Date: 7 June 2018
Time: 12:00 - 13.00
Location: Wolfson Lecture Theatre, Computing, Queen Mother Building
Host: Professor Stephen McKenna
We are very pleased to announce this forthcoming seminar with Shazia Akbar from the University of Toronto.
Title: Deep Learning in Digital Pathology
Abstract: The use of deep learning in medical applications has grown extensively in the last few years, surpassing more traditional methods of feature extraction and pattern recognition. Using such “deep” architectures we can achieve state-of-the-art performance in complex and challenging medical datasets. In this talk, I will describe applications of deep learning in digital pathology, where currently large volumes of data must be analysed and interpreted by expert pathologists. Not only is this costly to the healthcare sector but it is also time consuming and introduces intra- and inter-variability in the clinical pipeline. Here, deep learning can be used to extract tissue characteristics without hand engineering features and produce results comparable to experts in this field.
Bio: Shazia Akbar is a postdoctoral fellow at Sunnybrook Research Institute, Toronto and Medical Biophysics, University of Toronto. Her speciality lies in the field of machine learning and medical image analysis, and currently she is investigating automated methods of predicting risk of breast cancer recurrence using deep learning techniques. In 2015, Shazia completed her PhD at the University of Dundee in collaboration with Ninewells Hospital, developing methods to localise tumour in images of breast cancer tissue. In 2011, she graduated from the Applied Computing program at the School of Computing, University of Dundee, with a first-class degree.