An Enhanced Classification of Bacteria Pathogen on Microscopy Images Using Deep Learning

S. A. Akbar, K. Ghazali, H. Hasan, Z. Mohamed, W. S. Aji
{"title":"An Enhanced Classification of Bacteria Pathogen on Microscopy Images Using Deep Learning","authors":"S. A. Akbar, K. Ghazali, H. Hasan, Z. Mohamed, W. S. Aji","doi":"10.1109/ISRITI54043.2021.9702809","DOIUrl":null,"url":null,"abstract":"Classification of bacteria pathogens has significant importance issues in the clinical microbiology field. The taxonomy identification of bacteria is usually recognized through microscopy imaging. The classical procedure has the lacks detection and a high misclassification rate. Recently, computer-aided detection is an applied deep learning approach that has been growing to improve classification quality. This study proposed an enhanced classification technique to recognize the bacterial pathogen images. The DensNet201 pre-trained CNN architecture has been used for deep feature extraction and classification. In addition, the transfer learning with the freeze layer technique applied can enhance the accuracy performance and reduce the false-positive rate. The experimental result can improve state-of-the-art decision-making.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISRITI54043.2021.9702809","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

Classification of bacteria pathogens has significant importance issues in the clinical microbiology field. The taxonomy identification of bacteria is usually recognized through microscopy imaging. The classical procedure has the lacks detection and a high misclassification rate. Recently, computer-aided detection is an applied deep learning approach that has been growing to improve classification quality. This study proposed an enhanced classification technique to recognize the bacterial pathogen images. The DensNet201 pre-trained CNN architecture has been used for deep feature extraction and classification. In addition, the transfer learning with the freeze layer technique applied can enhance the accuracy performance and reduce the false-positive rate. The experimental result can improve state-of-the-art decision-making.
利用深度学习增强显微镜图像上细菌病原体的分类
病原菌的分类是临床微生物学领域一个非常重要的问题。细菌的分类鉴定通常是通过显微镜成像来识别的。经典方法存在检出率低、误分类率高的问题。近年来,计算机辅助检测作为一种应用深度学习的方法不断发展,以提高分类质量。本研究提出了一种增强分类技术来识别细菌病原体图像。DensNet201预训练CNN架构被用于深度特征提取和分类。此外,结合冻结层技术的迁移学习可以提高准确率,降低误报率。实验结果可以提高决策水平。
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
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信