My research group works on translational research to develop machine learning algorithms for medical images that can be deployed in clinics. Towards this goal, it was imperative that we worked with doctors, which presented its own challenges and rewards. For instance, both sides have to learn a bit of each others' vocabulary and gain appreciation for their operating constraints. However, the results can be very rewarding when such divides can be bridged to even some extent..I will take some examples of our collaborative work to illustrate these points in the context of developing technology to serve the bottom of the socio-economic pyramid.
Amit Sethi is a Professor of Electrical Engineering at IIT Bombay, and a Visiting Instructor of Pathology at UIC. His research group works on computer vision, deep learning, and medical image analysis. His current research is focused on extracting valuable information, such as for prognosis, using deep learning on inexpensive medical imaging modalities. Technical challenges to solve these real-world problems include working large images, small sample sizes, input quality issues, data mislabeling, and introduction of outliers during the use of such models. Before joining IIT Bombay, he worked as a faculty member of Electronics and Electrical Engineering at IIT Guwahati, and as a management consultant at ZS Associates' Chicago. He obtained his PhD in Electrical and Computer Engineering from University of Illinois at Urbana-Champaign with a focus on computer vision and machine learning, and a bachelors in Electrical Engineering from IIT Delhi.