Pranav Rajpurkar presentation

Pranav Rajpurkar will give the talk, "Deep Learning for Medical Image Interpretation."

Abstract: Recent advances in training deep learning algorithms have demonstrated potential to accommodate the complex variations present in medical data. In this talk, I will describe technical advancements and challenges in the development and clinical application of deep learning algorithms designed to interpret medical images. I will focus on deep learning algorithms for chest x-rays, the most common medical imaging examination in the world, by first describing both the development of algorithms and curation of medical imaging data. Next I will describe important discoveries in model generalization to distribution shifts observed in deployment settings. Finally, I will discuss findings from a study investigating physician improvement with deep learning assistance in a simulated clinical setting. Altogether this body of work explores the advances and current challenges in the development and, importantly, the translation of medical imaging deep learning algorithms into clinical practice.

Pranav Rajpurkar is a PhD candidate in the Computer Science department at Stanford University advised by Prof. Andrew Ng and Prof. Percy Liang, where he works on building reliable artificial intelligence (AI) technologies for medical decision making. Pranav’s work has been published in 30+ peer-reviewed publications in both scientific journals and AI conferences and has been covered by media outlets including NPR, The Washington Post, and WIRED. Pranav founded the AI for Healthcare Bootcamp at Stanford, where he has worked closely with and mentored over 100 Stanford students on various research projects. Pranav writes a weekly AI+Medicine research newsletter with Dr. Eric Topol called Doctor Penguin, now with 4,000+ readers. He designed and instructed the Coursera course series on AI for Medicine, now with 40,000+ students. Prior to his PhD, Pranav also received both his bachelor's and master's degrees in Computer Science from Stanford.

Meeting ID: 840 6625 8426
Password: 784486

Questions? Contact Lori Kelso