Speakers and Continuing Education Sessions


Tuesday/mardi 24 September/septembre 2019

Keynote/conférencier: Opportunities and Challenges for Implementing AI in Radiation Oncology


Tom Purdie, PhD, MCCPM
Princess Margaret Cancer Centre,
Toronto, Ontario






Wednesday/mercredi 25 September/septembre 2019

CE Session 1: Statistics and Data Analytics for Medical Physicists

Panel Members: John Braun, Rob Deardon, Charles Mayo

John Braun, PhD
Deputy Director, CANSSI-INCAS
Professor and Head of Computer Science, Mathematics, Physics and Statistics
Adjunct Professor, Dept. of Stat and Act Sci,
Simon Fraser University & University of Western Ontario
Kelowna, BC


Abstract: Feature Selection with Confidence Intervals

The LASSO and its relatives, SCAD and MCP, are powerful methods for doing variable selection in high dimensional regression. However, confidence intervals for the resulting regression coefficients are not always satisfactory. We review the literature and suggest a completely new variable selection procedure which is often competitive with the LASSO and which is amenable to confidence interval construction.

Rob Deardon, B.Sc (HONS), M.Sc, PhD
Faculty of Veterinary Medicine and Department of Mathematics & Statistics,
University of Calgary
Calgary, AB

Abstract: Artificial intelligence in infectious disease surveillance

Ongoing improvements in artificial intelligence technology offer up tantalizing opportunities in many areas of application, including infectious disease surveillance and epidemiology.  The opportunities arise from both improvements in modelling techniques (e.g., deep learning), and a vastly increased capacity for collecting data, especially through automated systems. A particular area of interest, for both public health and agricultural officials, is the development and implementation of automated disease surveillance systems. Such systems might be used, for example, identify the onset of the influenza season or the emergence of a new strain of the disease, or identify an outbreak of a disease on a particular farm using sensory data. The goals here are typically to provide for alarm systems which identify the outbreaks as early as possible, and/or improve upon the accuracy of human identification of such outbreaks. Here, we shall discuss how modern machine learning classification algorithms can be used to improve on current disease surveillance methods, how successful they appear to be, and what problems are still to be solved. This will be done within the context of a number of human and livestock diseases, including influenza and mastitis in cattle.

Charles S. Mayo, PhD, FAAPM
Associate Professor, Radiation Oncology
University of Michigan
Ann Arbor, MI

Abstract: Leveraging Clinical Healthcare Informatics and Analytics to Bring AI into Clinical Practice

The combination of big data with machine learning (ML) and artificial intelligence (AI) algorithms promise to fundamentally change the nature of how we develop, test and apply clinical insights in healthcare. By creating a high volume big data analytics resource system to integrate “real world” clinical experience into a standardized ontological framework and then applying it to feed these algorithms we are creating a pathway in our clinic toward increased ability to apply observational data driving discovery and informing decision frameworks. Enabling this shift requires physicists to work on several efforts on several fronts including: clinical practice standardization, development of databases and ontologies, modeling and profiling using statistical and machine learning, and treatment team coordination. Using recent examples including use of an of AI toxicity model to refine DVH constraints, ML profiling factors affecting of treatment and imaging times we will highlight the several roles physicists must play to enable this translation of AI into clinical practice.

COMP Women's Committee Hosted Speaker: 

Jennifer (Jenn) Jakobi, PhD
Dean Pro Tem College of Graduate Studies
Professor, Health and Exercise Sciences
The University of British Columbia – Okanagan Campus

Organizational Goals – Is there a fit for Diversity?

Thursday/jeudi 26 September/septembre 2019

CE Session 2: Preparing for your Class II CNSC Inspection

Panel Members: Wayne Beckham (RSO), Lesley Buckley (RSO), Yani Picard (CNSC), John Schreiner (RSO)
Moderator: Michelle Nielsen

Abstract: As part of their mandate, the Canadian Nuclear Safety Commission (CNSC) routinely conducts inspections of Class II licensed facilities. The goal of these inspections is to improve the radiation safety program at the facility, while ensuring compliance with regulations. Preparation for an inspection, particularly a comprehensive Type I audit, requires significant effort on the part of both the licensee and the inspection team. This preparation extends beyond the Radiation Safety Officer alone and necessarily involves members of the entire program. Thorough preparation prior to an inspection can alleviate concern and stress on the part of staff participating in the inspection and is key to ensuring an efficient review by the inspection team. The session will present strategies for preparing for a CNSC inspection, from the viewpoint of both the licensee and of the CNSC. Panel members will share some tested practices they have  used to ensure a smooth inspection.


Professional Practice Leader
BC Cancer Agency, Vancouver Island Centre
Kelowna, BC




Lesley Buckley, PhD, FCCPM
Medical Physicist, The Ottawa Hospital
Assistant Professor, Dept of Radiology, University of Ottawa
Ottawa, ON


Yani Picard, MSc
Directorate of Nuclear Substance Regulation
Canadian Nuclear Safety Commission
Ottawa, ON





L. John Schreiner, PhD, FCCPM, FCOMP
Chief Medical Physicist
Cancer Centre of Southeastern Ontario
Kingston, ON




Friday/ vendredi 27 September/ septembre 2019

CE Session 3: Big Data & Artificial Intelligence in Medical Physics


Rebecca Feldman, PhD
Assistant Professor
Department of Computer Science Mathematics Physics and Statistics
University of British Columbia
Kelowna, BC

 Abstract: Image reconstruction in MRI: from Fourier Transforms to Machine Learning

 Machine learning in MRI initially focused on the segmentation and classification of reconstructed images. Recently, various techniques have been applied to image reconstruction in MRI. The MRI raw data is not acquired as an immediately human-recognizable image. The role of the image reconstruction process is to transform the raw data acquired during the imaging pulse sequence into something that can be recognized. This process involves multiple signal processing steps that each have an impact on the image quality, and might be optimized.

We will present the fundamentals of the image reconstruction processing steps for MRI, and introduce the role of machine learning in image reconstruction and optimization. We will discuss how machine learning techniques can be used to facilitate the acceleration of image acquisition using compressed sensing and simultaneous multi-slice acquisitions.

Tim O'Connell, M.Eng, M.D.
Vice Chair of Clinical Informatics at UBC
CEO of Emtelligent
Vancouver, BC

Abstract: Big (complex) Data: Opportunities and Challenges in Clinical Natural Language Processing

In today's world of cheap disk space and computing power, the tools to discover the needles in our haystacks of clinical data are ubiquitous.  However, much of our medical data is unstructured text, is opaque to simple analysis tools, and requires laborious manual labour for information extraction.  This talk will introduce the audience to natural language processing software, discuss some of the opportunities and challenges in the use of such software, and discuss multiple use cases for big data information extraction from clinical data.

Learning Objectives:

1. Understand what medical natural language processing software is, and learn about two current open-source medical NLP platforms
2. Review how medical NLP software can be used to extract data for big data research projects
3. Understand some of the limitations and challenges in using medical NLP

Shirin Abbasinejad Enger, PhD
Assistant Professor, Gerald Bronfman Department of Oncology, Division of Radiation Oncology
Head of the Novel Patient-Specific Brachytherapy and Detector Technology lab, McGill University
Montreal, QC

Abstract: Use of Artificial Intelligence in Dosimetry

Monte Carlo method is the most accurate dose calculation method and the gold standard. However, Monte Carlo based dose calculation engines can be slow for use in a clinical workflow. Artificial Intelligence based system and methods can enable radiation calculations that are comparably accurate to the state of the art methods, but significantly faster to execute. In this talk I will present how supervised learning can use the training data generated from the gold-standard Monte Carlo algorithms to optimize the parameters of a deep neural network, allowing the trained neural network to very quickly calculate radiation quantities at accuracies arbitrarily close to those of the source Monte Carlo algorithm.