SBIR Phase I: Automated Gram Stain Interpretation Via Digital Holographic Microscopy

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is the improvement in hospital laboratory results by automating and standardizing a manual test procedure that is critical for the diagnosis of infections. Faster, higher quality and less expensive test results will help to ensure that patients receive timely treatment with the appropriate medications, reduce employee burnout through the automation of tedious laboratory tasks, and lower healthcare costs. Just as automated blood analyzers largely replaced manual blood cell counting, the proposed platform will eventually replace manual counting of bacteria and yeast cells. The new imaging technology developed as a part of this project will generate advanced manufacturing jobs and increase the economic competitiveness of the United States by introducing an innovative product to a market dominated by foreign firms. Long-term benefits to society include decreased antimicrobial (medicines that kill microorganisms) resistance as infections are managed with fewer unnecessary antimicrobials. This Small Business Innovation Research (SBIR) Phase I project involves the development of a novel microscopy platform for automating the interpretation of tests performed in hospital laboratories. This project fills an important gap specific to microbiology labs that are facing a trained labor shortage without affordable automated alternatives. Microbiology labs in hospitals are responsible for examining patient samples (e.g., urine and blood) for the presence, type, and quantity of microscopic organisms (e.g., bacteria and yeast). This project includes the engineering of a special light source, a customized camera, and a suite of artificial intelligence (AI)-enabled algorithms to analyze the microscopic images captured by the camera. Once the platform is built, its performance will be evaluated on real patient samples to demonstrate the feasibility of the technology by comparing it to experienced human lab technicians. The project will measure how often the platform produces the correct answer as well as how long it takes. The platform will also be tested in terms of image quality to demonstrate that it can take pictures of the smallest bacteria and accurately capture color. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.