Medical Image Analysis with AI
Details
Agenda
6:00 – 6:20 Intro
6:20 – 7:20 Medical Image Analysis with AI
7:20 – 7:40 Q&A
7:40 – 8:00 Wrap up
Medical Image Analysis with AI
Deep neural networks have taken computer vision by storm, showing unprecedented performance on a wide variety of image analysis tasks and igniting a gold rush of commercial opportunities. Healthcare has been no exception, seeing a huge surge in medical image analysis research, approvals, and patents.
There’s no question that the opportunities are many, but there are challenges to overcome. How do we ensure our models will generalize? How do we keep them from introducing or exacerbating disparities? How can we reliably quantify uncertainty, and how should it be handled? Interdisciplinary teams of researchers all over the world are grappling with these questions, and in the era of COVID, answers are urgently needed.
Nick will present an overview of current research in medical image computing, including applications that are showing great promise as well as stubborn challenges that remain the focus of intense study and debate.
About Nick Heller
Nicholas Heller is a 3rd year PhD Student in Computer Science at the University of Minnesota. His research focuses on the development and validation of clinical prediction models for risk stratification and treatment planning in genitourinary cancer, especially renal cell carcinoma. In particular, he is interested in the use of deep learning to incorporate tumor appearance into prediction models in more expressive and objective ways while maintaining transparency and biological plausibility. Nicholas serves as the lead organizer for the biennial Kidney Tumor Segmentation Challenge (KiTS), and the annual MICCAI LABELS workshop, which focuses on the science of creating medical imaging datasets for machine learning.