November 29, 2017: Invited Speaker Seminar: Medical Image Analysis in the Age of Big Data

Dr. Matthew Toews
École de Technologie Supérieure (ETS)

Wednesday, November 29, 2017 at 2:00 pm
Room EV003.309

Abstract

Technology has given us the ability to image and store virtually unlimited amounts of medical image data, along with patient records. This provides unprecedented opportunities for machine learning algorithms, e.g. for computer assisted diagnosis of a new patient based on similarities with previous patients. A key challenge is in coping with the computational complexity of identifying similar patterns of image structure. This presentation presents a general instance-based learning framework that scales gracefully to arbitrarily large numbers of image data. Large image sets are reduced into collections of local salient features that can be stored and indexed for highly efficient inference. We present results using the framework in diverse contexts, including classification of normal and pathological brain variability from brain MRI, identifying twins and family members from brain MRI and predicting lung disease in chest CT imaging, from datasets of up to 20,000 scans.

Biography

Matthew Toews is an associate professor of engineering with the École de Technologie Supérieure (ETS) at the Université du Québec à Montréal (UQAM). His research touches on computer vision, machine learning, signal processing, electronics, information theory and geometry. He obtained his Master’s and PhD in Electrical and Computer Engineering from McGill University (2003-2008), where among his contributions was the first system for detecting and classifying faces from images acquired from arbitrary viewpoints. As a postdoctoral researcher at Harvard Medical School (2009-2014), he developed methods for large-scale medical image analysis and classification, with applications ranging from image segmentation, registration and computer-assisted diagnosis. His research has investigated diseases including autism, Alzheimer's disease, chronic obstructive pulmonary disorder, brain and lung cancer, in addition to healthy neurodevelopment and genetics. He is a recipient of the Canadian National Sciences and Engineering Research Council (NSERC) Discovery Grant.