STTR Phase I: Using AI to develop a red blood cell health index for the monitoring of sickle cell disease

The broader impact of this Small Business Technology Transfer (STTR) Phase I project is to reach underserved communities and address inequities in health care for patients with hemolytic anemias by providing fast, affordable, and accurate diagnosis and monitoring of hemolytic anemias by combining 3D phase imaging with deep learning. Sickle Cell Disease (“SCD”) is a global health problem that significantly impacts the life span, quality of life, and health outcomes of affected individuals. SCD is one of the most common hemolytic diseases in Sub-Saharan Africa and the U.S, affecting up to 3% of the newborn population. However, few resources and research are dedicated to improving the diagnosis and monitoring of SCD. Individuals who lack access to screening and testing are susceptible to an early-life mortality rate of up to 90%. Unfortunately, those who are most likely to suffer from hemolytic diseases like SCD are frequently underserved by advanced health care. This project may significantly reduce the SCD burden by providing monitoring to prevent crises that require hospitalizations and emergency care. This Small Business Technology Transfer (STTR) Phase I project will advance Artificial Intelligence (AI) innovations for diagnosing red blood cell disease with quantitative phase imaging (QPI). While QPI images can be used to diagnose a handful of hemolytic anemias, no effort has been made to infuse it into health care at scale. This project develops an AI system to identify RBCs in crowded QPI images, as well as other blood cellular components, such as platelets and white blood cells. The project will develop robust machine learning models to learn from these data; in particular, new deep learning models, based on forms of convolutional neural networks and recurrent neural networks, will provide insight based on temporal and spatial data. 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.