利用基于深度学习的分类器快速计数大肠菌群和大肠埃希氏菌

IF 1.9 4区 农林科学 Q4 BIOTECHNOLOGY & APPLIED MICROBIOLOGY Journal of Food Safety Pub Date : 2024-08-06 DOI:10.1111/jfs.13158
Rina Wakabayashi, Atsuko Aoyanagi, Tatsuya Tominaga
{"title":"利用基于深度学习的分类器快速计数大肠菌群和大肠埃希氏菌","authors":"Rina Wakabayashi,&nbsp;Atsuko Aoyanagi,&nbsp;Tatsuya Tominaga","doi":"10.1111/jfs.13158","DOIUrl":null,"url":null,"abstract":"<p>To ensure that food has been handled hygienically, manufacturers routinely examine the numbers of indicator bacteria, such as coliforms and <i>Escherichia coli</i>. Using the deep-learning algorithm YOLO, we developed a classifier that automatically counts the number of coliforms (red colonies) and <i>E. coli</i> (blue colonies) on a chromogenic agar plate. Using <i>Citrobacter freundii</i> IAM 12471<sup>T</sup> and <i>E. coli</i> NBRC 3301, we trained our YOLO-based classifier with images of Petri dishes grown with each strain alone (10 images) and/or with a mixture of both strains (5 images). When the performance of the classifier was evaluated using 83 images, the accuracy rates for coliforms and <i>E. coli</i> reached 99.4% and 99.5%, respectively. We then investigated whether this classifier could detect other, non-trained coliform species (22 species) and <i>E. coli</i> strains (13 strains). The accuracy rates for coliforms and <i>E. coli</i> were 98.7% (90 Petri dishes) and 94.1% (46 Petri dishes), respectively. Furthermore, we verified the practical feasibility of the developed classifier using 38 meats (chicken, pork, and beef). The accuracy rates for coliforms and <i>E. coli</i> in meat isolates were 98.8% (80 Petri dishes) and 93.8% (35 Petri dishes), respectively. The time required to count coliforms/<i>E. coli</i> on a single plate was ~70 ms. This novel method should enable users to rapidly quantify coliforms/<i>E. coli</i> without relying on a human inspector's color vision, leading to improved assurance of food safety.</p>","PeriodicalId":15814,"journal":{"name":"Journal of Food Safety","volume":"44 4","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rapid counting of coliforms and Escherichia coli by deep learning-based classifier\",\"authors\":\"Rina Wakabayashi,&nbsp;Atsuko Aoyanagi,&nbsp;Tatsuya Tominaga\",\"doi\":\"10.1111/jfs.13158\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>To ensure that food has been handled hygienically, manufacturers routinely examine the numbers of indicator bacteria, such as coliforms and <i>Escherichia coli</i>. Using the deep-learning algorithm YOLO, we developed a classifier that automatically counts the number of coliforms (red colonies) and <i>E. coli</i> (blue colonies) on a chromogenic agar plate. Using <i>Citrobacter freundii</i> IAM 12471<sup>T</sup> and <i>E. coli</i> NBRC 3301, we trained our YOLO-based classifier with images of Petri dishes grown with each strain alone (10 images) and/or with a mixture of both strains (5 images). When the performance of the classifier was evaluated using 83 images, the accuracy rates for coliforms and <i>E. coli</i> reached 99.4% and 99.5%, respectively. We then investigated whether this classifier could detect other, non-trained coliform species (22 species) and <i>E. coli</i> strains (13 strains). The accuracy rates for coliforms and <i>E. coli</i> were 98.7% (90 Petri dishes) and 94.1% (46 Petri dishes), respectively. Furthermore, we verified the practical feasibility of the developed classifier using 38 meats (chicken, pork, and beef). The accuracy rates for coliforms and <i>E. coli</i> in meat isolates were 98.8% (80 Petri dishes) and 93.8% (35 Petri dishes), respectively. The time required to count coliforms/<i>E. coli</i> on a single plate was ~70 ms. This novel method should enable users to rapidly quantify coliforms/<i>E. coli</i> without relying on a human inspector's color vision, leading to improved assurance of food safety.</p>\",\"PeriodicalId\":15814,\"journal\":{\"name\":\"Journal of Food Safety\",\"volume\":\"44 4\",\"pages\":\"\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Food Safety\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/jfs.13158\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Food Safety","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jfs.13158","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

为确保食品的卫生处理,生产商会定期检查大肠菌群和大肠埃希氏菌等指示菌的数量。利用深度学习算法 YOLO,我们开发了一种分类器,可以自动计算显色琼脂平板上大肠菌群(红色菌落)和大肠杆菌(蓝色菌落)的数量。我们使用自由柠檬酸杆菌 IAM 12471T 和大肠杆菌 NBRC 3301,用每种菌株单独生长的培养皿图像(10 张)和/或两种菌株混合生长的培养皿图像(5 张)来训练基于 YOLO 的分类器。在使用 83 幅图像对分类器的性能进行评估时,大肠菌群和大肠杆菌的准确率分别达到了 99.4% 和 99.5%。随后,我们研究了该分类器能否检测出其他未经训练的大肠菌群(22 种)和大肠杆菌菌株(13 种)。大肠菌群和大肠杆菌的准确率分别为 98.7%(90 个培养皿)和 94.1%(46 个培养皿)。此外,我们还利用 38 种肉类(鸡肉、猪肉和牛肉)验证了所开发分类器的实际可行性。肉类分离物中大肠菌群和大肠埃希氏菌的准确率分别为 98.8%(80 个培养皿)和 93.8%(35 个培养皿)。在一个培养皿中计数大肠菌群/大肠杆菌所需的时间约为 70 毫秒。这种新方法可使用户无需依赖人类检验员的色觉就能快速量化大肠菌群/大肠杆菌,从而提高食品安全保障。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Rapid counting of coliforms and Escherichia coli by deep learning-based classifier

To ensure that food has been handled hygienically, manufacturers routinely examine the numbers of indicator bacteria, such as coliforms and Escherichia coli. Using the deep-learning algorithm YOLO, we developed a classifier that automatically counts the number of coliforms (red colonies) and E. coli (blue colonies) on a chromogenic agar plate. Using Citrobacter freundii IAM 12471T and E. coli NBRC 3301, we trained our YOLO-based classifier with images of Petri dishes grown with each strain alone (10 images) and/or with a mixture of both strains (5 images). When the performance of the classifier was evaluated using 83 images, the accuracy rates for coliforms and E. coli reached 99.4% and 99.5%, respectively. We then investigated whether this classifier could detect other, non-trained coliform species (22 species) and E. coli strains (13 strains). The accuracy rates for coliforms and E. coli were 98.7% (90 Petri dishes) and 94.1% (46 Petri dishes), respectively. Furthermore, we verified the practical feasibility of the developed classifier using 38 meats (chicken, pork, and beef). The accuracy rates for coliforms and E. coli in meat isolates were 98.8% (80 Petri dishes) and 93.8% (35 Petri dishes), respectively. The time required to count coliforms/E. coli on a single plate was ~70 ms. This novel method should enable users to rapidly quantify coliforms/E. coli without relying on a human inspector's color vision, leading to improved assurance of food safety.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Food Safety
Journal of Food Safety 工程技术-生物工程与应用微生物
CiteScore
5.30
自引率
0.00%
发文量
69
审稿时长
1 months
期刊介绍: The Journal of Food Safety emphasizes mechanistic studies involving inhibition, injury, and metabolism of food poisoning microorganisms, as well as the regulation of growth and toxin production in both model systems and complex food substrates. It also focuses on pathogens which cause food-borne illness, helping readers understand the factors affecting the initial detection of parasites, their development, transmission, and methods of control and destruction.
期刊最新文献
Cold Plasma and Pulsed Light Inactivates Escherichia coli O157: H7 in Romaine Lettuce and Preserves Produce Quality Ginger Essential Oil Exerts Antibacterial Activity Against Shewanella putrefaciens by Disrupting Cell Structure and Resisting Biofilm Investigation of the Storage Temperature Effect on Phthalate Migration Potential in Vacuum-Packed Fish Fillets Issue Information Epiphytic, Attached, and Internal Escherichia coli O157:H7 Subpopulations Associating With Romaine Lettuce Are Strain-Dependent and Affected by Relative Humidity and Pre- and Postharvest Plant State
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1