Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion
Abstract
1. Introduction
2. Materials and Methods
2.1. Data Acquisition
2.1.1. Bacterial Strains and Sample Preparation
2.1.2. Hyperspectral Microscopy and Data Consistency Check
2.2. Data Preprocessing and Spectral Feature Engineering
2.3. Machine Learning Models for Spectral Branch
2.3.1. Model Architectures
2.3.2. Model Training
2.4. Multimodal Spectral-Spatial Fusion
2.4.1. CNN for Image Branch
2.4.2. Fusion of Spectral and Image-Based Prediction Outputs
2.5. Model Evaluation and Performance Metrics
3. Results
3.1. Comparision of Hyperspectral Data of Salmonella Serovars
3.2. Selection of the Optimal Classification Model Within the Spectral Branch
3.2.1. Influences of Manual Feature Selection and Data-Driven Feature Extraction
3.2.2. Performance Comparison of Machine Learning Models Using Spectral Features
3.3. Multimodal Classification by Fusion of Spectral and Image-Based Features
4. Discussion
4.1. Hyperspectral Microscopy Captures Intrinsic Differences Among Salmonella Serovars
4.2. Data-Driven Feature Extraction Improves Spectral Data Representation
4.3. Multimodal Fusion of Spectral and Image-Based Features Enhances Classification and Mitigates Overfitting
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
PCA | Principle Component Analysis |
MLP | Multilayer Perceptron |
CNN | Convolutional Neural Network |
FDA | Food and Drug Administration |
BAM | Bacteriological Analytical Manual |
ROI | Regions of Interest |
RF | Random Forest |
SVM | Support Vector Machine |
k-NN | k-Nearest Neighbors |
DI | De-Ionized |
FOV | Field of View |
SNV | Standard Normal Variate |
PC | Principal Component |
ReLU | Rectified Linear Unit |
TP | True Positive |
TN | True Negative |
FP | False Positive |
FN | False Negative |
STD | Standard Deviation |
References
- Bell, R.L.; Jarvis, K.G.; Ottesen, A.R.; McFarland, M.A.; Brown, E.W. Recent and emerging innovations in Salmonella detection: A food and environmental perspective. Microb. Biotechnol. 2016, 9, 279–292. [Google Scholar] [CrossRef]
- Centers for Disease Control and Prevention (CDC). About Salmonella Infection. Available online: https://www.cdc.gov/salmonella/about/index.html (accessed on 25 June 2025).
- Daquigan, N.; Grim, C.J.; White, J.R.; Hanes, D.E.; Jarvis, K.G. Early recovery of Salmonella from food using a 6-hour non-selective pre-enrichment and reformulation of tetrathionate broth. Front. Microbiol. 2016, 7, 2103. [Google Scholar] [CrossRef]
- Andrews, W.H.; Wang, H.; Jacobson, A.; Hammack, T. Bacteriological Analytical Manual (BAM) Chapter 5: Salmonella. Available online: https://www.fda.gov/food/laboratory-methods-food/bam-chapter-5-salmonella (accessed on 25 June 2025).
- Patel, A.; Wolfram, A.; Desin, T.S. Advancements in detection methods for Salmonella in Food: A comprehensive review. Pathogens 2024, 13, 1075. [Google Scholar] [CrossRef]
- Ranieri, M.L.; Shi, C.; Moreno Switt, A.I.; den Bakker, H.C.; Wiedmann, M. Comparison of typing methods with a new procedure based on sequence characterization for Salmonella serovar prediction. J. Clin. Microbiol. 2013, 51, 1786–1797. [Google Scholar] [CrossRef] [PubMed]
- Herrera-León, S.; Ramiro, R.; Arroyo, M.; Díez, R.; Usera, M.A.; Echeita, M.A. Blind comparison of traditional serotyping with three multiplex PCRs for the identification of Salmonella serotypes. Res. Microbiol. 2007, 158, 122–127. [Google Scholar] [CrossRef] [PubMed]
- Grinevich, D.; Harden, L.; Thakur, S.; Callahan, B. Serovar-level identification of bacterial foodborne pathogens from full-length 16S rRNA gene sequencing. mSystems 2024, 9, e0075723. [Google Scholar] [CrossRef] [PubMed]
- Bhunia, A.K.; Singh, A.K.; Parker, K.; Applegate, B.M. Petri-plate, bacteria, and laser optical scattering sensor. Front. Cell. Infect. Microbiol. 2022, 12, 1087074. [Google Scholar] [CrossRef]
- Wang, P.; Sun, H.; Yang, W.; Fang, Y. Optical methods for label-free detection of bacteria. Biosensors 2022, 12, 1171. [Google Scholar] [CrossRef]
- McGoverin, C.; Steed, C.; Esan, A.; Robertson, J.; Swift, S.; Vanholsbeeck, F. Optical methods for bacterial detection and characterization. APL Photonics 2021, 6, 080903. [Google Scholar] [CrossRef]
- Franco-Duarte, R.; Černáková, L.; Kadam, S.; Kaushik, K.S.; Salehi, B.; Bevilacqua, A.; Corbo, M.R.; Antolak, H.; Dybka-Stępień, K.; Leszczewicz, M.; et al. Advances in chemical and biological methods to identify microorganisms—From past to present. Microorganisms 2019, 7, 130. [Google Scholar] [CrossRef]
- Ma, L.; Yi, J.; Wisuthiphaet, N.; Earles, M.; Nitin, N. Accelerating the detection of bacteria in food using artificial intelligence and optical imaging. Appl. Environ. Microbiol. 2022, 89, e01828-22. [Google Scholar] [CrossRef]
- Yi, J.; Wisuthiphaet, N.; Raja, P.; Nitin, N.; Earles, J.M. AI-enabled biosensing for rapid pathogen detection: From liquid food to agricultural water. Water Res. 2023, 242, 120258. [Google Scholar] [CrossRef]
- Kang, R.; Park, B.; Chen, K. Identifying non-O157 Shiga toxin-producing Escherichia coli (STEC) using deep learning methods with hyperspectral microscope images. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2020, 224, 117386. [Google Scholar] [CrossRef]
- Wu, C.; Xie, Y.; Xi, Q.; Han, X.; Li, Z.; Li, G.; Zhao, J.; Liu, M. Rapid and high accurate identification of Escherichia coli active and inactivated state by hyperspectral microscope imaging combing with machine learning algorithm. Vib. Spectrosc. 2024, 130, 103645. [Google Scholar] [CrossRef]
- Zhu, H.; Luo, J.; Liao, J.; He, S. High-accuracy rapid identification and classification of mixed bacteria using hyperspectral transmission microscopic imaging and machine learning. Prog. Electromagn. Res. 2023, 178, 49–62. [Google Scholar] [CrossRef]
- Eady, M.; Park, B.; Choi, S. Rapid and early detection of Salmonella serotypes with hyperspectral microscopy and multivariate data analysis. J. Food Prot. 2015, 78, 668–674. [Google Scholar] [CrossRef]
- Eady, M.; Park, B. Classification of Salmonella enterica serotypes with selective bands using visible/NIR hyperspectral microscope images. J. Microsc. 2016, 263, 10–19. [Google Scholar] [CrossRef] [PubMed]
- Tao, C.; Du, J.; Wang, J.; Hu, B.; Zhang, Z. Rapid identification of infectious pathogens at the single-cell level via combining hyperspectral microscopic images and deep learning. Cells 2023, 12, 379. [Google Scholar] [CrossRef]
- Park, B.; Shin, T.; Wang, B.; McDonogh, B.; Fong, A. Classification between live and dead foodborne bacteria with hyperspectral microscope imagery and machine learning. J. Microbiol. Methods 2023, 209, 106739. [Google Scholar] [CrossRef]
- Papa, M.; Wasit, A.; Pecora, J.; Bergholz, T.M.; Yi, J. Detection of viable but nonculturable E. coli induced by low-level antimicrobials using AI-enabled hyperspectral microscopy. J. Food Prot. 2025, 88, 100430. [Google Scholar] [CrossRef] [PubMed]
- Centers for Disease Control and Prevention (CDC). Burden of Foodborne Illness: Findings. Available online: https://www.cdc.gov/foodborneburden/2011-foodborne-estimates.html (accessed on 24 July 2025).
- Lamichhane, B.; Mawad, A.M.M.; Saleh, M.; Kelley, W.G.; Harrington, P.J., II; Lovestad, C.W.; Amezcua, J.; Sarhan, M.M.; El Zowalaty, M.E.; Ramadan, H.; et al. Salmonellosis: An overview of epidemiology, pathogenesis, and innovative approaches to mitigate the antimicrobial resistant infections. Antibiotics 2024, 13, 76. [Google Scholar] [CrossRef] [PubMed]
- Centers for Disease Control and Prevention (CDC). Outbreak of Salmonella Infections Linked to Backyard Poultry. 2024. Available online: https://www.cdc.gov/salmonella/outbreaks/backyardpoultry-05-24/investigation.html (accessed on 24 July 2025).
- Park, B.; Shin, T.; Kang, R.; Fong, A.; McDonogh, B.; Yoon, S.-C. Automated segmentation of foodborne bacteria from chicken rinse with hyperspectral microscope imaging and deep learning methods. Comput. Electron. Agric. 2023, 208, 107802. [Google Scholar] [CrossRef]
- Kang, R.; Park, B.; Eady, M.; Ouyang, Q.; Chen, K. Single-cell classification of foodborne pathogens using hyperspectral microscope imaging coupled with deep learning frameworks. Sens. Actuators B Chem. 2020, 309, 127789. [Google Scholar] [CrossRef]
- Fong, A.; Shu, G.; McDonogh, B.; Park, B. Detecting foodborne pathogens with darkfield hyperspectral microscopy. In Proceedings of the Hyperspectral Imaging and Applications, Online, 4 October 2020; SPIE: Bellingham, WA, USA, 2020; pp. 9–16. [Google Scholar] [CrossRef]
- He, Y.; Xu, W.; Zhi, Y.; Tyagi, R.; Hu, Z.; Cao, G. Rapid bacteria identification using structured illumination microscopy and machine learning. J. Innov. Opt. Health Sci. 2018, 11, 1850007. [Google Scholar] [CrossRef]
- Turra, G.; Arrigoni, S.; Signoroni, A. CNN-based identification of hyperspectral bacterial signatures for digital microbiology. In Proceedings of the Image Analysis and Processing-ICIAP 2017, Catania, Italy, 11–15 September 2017; Springer International Publishing: Cham, Switzerland, 2017; pp. 500–510. [Google Scholar] [CrossRef]
- Seo, Y.W.; Yoon, S.C.; Park, B.; Hinton Jr, A.; Windham, W.R.; Lawrence, K.C. Development of classification models to detect Salmonella Enteritidis and Salmonella Typhimurium found in poultry carcass rinses by visible-near infrared hyperspectral imaging. In Proceedings of the Sensing for Agriculture and Food Quality and Safety V, Baltimore, MD, USA, 29 April–1 May 2013; SPIE: Bellingham, WA, USA, 2013; pp. 70–78. [Google Scholar] [CrossRef]
- Maeda, Y.; Sugiyama, Y.; Kogiso, A.; Lim, T.-K.; Harada, M.; Yoshino, T.; Matsunaga, T.; Tanaka, T. colony fingerprint-based discrimination of Staphylococcus species with machine learning approaches. Sensors 2018, 18, 2789. [Google Scholar] [CrossRef] [PubMed]
- Signoroni, A.; Savardi, M.; Baronio, A.; Benini, S. Deep learning meets hyperspectral image analysis: A multidisciplinary review. J. Imaging 2019, 5, 52. [Google Scholar] [CrossRef]
- Kang, R.; Park, B.; Ouyang, Q.; Ren, N. Rapid identification of foodborne bacteria with hyperspectral microscopic imaging and artificial intelligence classification algorithms. Food Control 2021, 130, 108379. [Google Scholar] [CrossRef]
- Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. Pytorch: An imperative style, high-performance deep learning library. arXiv 2019, arXiv:1912.01703. [Google Scholar]
- Tan, M.; Le, Q.V. EfficientNetV2: Smaller models and faster training. In Proceedings of the 38th International Conference on Machine Learning (ICML 2021), Online, 18–24 July 2021; pp. 10096–10106. [Google Scholar]
- Buslaev, A.; Iglovikov, V.I.; Khvedchenya, E.; Parinov, A.; Druzhinin, M.; Kalinin, A.A. Albumentations: Fast and flexible image augmentations. Information 2020, 11, 125. [Google Scholar] [CrossRef]
- Eady, M.; Park, B. Rapid identification of Salmonella serotypes through hyperspectral microscopy with different lighting sources. J. Spectr. Imaging 2016, 5, a4. [Google Scholar] [CrossRef]
- Andino, A.; Hanning, I. Salmonella enterica: Survival, colonization, and virulence differences among serovars. Sci. World J. 2015, 2015, 520179. [Google Scholar] [CrossRef] [PubMed]
- Heffernan, L.M.; Lawrence, A.L.E.; Marcotte, H.A.; Sharma, A.; Jenkins, A.X.; Iguwe, D.; Abuaita, B.H. Heterogeneity of Salmonella enterica lipopolysaccharide counteracts macrophage and antimicrobial peptide defenses. Infect. Immun. 2024, 92, e00251-24. [Google Scholar] [CrossRef]
- Park, B.; Sundaram, J.; Hinton, A.; Yoon, S.-C.; Lawrence, K.C. Detection and characterization of Salmonella with hyperspectral microscope imaging. J. Spec. Imaging 2016, 5, 1–6. [Google Scholar]
- Zheng, S.; Bawazir, M.; Dhall, A.; Kim, H.-E.; He, L.; Heo, J.; Hwang, G. Implication of surface properties, bacterial motility, and hydrodynamic conditions on bacterial surface sensing and their initial adhesion. Front. Bioeng. Biotechnol. 2021, 9, 643722. [Google Scholar] [CrossRef]
- Buncic, S.; Avery, S.M.; Rocourt, J.; Dimitrijevic, M. Can food-related environmental factors induce different behaviour in two key serovars, 4b and 1/2a, of Listeria monocytogenes? Int. J. Food Microbiol. 2001, 65, 201–212. [Google Scholar] [CrossRef]
- Ferrari, R.G.; Rosario, D.K.A.; Cunha-Neto, A.; Mano, S.B.; Figueiredo, E.E.S.; Conte-Junior, C.A. Worldwide epidemiology of Salmonella serovars in animal-based foods: A meta-analysis. Appl. Environ. Microbiol. 2019, 85, e00591-19. [Google Scholar] [CrossRef]
- Khan, H.A.; Neyaz, L.A.; Malak, H.A.; Alshehri, W.A.; Elbanna, K.; Organji, S.R.; Asiri, F.H.; Aldosari, M.S.; Abulreesh, H.H. Diversity and antimicrobial susceptibility patterns of clinical and environmental Salmonella enterica serovars in Western Saudi Arabia. Folia Microbiol. 2024, 69, 1305–1317. [Google Scholar] [CrossRef]
- Jia, J.; Zheng, X.; Wang, Y.; Chen, Y.; Karjalainen, M.; Dong, S.; Lu, R.; Wang, J.; Hyyppä, J. The effect of artificial intelligence evolving on hyperspectral imagery with different signal-to-noise ratio, spectral and spatial resolutions. Remote Sens. Environ. 2024, 311, 114291. [Google Scholar] [CrossRef]
- Wang, Z.; Liang, S.; Xu, L.; Song, W.; Wang, D.; Huang, D. Dimensionality reduction method for hyperspectral image analysis based on rough set theory. Eur. J. Remote Sens. 2020, 53, 192–200. [Google Scholar] [CrossRef]
- Han, Y.; Joe, I. Enhancing machine learning models through PCA, SMOTE-ENN, and stochastic weighted averaging. Appl. Sci. 2024, 14, 9772. [Google Scholar] [CrossRef]
- Rodarmel, C.; Shan, J. Principal component analysis for hyperspectral image classification. Surv. Land. Inf. Sci. 2002, 62, 115–122. [Google Scholar]
- Taşkın, G.; Kaya, H.; Bruzzone, L. Feature selection based on high dimensional model representation for hyperspectral images. IEEE Trans. Image Process. 2017, 26, 2918–2928. [Google Scholar] [CrossRef]
- Cozzolino, D.; Williams, P.J.; Hoffman, L.C. An overview of pre-processing methods available for hyperspectral imaging applications. Microchem. J. 2023, 193, 109129. [Google Scholar] [CrossRef]
- Gould, E.; Fraser, H.S.; Parker, T.H.; Nakagawa, S.; Griffith, S.C.; Vesk, P.A.; Fidler, F.; Hamilton, D.G.; Abbey-Lee, R.N.; Abbott, J.K.; et al. Same data, different analysts: Variation in effect sizes due to analytical decisions in ecology and evolutionary biology. BMC Biol. 2025, 23, 35. [Google Scholar] [CrossRef]
- Matenda, R.T.; Rip, D.; Marais, J.; Williams, P.J. Exploring the potential of hyperspectral imaging for microbial assessment of meat: A review. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2024, 315, 124261. [Google Scholar] [CrossRef] [PubMed]
- Imani, M.; Ghassemian, H. An overview on spectral and spatial information fusion for hyperspectral image classification: Current trends and challenges. Inf. Fusion 2020, 59, 59–83. [Google Scholar] [CrossRef]
- Li, N.; Wang, Z.; Cheikh, F.A. Discriminating spectral–spatial feature extraction for hyperspectral image classification: A review. Sensors 2024, 24, 2987. [Google Scholar] [CrossRef]
- Krüger, G.I.; Pardo-Esté, C.; Álvarez, J.; Pacheco, N.; Castro-Severyn, J.; Alvarez-Thon, L.; Saavedra, C.P. Adaptive signatures of emerging Salmonella serotypes in response to stressful conditions in the poultry industry. LWT 2025, 215, 117188. [Google Scholar] [CrossRef]
- Mattock, J.; Smith, A.M.; Keddy, K.H.; Manners, E.J.; Duze, S.T.; Smouse, S.; Langridge, G.C. Genetic characterization of Salmonella Infantis from South Africa, 2004–2016. Access Microbiol. 2022, 4, 000371. [Google Scholar] [CrossRef] [PubMed]
- Girard, R.; Chaby, R. Comparative studies on Salmonella Johannesburg bacteriophages: Morphology, virulence and interactions with the host cell lipopolysaccharide. Ann. Microbiol. 1981, 132, 197–214. [Google Scholar]
- Liu, K.; Ke, Z.; Chen, P.; Zhu, S.; Yin, H.; Li, Z.; Chen, Z. Classification of two species of Gram-positive bacteria through hyperspectral microscopy coupled with machine learning. Biomed. Opt. Express 2021, 12, 7906–7916. [Google Scholar] [CrossRef] [PubMed]
- Praveen, B.; Menon, V. Study of spatial–spectral feature extraction frameworks with 3-D convolutional neural network for robust hyperspectral imagery classification. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 1717–1727. [Google Scholar] [CrossRef]
Spectral Features | Accuracy | Precision | Recall | ||||
---|---|---|---|---|---|---|---|
Model | Train | Test | Train | Test | Train | Test | |
Manual selection 1 | k-NN | 67.2% | 60.1% | 67.7% | 60.1% | 67.2% | 60.1% |
SVM | 55.9% | 54.1% | 58.1% | 56.0% | 55.9% | 54.1% | |
RF | 100.0% | 59.5% | 100.0% | 58.8% | 100.0% | 59.5% | |
MLP | 64.6% | 62.2% | 65.0% | 62.1% | 64.6% | 62.2% | |
Data-driven extraction 2 | k-NN | 81.7% | 73.7% | 81.9% | 74.2% | 81.7% | 73.7% |
SVM | 81.7% | 75.0% | 82.1% | 76.3% | 81.7% | 75.0% | |
RF | 100.0% | 77.7% | 100.0% | 78.6% | 100.0% | 77.7% | |
MLP | 99.4% | 81.1% | 99.4% | 81.1% | 99.4% | 81.1% |
Accuracy | Precision | Recall | ||||
---|---|---|---|---|---|---|
Model | Train | Test | Train | Test | Train | Test |
Spectral only 1 | 99.4% | 81.1% | 99.4% | 81.1% | 99.4% | 81.1% |
Image only 2 | 68.2% | 57.3% | 77.8% | 57.3% | 77.8% | 57.3% |
Multimodal fusion | 93.6% | 82.4% | 86.4% | 82.4% | 86.4% | 82.4% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Papa, M.; Bhattacharya, S.; Park, B.; Yi, J. Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion. Foods 2025, 14, 2737. https://doi.org/10.3390/foods14152737
Papa M, Bhattacharya S, Park B, Yi J. Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion. Foods. 2025; 14(15):2737. https://doi.org/10.3390/foods14152737
Chicago/Turabian StylePapa, MeiLi, Siddhartha Bhattacharya, Bosoon Park, and Jiyoon Yi. 2025. "Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion" Foods 14, no. 15: 2737. https://doi.org/10.3390/foods14152737
APA StylePapa, M., Bhattacharya, S., Park, B., & Yi, J. (2025). Rapid Salmonella Serovar Classification Using AI-Enabled Hyperspectral Microscopy with Enhanced Data Preprocessing and Multimodal Fusion. Foods, 14(15), 2737. https://doi.org/10.3390/foods14152737