Speaker: Charlotte Kyeremah, University of Massachusetts Boston

Abstract: Early and accurate diagnosis of malaria in the human red blood cells is acute to the success of eliminating malaria. The method of malaria diagnosis using optical microscopy involves staining and manual counting of infected cells by trained personnel, making the process subjective, time-consuming, and labor-intensive. Here we propose to develop a 3D-printed lensless in-line digital microscope (LiDHM) without the need for staining the cells. We will integrate the microscope with a small embedded systems hardware platform to run multiple neural networks in parallel for image classification, object detection, segmentation, processing, and machine learning algorithms for automatic detection and quantification based on parasite stages in infected cells, and display for the visual user interface. We present the results of LiDHM along with the proof of concept by imaging-controlled phase objects and biological specimens.

For more information, please visit the Physics Department website.