- This event has passed.
Online: Skule™ Lunch & Learn: Machine Learning for Medical Imaging with Imbalanced Data with Prof. Shahrokh Valaee
The event URL will be sent to registered participants April 29.
Join U of T Engineering 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.