Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy
Rapid detection of bacterial pathogens is essential for food safety and public health, yet bacteria can evade detection by entering a viable but nonculturable (VBNC) state under sublethal stress, such as antimicrobial residues. These bacteria remain active but undetectable by standard culture-based...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Journal of Food Protection |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0362028X2400214X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553866862100480 |
|---|---|
| author | MeiLi Papa Aarham Wasit Justin Pecora Teresa M. Bergholz Jiyoon Yi |
| author_facet | MeiLi Papa Aarham Wasit Justin Pecora Teresa M. Bergholz Jiyoon Yi |
| author_sort | MeiLi Papa |
| collection | DOAJ |
| description | Rapid detection of bacterial pathogens is essential for food safety and public health, yet bacteria can evade detection by entering a viable but nonculturable (VBNC) state under sublethal stress, such as antimicrobial residues. These bacteria remain active but undetectable by standard culture-based methods without extensive enrichment, necessitating advanced detection methods. This study developed an AI-enabled hyperspectral microscope imaging (HMI) framework for rapid VBNC detection under low-level antimicrobials. The objectives were to (i) induce the VBNC state in Escherichia coli K-12 by exposure to selected antimicrobial stressors, (ii) obtain HMI data capturing physiological changes in VBNC cells, and (iii) automate the classification of normal and VBNC cells using deep learning image classification. The VBNC state was induced by low-level oxidative (0.01% hydrogen peroxide) and acidic (0.001% peracetic acid) stressors for 3 days, confirmed by live-dead staining and plate counting. HMI provided spatial and spectral data, extracted into pseudo-RGB images using three characteristic spectral wavelengths. An EfficientNetV2-based convolutional neural network architecture was trained on these pseudo-RGB images, achieving 97.1% accuracy of VBNC classification (n = 200), outperforming the model trained on RGB images at 83.3%. The results highlight the potential for rapid, automated VBNC detection using AI-enabled hyperspectral microscopy, contributing to timely intervention to prevent foodborne illnesses and outbreaks. |
| format | Article |
| id | doaj-art-0c595651abcf4f6294a26d27a7cf6051 |
| institution | Kabale University |
| issn | 0362-028X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Food Protection |
| spelling | doaj-art-0c595651abcf4f6294a26d27a7cf60512025-01-09T06:12:37ZengElsevierJournal of Food Protection0362-028X2025-01-01881100430Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral MicroscopyMeiLi Papa0Aarham Wasit1Justin Pecora2Teresa M. Bergholz3Jiyoon Yi4Department of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USADepartment of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824, USADepartment of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USADepartment of Food Science and Human Nutrition, Michigan State University, East Lansing, MI 48824, USADepartment of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USA; Corresponding author.Rapid detection of bacterial pathogens is essential for food safety and public health, yet bacteria can evade detection by entering a viable but nonculturable (VBNC) state under sublethal stress, such as antimicrobial residues. These bacteria remain active but undetectable by standard culture-based methods without extensive enrichment, necessitating advanced detection methods. This study developed an AI-enabled hyperspectral microscope imaging (HMI) framework for rapid VBNC detection under low-level antimicrobials. The objectives were to (i) induce the VBNC state in Escherichia coli K-12 by exposure to selected antimicrobial stressors, (ii) obtain HMI data capturing physiological changes in VBNC cells, and (iii) automate the classification of normal and VBNC cells using deep learning image classification. The VBNC state was induced by low-level oxidative (0.01% hydrogen peroxide) and acidic (0.001% peracetic acid) stressors for 3 days, confirmed by live-dead staining and plate counting. HMI provided spatial and spectral data, extracted into pseudo-RGB images using three characteristic spectral wavelengths. An EfficientNetV2-based convolutional neural network architecture was trained on these pseudo-RGB images, achieving 97.1% accuracy of VBNC classification (n = 200), outperforming the model trained on RGB images at 83.3%. The results highlight the potential for rapid, automated VBNC detection using AI-enabled hyperspectral microscopy, contributing to timely intervention to prevent foodborne illnesses and outbreaks.http://www.sciencedirect.com/science/article/pii/S0362028X2400214XArtificial IntelligenceDeep learningEscherichia coliHyperspectral microscopyViable but nonculturable |
| spellingShingle | MeiLi Papa Aarham Wasit Justin Pecora Teresa M. Bergholz Jiyoon Yi Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy Journal of Food Protection Artificial Intelligence Deep learning Escherichia coli Hyperspectral microscopy Viable but nonculturable |
| title | Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy |
| title_full | Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy |
| title_fullStr | Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy |
| title_full_unstemmed | Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy |
| title_short | Detection of Viable but Nonculturable E. coli Induced by Low-Level Antimicrobials Using AI-Enabled Hyperspectral Microscopy |
| title_sort | detection of viable but nonculturable e coli induced by low level antimicrobials using ai enabled hyperspectral microscopy |
| topic | Artificial Intelligence Deep learning Escherichia coli Hyperspectral microscopy Viable but nonculturable |
| url | http://www.sciencedirect.com/science/article/pii/S0362028X2400214X |
| work_keys_str_mv | AT meilipapa detectionofviablebutnonculturableecoliinducedbylowlevelantimicrobialsusingaienabledhyperspectralmicroscopy AT aarhamwasit detectionofviablebutnonculturableecoliinducedbylowlevelantimicrobialsusingaienabledhyperspectralmicroscopy AT justinpecora detectionofviablebutnonculturableecoliinducedbylowlevelantimicrobialsusingaienabledhyperspectralmicroscopy AT teresambergholz detectionofviablebutnonculturableecoliinducedbylowlevelantimicrobialsusingaienabledhyperspectralmicroscopy AT jiyoonyi detectionofviablebutnonculturableecoliinducedbylowlevelantimicrobialsusingaienabledhyperspectralmicroscopy |