Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses
Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting <i>Escherichia...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/6/2213 |
id |
doaj-cd78d2b34340420fb704ee52a9171d18 |
---|---|
record_format |
Article |
spelling |
doaj-cd78d2b34340420fb704ee52a9171d182021-03-23T00:02:31ZengMDPI AGSensors1424-82202021-03-01212213221310.3390/s21062213Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant AnalysesAhyeong Lee0Saetbyeol Park1Jinyoung Yoo2Jungsook Kang3Jongguk Lim4Youngwook Seo5Balgeum Kim6Giyoung Kim7Rural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaRural Development Administration, 310 Nongsaengmyeng-ro, Deokjin-gu, Jeonju 54875, KoreaBiofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting <i>Escherichia coli </i>(<i>E. coli</i>) and <i>Salmonella typhimurium</i> (<i>S. typhimurium</i>) on the surface of food processing facilities by using fluorescence hyperspectral imaging. <i>E. coli</i> and <i>S. typhimurium</i> were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, <i>k</i>-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for <i>E. coli </i>(1–4 log CFU·cm<sup>−2</sup>) and <i>S. typhimurium </i>(1–6 log CFU·cm<sup>−2</sup>) were over 90% for most machine learning models used, and the highest performances were generally obtained from the <i>k</i>-nearest neighbor (<i>k</i>-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images.https://www.mdpi.com/1424-8220/21/6/2213<i>E. coli</i><i>S</i> <i>. typhimuriu</i> <i>m</i>biofilmhyperspectral imagingdiscriminant analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ahyeong Lee Saetbyeol Park Jinyoung Yoo Jungsook Kang Jongguk Lim Youngwook Seo Balgeum Kim Giyoung Kim |
spellingShingle |
Ahyeong Lee Saetbyeol Park Jinyoung Yoo Jungsook Kang Jongguk Lim Youngwook Seo Balgeum Kim Giyoung Kim Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses Sensors <i>E. coli</i> <i>S</i> <i>. typhimuriu</i> <i>m</i> biofilm hyperspectral imaging discriminant analysis |
author_facet |
Ahyeong Lee Saetbyeol Park Jinyoung Yoo Jungsook Kang Jongguk Lim Youngwook Seo Balgeum Kim Giyoung Kim |
author_sort |
Ahyeong Lee |
title |
Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses |
title_short |
Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses |
title_full |
Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses |
title_fullStr |
Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses |
title_full_unstemmed |
Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses |
title_sort |
detecting bacterial biofilms using fluorescence hyperspectral imaging and various discriminant analyses |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-03-01 |
description |
Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting <i>Escherichia coli </i>(<i>E. coli</i>) and <i>Salmonella typhimurium</i> (<i>S. typhimurium</i>) on the surface of food processing facilities by using fluorescence hyperspectral imaging. <i>E. coli</i> and <i>S. typhimurium</i> were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, <i>k</i>-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for <i>E. coli </i>(1–4 log CFU·cm<sup>−2</sup>) and <i>S. typhimurium </i>(1–6 log CFU·cm<sup>−2</sup>) were over 90% for most machine learning models used, and the highest performances were generally obtained from the <i>k</i>-nearest neighbor (<i>k</i>-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images. |
topic |
<i>E. coli</i> <i>S</i> <i>. typhimuriu</i> <i>m</i> biofilm hyperspectral imaging discriminant analysis |
url |
https://www.mdpi.com/1424-8220/21/6/2213 |
work_keys_str_mv |
AT ahyeonglee detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT saetbyeolpark detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT jinyoungyoo detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT jungsookkang detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT jongguklim detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT youngwookseo detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT balgeumkim detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses AT giyoungkim detectingbacterialbiofilmsusingfluorescencehyperspectralimagingandvariousdiscriminantanalyses |
_version_ |
1724207055896576000 |