Hemoglobin and hematocrit measurements are used by physicians in a wide variety of medical contexts including early identification of anemic patients, but current technologies require blood draws and patient visits to the clinic. In this project, we are developing a new method to perform these tests non-invasively. An optical device senses images blood as it flows past superficial capillaries in the finger. The team has previously collected video capillary data from patients with varying levels of hemoglobin and hematocrit. My project will focus on analyzing these data and developing new image processing algorithms that can determine hemoglobin and hematocrit based on the non-invasive videos alone.

I am participating in SuperUROP because I want to gain experience in conducting high-quality research from start to finish. I took Biomedical Signal and Image Processing (6.555) and Discrete-Time Signal Processing (6.341), so I hope to be able to apply what I have learned, learn more tricks of the trade, and ultimately publish a paper. Noninvasive medical devices are super-cool, so it will be fun to work with new technologies.