[Establishment and application of an artificial intelligence-assisted platform for detection of parasite eggs].

Q3 Medicine

中国血吸虫病防治杂志 Pub Date : 2024-08-27 DOI:10.16250/j.32.1374.2024094

H Zhu, Y Li, D Zhu, Y Wang, J Zhang, S Chen, X Ma, H Wang, H Li, J Li

{"title":"[Establishment and application of an artificial intelligence-assisted platform for detection of parasite eggs].","authors":"H Zhu, Y Li, D Zhu, Y Wang, J Zhang, S Chen, X Ma, H Wang, H Li, J Li","doi":"10.16250/j.32.1374.2024094","DOIUrl":null,"url":null,"abstract":"Objective: To establish an artificial intelligence (AI)-assisted platform for detection of parasite eggs, and to evaluate its detection efficiency and accuracy, so as to provide technical supports for elimination of parasitic diseases.Methods: A total of 1 003 slides of Enterobius vermicularis, horkworm, Trichuris trichiura, Clonorchis sinensis, Taenia, Ascaris lumbricoides, Schistosoma japonicum, Paragonimus westermani and Fasciolopsis buski eggs were collected, and converted into digital images with an automatated scanning microscope to create a dataset. Based on the Object Detection platform on the Baidu Easy DL model, an AI-assisted platform for detection of parasite eggs was created through procedures of uploading, labeling, training, evaluation and optimization. Then, 70% of the datasets were randomly selected for model training, and the precision, recall and average accuracy were calculated to evaluate the effectiveness of platform for recognition of parasite eggs. In addition, the platform was deployed on the computer and smart phone terminals for use.Results: An AI-assisted platform for detection of parasite eggs was successfully created. If the platform was deployed using the public cloud application programming interface (API), the average accuracy, precision and recall of the platform were 93.42%, 92.55% and 89.32% for recognition of parasite eggs. If the platform was deployed using the offline software development kit (SDK), the average accuracy, precision and recall of the platform were 92.97%, 94.78% and 87.63% for recognition of parasite eggs. In addition, the precision of the platform was 97.00% and 96.23% for identification of Taenia and C. sinensis eggs, respectively.Conclusions: The AI-assisted platform for detection of parasite eggs has been successfully created, which is high in the accuracy for recognition of parasite eggs and convenient in use. This platform may provide a powerful technical support for parasitic disease diagnosis.","PeriodicalId":38874,"journal":{"name":"中国血吸虫病防治杂志","volume":"36 6","pages":"643-648"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国血吸虫病防治杂志","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.16250/j.32.1374.2024094","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}

引用次数: 0

Abstract

Objective: To establish an artificial intelligence (AI)-assisted platform for detection of parasite eggs, and to evaluate its detection efficiency and accuracy, so as to provide technical supports for elimination of parasitic diseases.

Methods: A total of 1 003 slides of Enterobius vermicularis, horkworm, Trichuris trichiura, Clonorchis sinensis, Taenia, Ascaris lumbricoides, Schistosoma japonicum, Paragonimus westermani and Fasciolopsis buski eggs were collected, and converted into digital images with an automatated scanning microscope to create a dataset. Based on the Object Detection platform on the Baidu Easy DL model, an AI-assisted platform for detection of parasite eggs was created through procedures of uploading, labeling, training, evaluation and optimization. Then, 70% of the datasets were randomly selected for model training, and the precision, recall and average accuracy were calculated to evaluate the effectiveness of platform for recognition of parasite eggs. In addition, the platform was deployed on the computer and smart phone terminals for use.

Results: An AI-assisted platform for detection of parasite eggs was successfully created. If the platform was deployed using the public cloud application programming interface (API), the average accuracy, precision and recall of the platform were 93.42%, 92.55% and 89.32% for recognition of parasite eggs. If the platform was deployed using the offline software development kit (SDK), the average accuracy, precision and recall of the platform were 92.97%, 94.78% and 87.63% for recognition of parasite eggs. In addition, the precision of the platform was 97.00% and 96.23% for identification of Taenia and C. sinensis eggs, respectively.

Conclusions: The AI-assisted platform for detection of parasite eggs has been successfully created, which is high in the accuracy for recognition of parasite eggs and convenient in use. This platform may provide a powerful technical support for parasitic disease diagnosis.

查看原文本刊更多论文

[人工智能辅助虫卵检测平台的建立与应用]。

目的：建立人工智能辅助的虫卵检测平台，并对其检测效率和准确性进行评估，为消除寄生虫病提供技术支持。方法：收集蛭肠虫、蛔虫、毛滴虫、华支睾吸虫、带绦虫、蛔虫、日本血吸虫、威氏并殖吸虫、布氏片形虫虫卵1 003份载玻片，利用自动扫描显微镜将载玻片转换成数字图像，建立数据集。以百度Easy DL模型上的Object Detection平台为基础，通过上传、标注、训练、评估、优化等流程，构建了一个人工智能辅助的虫卵检测平台。然后，随机抽取70%的数据集进行模型训练，计算准确率、召回率和平均准确率，评价平台对寄生虫卵识别的有效性。此外，该平台已部署在计算机和智能手机终端上使用。结果：成功建立了人工智能辅助虫卵检测平台。如果使用公有云应用程序编程接口（API）部署，平台对寄生虫卵的识别平均正确率、精密度和召回率分别为93.42%、92.55%和89.32%。如果使用离线软件开发工具包（SDK）部署，平台对寄生虫卵的识别平均正确率、精密度和召回率分别为92.97%、94.78%和87.63%。此外，该平台对带绦虫卵和中华棘球绦虫卵的鉴定精度分别为97.00%和96.23%。结论：成功构建了人工智能辅助虫卵检测平台，虫卵识别准确率高，使用方便。该平台可为寄生虫病的诊断提供有力的技术支持。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

中国血吸虫病防治杂志 Medicine-Medicine (all)

CiteScore

1.30

自引率

0.00%

发文量

7021

期刊介绍： Chinese Journal of Schistosomiasis Control (ISSN: 1005-6661, CN: 32-1374/R), founded in 1989, is a technical and scientific journal under the supervision of Jiangsu Provincial Health Commission and organised by Jiangsu Institute of Schistosomiasis Control. It is a scientific and technical journal under the supervision of Jiangsu Provincial Health Commission and sponsored by Jiangsu Institute of Schistosomiasis Prevention and Control. The journal carries out the policy of prevention-oriented, control-oriented, nationwide and grassroots, adheres to the tenet of scientific research service for the prevention and treatment of schistosomiasis and other parasitic diseases, and mainly publishes academic papers reflecting the latest achievements and dynamics of prevention and treatment of schistosomiasis and other parasitic diseases, scientific research and management, etc. The main columns are Guest Contributions, Experts‘ Commentary, Experts’ Perspectives, Experts' Forums, Theses, Prevention and Treatment Research, Experimental Research, The main columns include Guest Contributions, Expert Commentaries, Expert Perspectives, Expert Forums, Treatises, Prevention and Control Studies, Experimental Studies, Clinical Studies, Prevention and Control Experiences, Prevention and Control Management, Reviews, Case Reports, and Information, etc. The journal is a useful reference material for the professional and technical personnel of schistosomiasis and parasitic disease prevention and control research, management workers, and teachers and students of medical schools. 　　 The journal is now included in important domestic databases, such as Chinese Core List (8th edition), China Science Citation Database (Core Edition), China Science and Technology Core Journals (Statistical Source Journals), and is also included in MEDLINE/PubMed, Scopus, EBSCO, Chemical Abstract, Embase, Zoological Record, JSTChina, Ulrichsweb, Western Pacific Region Index Medicus, CABI and other international authoritative databases.