Basic blood tests require significant manual effort and are ubiquitous bottlenecks in healthcare systems. SafineAI seeks to develop a new “intelligent” computational microscope that, combined with cloud-based machine learning algorithms, will automate blood analysis and open up new diagnostic possibilities.

Duke engineering graduate students formed SafineAI to miniaturize a reconfigurable LED microscope. This concept has already earned them a $120,000 prize at a local pitch competition.

This microscope adapts its lighting angles, colors, and patterns while teaching itself the optimal settings needed to complete a given diagnostic task. In the initial proof-of-concept study, the microscope simultaneously developed a lighting pattern and classification system that allowed it to quickly identify red blood cells infected by the malaria parasite more accurately than trained physicians and other machine learning approaches.

The research was published in Biomedical Optics Express, a publication of The Optical Society (OSA) (www.dx.doi.org/10.1364/BOE.10.006351).