4] Cheng TC.General parasitology[M].Second Edition.Florida:Elsevier,2012.
[5] Bogitsh BJ,Carter CE,Oeltmann TN.Human parasitology[M].Fifth Edition.Massachusetts:Academic Press,2018.
[6] 詹希美. 人体寄生虫学[M].北京:人民卫生出版社,2001.
[7] Lowe DG.Object recognition from local scale-invariant features[C]//Proceedings of the seventh IEEE International Conference on Computer Vision. Kerkyra:IEEE,1999:1150-1157.
[8] Kanan C,Cottrell GW.Color-to-grayscale:Does the method matter in image recognition?[J]. PLoS One,2012,7(1):e29740.
[9] Russell BC,Torralba A,Murphy KP,et al.LabelMe:A database and web-based tool for image annotation[J].Int J Comput Vis,2008,77:157-173.
[10] Chen K,Wang J,Pang J,et al.MMDetection:Open mmlab detection toolbox and benchmark[J].ArXiv,2019:1906.07155.
[11] He K,Gkioxari G,Dollár P,et al.Mask r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision.Venice:IEEE,2017:2961-2969.
[12] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Nevada:IEEE,2016:770-778.
[13] LeCun Y,Bengio Y,Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[14] Gu J,Wang Z,Kuen J,et al.Recent advances in convolutional neural networks[J].Pattern Recognit,2018,77:354-377.
[15] Rivenson Y,Wang H,Wei Z,et al.Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning[J].Nat Biomed Eng,2019,3(6):466-477.
[16] Hamidinekoo A,Denton E,Rampun A,et al.Deep learning in mammography and breast histology,an overview and future trends[J].Med Image Anal,2018,47:45-67.
[17] Hashemzehi R,Mahdavi SJS,Kheirabadi M,et al.Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE[J].Biocybern Biomed Eng,2020,40(3):1225-1232.
[18] Ölmez E,Akdoğan V,Korkmaz M,et al.Automatic segmentation of meniscus in multispectral MRI using regions with convolutional neural network (R-CNN)[J].J Digit Imaging,2020,33(4):916-929.
[19] 张正龙. 显微粪便医学图像中寄生虫卵的自动识别及分类技术研究[D].成都:电子科技大学,2017.
[20] Lee CC,Huang PJ,Yeh YM,et al.Helminth egg analysis platform (HEAP):An opened platform for microscopic helminth egg identification and quantification based on the integration of deep learning architectures[J].J Microbiol Immunol Infect,2022,55(3):395-404.
[21] Burns BL,Rhoads DD,Misra A.The use of machine learning for image analysis artificial intelligence in clinical microbiology[J].J Clin Microbiol,2023,61(9):e02336-21.
[22] Oyibo P,Jujjavarapu S,Meulah B,et al.Schistoscope:An automated microscope with artificial intelligence for detection of Schistosoma haematobium eggs in resource-limited settings[J]. Micromachines(Basel),2022,13(5):643.

基于卷积神经网络的肠道寄生虫虫卵识别模型研究

Research on recognition model of intestinal parasite eggs based on convolutional neural network

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	张微, 方良好, 温韵菁, 廖鑫龙, 秦鹏哲, 甄若楠, 许建雄. 我国公众对猴痘知晓情况及相关影响因素研究[J]. 华南预防医学, 2023, 49(7): 818-823.
[2]	来学惠, 舒波, 孙映梅, 苏少冰, 李晓莹. 2011—2020年中山市HIV/AIDS时空聚集性分析[J]. 华南预防医学, 2023, 49(7): 869-871.
[3]	张国珍, 刘礼荣, 张泽文, 席苗苗, 戴江红. HIV阴性男男性行为人群肛门HPV 6/16型反复感染的影响因素研究[J]. 华南预防医学, 2023, 49(3): 310-314.
[4]	贾敏, 李红兵, 何微, 梁文革. 2005—2020年宝鸡市丙型肝炎流行特征和发病趋势预测[J]. 华南预防医学, 2022, 48(8): 974-977.
[5]	易萍, 周逢洽, 杨芳, 欧嘉怡, 王亚辉, 白菊. 2018—2021年新疆图木舒克市72 882例患者HBV感染情况[J]. 华南预防医学, 2022, 48(5): 636-638.
[6]	孙立昆, 郭伟杰, 史曼丽. 2014—2021年北京市石景山区乙肝流行病学特征分析[J]. 华南预防医学, 2022, 48(4): 522-524.
[7]	李一鹏, 林苑腾. 江门市15~24岁男男同性性传播HIV感染者预后分析[J]. 华南预防医学, 2021, 47(7): 920-922.
[8]	廖晓文, 岑玫喜, 陈华英, 赖辉兵. 云浮市2009—2018年丙型病毒性肝炎流行特征分析[J]. 华南预防医学, 2021, 47(1): 61-63.
[9]	陈国翠, 陈伟红, 卓菲, 杨贵清. 深圳市外来务工人群丙型肝炎基因型分布及感染危险因素研究[J]. 华南预防医学, 2021, 47(1): 64-66.
[10]	谈琦琪，吴德. 克雅氏病的研究进展[J]. 华南预防医学, 2016, 42(5): 495-497.
[11]	陈思秇，马文军. 手足口病发病的危险因素研究进展[J]. 华南预防医学, 2016, 42(3): 282-286.
[12]	李小玲，徐玲玲，邹霞，陈雯，凌莉. 美沙酮维持治疗综合服务评价指标体系的构建[J]. 华南预防医学, 2015, 41(3): 248-254.
[13]	黎健荣, 杨放, 林鹏, 李艳, 刘珺, 罗玉兰, 付笑冰, 徐慧芳. 广东省第四轮艾滋病综合防治示范区艾滋病防控需求分析[J]. 华南预防医学, 2021, 47(8): 964-967.
[14]	郭萌, 周康平, 蔡昆, 刘聪, 梅芳华, 郑武. 2018—2020年湖北省新治疗HIV感染者病毒载量水平及影响因素研究[J]. 华南预防医学, 2022, 48(1): 115-118.
[15]	刘腾, 高宪社, 郭欣, 王露婕, 魏惠琴, 魏明敏, 杨云云. 2014—2017年渭南市艾滋病哨点监测结果分析[J]. 华南预防医学, 2022, 48(1): 122-125.