|
|
|
|
|
|
| A Novel Classification Method of Foodborne Bacterial Species Based on Hyperspectral Microscopy Imaging Technology |
| KANG Rui1, 2, CHENG Ya-wen1, 2, ZHOU Ling-li1, 2, REN Ni1, 2* |
1. Jiangsu Academy of Agricultural Sciences, Nanjing 210031, China
2. Key Laboratory of Intelligent Agricultural Technology, Ministry of Agriculture and Rural Affairs, Nanjing 210031, China
|
|
|
|
|
Abstract The early and rapid detection of food-borne pathogens still challenges global food safety. Although routine tests such as selective agars served as the gold standard for decades, these methods are time consuming, often exceeding the best control time for foodborne bacterial outbreak. A hyperspectral microscopic imaging (HMI) technology coupled with an artificial intelligence algorithm was proposed to detect the common foodborne bacteria. The HMI technology has a natural trait in generating robust high-resolution spatial and spectral characterization at the cellular level. In this study, the Bi-directional long short-term memory (Bi-LSTM) was employed in the classification of Campylobacter jejuni (C. jejuni), Escherichia coli O157:H7 (E. coli), Salmonella Typhimurium (S. Typhimurium) based on morphological and spectral features extracted from single cell hypercubes. Compared with traditional linear discriminant analysis (LDA, 80.1%) and principal components analysis with support vector machine (PCA-SVM, 88.5%) classifiers, our proposed Bi-LSTM achieved the highest accuracy of 91.0% on the spectral dataset. Serious false-positive problems occurred in recognising E. coli and S. Typhimurium. However, with the involvement of morphological features, the discriminability of all classifiers was significantly improved. The proposed Bi-LSTM classifier achieved the highest accuracy of 98.1% based on the morphological-spectral feature dataset, while the LDA and PCA-SVM all achieved an accuracy of 95.3%. Our study demonstrated the applicability of HMI technology for foodborne bacterial cell characterization. Furthermore, with the advantage of Bi-LSTM in instantly processing the high-dimensional spatial-spectral features, the intelligent HMI shows great potential for rapid detection of foodborne pathogens.
|
|
Received: 2022-06-30
Accepted: 2022-09-14
|
|
|
|
Corresponding Authors:
REN Ni
E-mail: rn@jaas.ac.cn
|
|
[1] Li Yongqiang, Huang Yaling, Yang Jijun, et al. BMC Public Health, 2018, 18(1): 519.
[2] Li Weiwei, Pires Sara M, Liu Zhitao, et al. Food Control, 2020, 118: 107359.
[3] LIU Yu, LI Zeng-wei, DENG Zhi-peng, et al(刘 宇, 李增威, 邓志鹏, 等). Spectroscopy and Spectral Analysis (光谱学与光谱分析), 2021, 41(9): 6.
[4] Tang Yanjie, Kim Huisung, Singh K Atul, et al. PLOS ONE, 2014, 9(8): 105272.
[5] Windham William R, Yoon Seung-Chul, Ladely Scott R, et al. Journal of Food Protection, 2013, 76(7): 1129.
[6] Bhardwaj Neha, Bhardwaj Sanjeev K, Nayak Manoj K, et al. TrAC Trends in Analytical Chemistry, 2017, 97(1): 120.
[7] Kang Rui, Park Bosoon, Chen Kunjie. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 224: 117386.
[8] Kang Rui, Park Bosoon, Eady Matthew, et al. Sensors and Actuators B: Chemical, 2020, 309: 127789.
[9] Zimbro M J, Power D A. DIFCO and BBL Manual: Manual of Microbiological Culture Media, 2nd ed. Becton Dickinson & Company, Sparks, MD, USA, 2009.
[10] Eady Matthew, Setia Gayatri, Park Bosoon. Talanta, 2019, 195: 313.
[11] Kang Rui, Park Bosoon, Eady Matthew, et al. Applied Microbiology and Biotechnology, 2020, 104(7): 3157.
[12] Kang Rui, Park Bosoon, Ouyang Qin, et al. Food Control, 2021, 130: 108379.
|
| [1] |
WANG Yu-ye1, 2, LI Hai-bin1, 2, JIANG Bo-zhou1, 2, GE Mei-lan1, 2, CHEN Tu-nan3, FENG Hua3, WU Bin4ZHU Jun-feng4, XU De-gang1, 2, YAO Jian-quan1, 2. Terahertz Spectroscopic Early Diagnosis of Cerebral Ischemia in Rats[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 788-794. |
| [2] |
XUE Wen-dong1*, CHEN Ben-neng1, HONG De-ming1, YANG Zhen-hai1, LIU Guo-kun2. Research on Raman Spectrum Recognition Method Based on Improved
Reverse Matching[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 753-759. |
| [3] |
LIU Shi-jie1, ZHU Yao-di1, 2, LI Miao-yun1, 2*, ZHAO Gai-ming1, 2, ZHAO Li-jun1, 2, MA Yang-yang1, 2, WANG Na1. Raman Spectroscopic Characteristic Structure Analysis and Rapid Identification of Food-Borne Pathogen Spores Based on SERS Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2774-2780. |
| [4] |
LIU Yan-yan1, TAO Ning-ping1, 2, 3, WANG Xi-chang1, 2, 3, LU Ying1, 2, 3*，XU Chang-hua1, 2, 3*. Integrated Detection of Foodborne Pathogens by In-Situ Infrared Spectroscopy Based on ZnSe Film Transmission Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 419-424. |
| [5] |
HU Qi-feng, CAI Jian. Research of Terahertz Time-Domain Spectral Identification Based on Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 94-99. |
| [6] |
LAI Wen-hao1, ZHOU Meng-ran1*, LI Da-tong1, WANG Ya2, HU Feng1, ZHAO Shun3, GU Yu-lin1. Application of Unsupervised Learning AE and MVO-DBSCAN Combined with LIF in Mine Water Inrush Recognition[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(08): 2437-2442. |
| [7] |
GAO Bin1, ZHAO Peng-fei1, LU Yu-xin1, FAN Ya1, ZHOU Lin-hua1*, QIAN Jun2, LIU Lin-na2, ZHAO Si-yan2, KONG Zhi-feng3. Study on Recognition and Classificationof Blood Fluorescence Spectrum with BP Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(10): 3136-3143. |
| [8] |
YANG Shuai1, ZUO Jian1*, LIU Shang-jian2*, ZHANG Cun-lin1 . Application of Terahertz Spectroscopy in the Detection of Chinese Medicine Processed Drugs of Rhubarb[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(12): 3870-3874. |
| [9] |
ZENG Ya-ling, JIANG Long, CAI Xiao-yu, LI Yu* . Identification of the Characteristic Vibrations for 16 PAHs Based on Raman Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(11): 2999-3004. |
| [10] |
GUO Shu-xia1, ZHANG Feng-ling1, GAO Pan1, ZENG Yong-ming2, CHEN Hong-ju2, LIU Guo-kun2, WANG Lei1* . SERS Spectrum Recognition for Malachite Green Real-Time Detection in Aquaculture Used Seawater [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(05): 1284-1288. |
| [11] |
CHEN Bing1, 2, WANG Fang-yong1, HAN Huan-yong1, LIU Zheng1, XIAO Chun-hua2, ZOU Nan2 . Research of Influence Factors on Spectral Recognition for Cotton Leaf Infected by Verticillium wilt[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(03): 795-800. |
| [12] |
HE Ting, SHEN Jing-ling* . Applications of Terahertz Spectroscopy in Illicit Drugs Detection [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(09): 2348-2353. |
| [13] |
CAO Hui1，ZHOU Yan2* . Multi-Population Elitists Shared Genetic Algorithm for Outlier Detection of Spectroscopy Analysis [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2011, 31(07): 1847-1851. |
| [14] |
LIU Zhong-tian, QIU Kuan-min. A Method for Auto-Recognizing the Stars Based on Spectral Feature [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(01): 274-277. |
| [15] |
CHEN Yan-jiang, LIU Yan-yan, ZHAO Guo-zhong, WANG Wei-ning, LI Fu-li*. Chinese Traditional Medicine Recognition by Support Vector Machine (SVM) Terahertz Spectrum [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(09): 2346-2350. |
|
|
|
|
