Bacterial infections are a leading cause of death in both developed and developing nations. These infections are also costly to treat, accounting for 8.7% of annual healthcare spending, or $33 billion, in the United States alone. Current diagnostic methods require sample culturing to detect and identify the bacteria and its antibiotic susceptibility, a slow process that can take days even in state-of-the-art labs.
Partnering with a client in the BioTech industry, our team developed an effective classification algorithm for rapid detection and categorization of microorganisms, including identifying pathogens, through the visual spectral analysis based on Fresnel diffraction.
The results led to a successful commercialization of a hardware device by the client for microorganism identification.
Industry: PharmaTech, BioTech
Project Category: AI, image analysis, data analytics, software development
Lead Member: QuantUp
Project Description
Early identification of pathogens is an important task in healthcare, food- & cosmetic industries.
Our team developed a novel method for pathogen identification based on the analysis of the light diffraction on microorganism colonies in an optical system with converging spherical wave illumination. The implemented algorithm has proven highly effective and is able to identify pathogens with the accuracy of over 98%.
The image above illustrates sample results of light diffraction for the following microorganisms (from left to right): Candida albicans, Escherichia coli, Staphylococcus aureus, Pseudomonas aeruginosa (source)
References
"Bacteria identification in an optical system with optimized diffraction pattern registration condition supported by enhanced statistical analysis", Agnieszka Suchwałko et al., Optics Express Vol. 22, Issue 21, pp. 26312-26327 (2014), https://doi.org/10.1364/OE.22.026312