POSTPONED: Skule Lunch & Learn: Machine Learning for Medical Imaging with Imbalanced Data

***The in-person portion of this event has been canceled. A livestreamed version of this event will be rescheduled for a later date.***
Join us this month as Prof. Shahrokh Valaee, discusses the challenges at the forefront of medical imaging for the future. The success of machine learning in tackling challenging problems has made it the focus of research in academia and industry. The popularity of machine learning is indebted to the emergence of deep neural networks—networks that have multiple layers of processing units. The availability of data is the chief requirement for proper operation of deep neural networks. Unfortunately, applications such as rare diseases, which are usually more challenging to diagnose, have much less available data points than common ones. In this talk, we will discuss methodologies for machine learning in the absence of voluminous data. We will also look into datasets that are imbalanced in nature. We will show how synthesized X-ray images can boost the performance of machine learning algorithms for chest disease diagnosis.
Shahrokh Valaee is a Professor with the Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto. He is the Founder and the Director of the Wireless and Internet Research Laboratory (WIRLab). Professor Valaee was the TPC Co-Chair and the Local Organization Chair of the IEEE PIMRC Symposium 2011. He is a Track Co-chair for PIMRC 2020 and VTC Fall 2020. From 2010-2012, he was the Associate Editor of the IEEE Signal Processing Letters. From 2010-2015, he served as an Editor of IEEE Transactions on Wireless Communications. Currently, he is an Editor of Journal of Computer and System Science. Professor Valaee is a Fellow of the Engineering Institute of Canada, and a Fellow of IEEE.
Can’t attend in person? RSVP for the Livestream today!