Summary:
Researchers from UCLA’s Electrical and Computer Engineering and Bioengineering Departments have invented a novel automated system that quickly detects and classifies colonies of live bacteria in water by using deep neural networks to analyze holographic images.
Background:
Early identification of pathogenic bacteria in food, water, and bodily fluids is very important and yet challenging, owing to sample complexities and large sample volumes that need to be rapidly screened. Existing screening methods based on plate counting or molecular analysis present various tradeoffs with regard to the detection time, accuracy/sensitivity, cost, and sample preparation complexity. Thus, there is a need for fast, accurate, automatic methods that can handle large sample sizes.
Innovation:
Researchers from UCLA’s Electrical and Computer Engineering and Bioengineering Department have developed a deep learning-based monitoring system for the early detection and classification of live-bacteria in samples, known as colony forming units (CFU). The system analyzes lens-free holographic microscopy images of bacteria growing on agar plates. A proof-of-concept device was demonstrated by using 3 types of bacteria, and >12 h time savings were achieved for both the early detection and the classification of growing species compared to the gold-standard EPA-approved methods. This automated and cost-effective live bacteria detection platform can be transformative for a wide range of applications in microbiology by significantly reducing the detection time and automating the identification of colonies without labelling or the need for an expert. The system will not only improve monitoring of food and water quality, but also provides a powerful tool for microbiology research.
Potential Applications:
• Monitoring of food and water quality
• Microbiome studies
• Clinical diagnoses
• Drug discovery screening assays
Advantages:
• Rapid and high-throughput bacterial colony forming unit (CFU) detection
• High sensitivity
• Cost-effective
• Automated detection of bacterial CFU without the need for an expert
Development-To-Date:
Proof-of-concept device has been successfully demonstrated.
Related Papers:
Wang, H., Ceylan Koydemir, H., Qiu, Y. et al. Early detection and classification of live bacteria using time-lapse coherent imaging and deep learning. Light Sci Appl 9, 118 (2020). https://doi.org/10.1038/s41377-020-00358-9
Reference: UCLA Case No. 2020-487