Nguyen receives NSF HBCU Excellence in Research grant to use big data for pancreatic cells quantitation
Recognition and evaluation of pancreatic cells is critical to assessing how the body responds to disease or treatment. Improving that process will lead to better health care for patients with comorbidities like obesity and diabetes.
Long Nguyen, Ph.D., assistant professor, computer science and data science, will pursue a novel approach to pancreatic cell quantitation thanks to a HBCU Excellence in Research grant from the National Science Foundation. The $599,995 award will fund the research project “Harnessing Big Data and Domain Knowledge to Advance Deep Learning for Interpretable Cell Quantitation.”
Dr. Nguyen has designed a comprehensive project that integrates cutting-edge technologies like deep learning and transfer learning with domain knowledge to create a more reliable and interpretable system for quantitating pancreatic cells.
“My hope is this research will help provide vital information for health care professionals, ultimately improving treatment for patients struggling with obesity and diabetes,” says Dr. Nguyen.
Dr. Nguyen’s research will improve upon existing methods that either rely on manual recognition or involve intricate parameter settings for automation.
“Integrating domain knowledge to guide our algorithm will improve its accuracy and reliability,” says Dr. Nguyen. “Transfer learning will fill important knowledge gaps at the intersection of deep learning and biomedical imaging.”
Dr. Nguyen’s work also supports Meharry SACS efforts to increase diversity in the data science field.
“The grant will fund some student research assistants and create other new research opportunities for our students, most of whom are from communities that are underrepresented in data science and other STEM fields,” says Dr. Nguyen.
The project will also benefit researchers in biomedical imaging, transfer learning and human-machine interaction. Additionally, Dr. Nguyen’s work will provide students practical studying materials in areas such as deep learning, image processing, and interpretable methods.
