DOI QR코드

DOI QR Code

Detection of E.coli biofilms with hyperspectral imaging and machine learning techniques

  • Lee, Ahyeong (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Seo, Youngwook (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Lim, Jongguk (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Park, Saetbyeol (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Yoo, Jinyoung (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Kim, Balgeum (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Kim, Giyoung (Department of Agricultural Engineering, National Institute of Agricultural Sciences, Rural Development Administration)
  • 투고 : 2020.04.01
  • 심사 : 2020.08.12
  • 발행 : 2020.09.01

초록

Bacteria are a very common cause of food poisoning. Moreover, bacteria form biofilms to protect themselves from harsh environments. Conventional detection methods for foodborne bacterial pathogens including the plate count method, enzyme-linked immunosorbent assays (ELISA), and polymerase chain reaction (PCR) assays require a lot of time and effort. Hyperspectral imaging has been used for food safety because of its non-destructive and real-time detection capability. This study assessed the feasibility of using hyperspectral imaging and machine learning techniques to detect biofilms formed by Escherichia coli. E. coli was cultured on a high-density polyethylene (HDPE) coupon, which is a main material of food processing facilities. Hyperspectral fluorescence images were acquired from 420 to 730 nm and analyzed by a single wavelength method and machine learning techniques to determine whether an E. coli culture was present. The prediction accuracy of a biofilm by the single wavelength method was 84.69%. The prediction accuracy by the machine learning techniques were 87.49, 91.16, 86.61, and 86.80% for decision tree (DT), k-nearest neighbor (k-NN), linear discriminant analysis (LDA), and partial least squares-discriminant analysis (PLS-DA), respectively. This result shows the possibility of using machine learning techniques, especially the k-NN model, to effectively detect bacterial pathogens and confirm food poisoning through hyperspectral images.

참고문헌

  1. Beuchat LR. 2002. Ecological factors influencing survival and growth of human pathogens on raw fruits and vegetables. Microbes and infection 4:413-423. https://doi.org/10.1016/S1286-4579(02)01555-1
  2. CDC (Centers of Disease Control and Prevention). 2018. Centers for Disease Control and Prevention. Accessed in http://www.cdc.gov/foodsafety/foodborne-germs.html on 26 March 2020.
  3. Cramer M. 2012. Biofilms: Impact on the food industry. Food Safety Magazine 18:20-23.
  4. Donlan RM. 2002. Biofilms: Microbial life on surfaces. Emerging Infectious Diseases 8:881-890. https://doi.org/10.3201/eid0809.020063
  5. Huang L, Zhao J, Chen Q, Zhang Y. 2013. Rapid detection of total viable count (TVC) in pork meat by hyperspectral imaging. Food Research International 54:821-828. https://doi.org/10.1016/j.foodres.2013.08.011
  6. Jun W, Kim MS, Cho BK, Millner PD, Chao K, Chan DE. 2010. Microbial biofilm detection on food contact surfaces by macro-scale fluorescence imaging. Journal of food engineering 99:314-322. https://doi.org/10.1016/j.jfoodeng.2010.03.005
  7. Jun W, Kim MS, Lee KJ, Millner P, Chao K. 2009. Assessment of bacterial biofilm on stainless steel by hyperspectral fluorescence imaging. Sensing and Instrumentation for Food Quality and Safety 3:41-48. https://doi.org/10.1007/s11694-009-9069-1
  8. Lim JG, Kim GY, Mo CY, Kim MS, Chao K, Qin J, Fu X, Baek IS, Cho BK. 2016. Detection of melamine in milk powders using near-infrared hyperspectral imaging combined with regression coefficient of partial least square regression model. Talanta 151:183-191. https://doi.org/10.1016/j.talanta.2016.01.035
  9. Lim JG, Kim MS, Baek IS, Mo CY, Lee HY, Kang SW, Lee KJ, Kim GY. 2013. Prediction of the melamine particle concentration in milk powder using hyperspectral reflectance imaging and partial least square regression model. Food Engineering Progress 17:1-11. [in Korean]
  10. Peng Y, Zhang J, Wang W, Li Y, Wu J, Huang H, Gao X, Jiang W. 2011. Potential prediction of the microbial spoilage of beef using spatially resolved hyperspectral scattering profiles. Journal of Food Engineering 102:163-169. https://doi.org/10.1016/j.jfoodeng.2010.08.014
  11. Poulsen LV. 1999. Microbial biofilm in food processing. LWT-Food Science and Technology 32:321-326. https://doi.org/10.1006/fstl.1999.0561
  12. Rahman A, Park ES, Bae HJ, Cho BK. 2018. Hyperspectral imaging technique to evaluate the firmness and the sweetness index of tomatoes. Korean Journal of Agricultural Science 45:823-837.
  13. Wu D, Sun DW. 2013. Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A review - Part I: Fundamentals. Innovative Food Science & Emerging Technologies 19:1-14. https://doi.org/10.1016/j.ifset.2013.04.014
  14. Yoon SC, Lawrence KC, Siragusa GR, Line JE, Park B, Feldner PW. 2009. Hyperspectral reflectance imaging for detecting a foodborne pathogen: Campylobacter. Transactions of the ASABE 52:651-662. https://doi.org/10.13031/2013.26814
  15. Zhao X, Zhao F, Wang J, Zhong N. 2017. Biofilm formation and control strategies of foodborne pathogens: Food safety perspectives. Royal Society of Chemistry advances 7:36670-36683.
  16. Zhu F, Yao H, Hruska Z, Kincaid R, Brown R, Bhatnagar D, Cleveland T. 2016. Integration of fluorescence and reflectance visible near-infrared (VNIR) hyperspectral images for detection of aflatoxins in corn kernels. Transactions of the ASABE 59:785-794. https://doi.org/10.13031/trans.59.11365