Computer Vision News - October 2021

42 Interview Best of MICCAI 2021 Mert, can you tell us about what you do in the Sabuncu Lab at Cornell? Our research group focuses on developing computational methods, i.e., algorithms, for medical imaging problems, including anything from MR acquisition to downstream applications using medical imaging data in the context of clinical workflows. How did you come to work in the field of medical imaging? I did my PhD at Princeton University in electrical engineering. Princeton doesn’t have a medical school and when I first started my PhD, I wasn’t sure what I wanted to work on. I knew that I wanted to do something that involved image processing, and in the early 2000s, there was some excitement around machine learning, so I started learning about that. While kicking around and thinking about it, I ran into a bunch of neuroscientists at Princeton who did functional MRI research. One of the group, James Haxby – who is now at Dartmouth College – introduced me to some image analysis problems in fMRI. That was my first experience with medical imaging. Then I had the opportunity during grad school to intern at Siemens Corporate Research - Siemens Healthineers now - which is also located in Princeton, New Jersey. I worked there over the summer and during the year I would collaborate with them. They have a heavy focus on medical imaging. What convinced you that this focus was the right one for you? I’m a strong believer that the research we do should have a real- world impact. I’m very pragmatic in Mert Sabuncu is an Associate Professor in Electrical and Computer Engineering at Cornell University and Cornell Tech. He also has a secondary appointment at Weill Cornell Medicine in radiology. He speaks to us about his career to date and his hopes for the future of medical imaging. LAST MINUTE NEWS : Mert has just been selected as winner of the Michael Tien ' 72 Sustained Excellence & Innovation in Engineering Education Award, the highest award for teaching at @CornellEng… Congrats, Mert!

RkJQdWJsaXNoZXIy NTc3NzU=