In February 2021, we launched the CAR’s national curriculum, “Artificial Intelligence in Radiology: Foundations to Current Applications,” consisting of five courses and multiple modules to be rolled out over time. Grounded in the latest science and developed by experts in the field, the modules offer a wealth of knowledge that is tailored for radiologists. So, where are we now?
Introduction to Artificial Intelligence in Radiology is fully available and includes four exciting interactive, modules:
- Module 1.1 Artificial Intelligence in Radiology: What This Means for Our Profession – Dr. An Tang, former Chair of the AI Standing Committee, provides an introduction to the curriculum and key concepts, such as the hierarchy of AI fields and various ways of conceptualizing the role of AI in radiology, including three potential applications within clinical workflows and six potential use cases.
- Module 1.2 Evaluating Radiology AI Applications – In this practical module, Dr. Jaron Chong, Chair of the AI Standing Committee, introduces the basics of AI model development and validation and takes you through a framework for evaluating AI applications. You’ll have the opportunity to apply this framework in an interactive scenario.
- Module 1.3 Best Practices for Producing Effective Predictor Systems – Dr. Russ Greiner, a renowned professor of computer science at the University of Alberta, has worked with many teams of medical professionals to build predictive algorithms that improve assessment, diagnosis, and treatment planning for patients. In this module, he shares what you need to know in order to successfully collaborate on such a team in the future.
- Module 1.4 Perceptions of How AI will Affect Radiology: A Focus on Medical Students – Dr. Bo Gong explores survey data revealing medical students’ concerns regarding radiology as a future career due to misconceptions about AI. He also shares insights from his own experience as a medical student and current radiology resident at UBC with a growing interest in AI.
Fundamentals of Machine Learning takes it up a notch in terms of the more technical aspects of AI. The first three interactive modules are currently available, with a fourth module in development:
- Module 2.1 The 4 Things You Need to Know About Radiology AI – Dr. Jaron Chong highlights four key points about AI, reintroducing some concepts from Course 1 from a slightly different perspective and with a little more detail. This module is the perfect steppingstone to a more in-depth look at machine learning.
- Module 2.2 Basic Principles of Machine Learning – In this module, Dr. Amir Pakdel, Chair of the AI Standing Committee, Education Section, takes you through the steps of building a machine learning algorithm. The statistical underpinnings of machine learning are revealed with animated examples that gradually increase in complexity.
- Module 2.3 Fundamentals of Neural Networks – Dr. Roger Tam is an associate professor in the Department of Radiology at UBC with expertise in applying machine learning methods to the quantitative analysis of medical images. In this module, he introduces the anatomy of a simple artificial neural network and builds on the training process introduced in Module 2.2.
- Module 2.4 Natural Language Processing: What Radiologists Need to Know – Dr. Osmar Zaïane is internationally recognized for his work on data mining, social network analysis, and natural language processing (NLP) at the University of Alberta. His upcoming module aims to dispel some of the mysteries behind extracting information from raw unstructured text and will cover several applications of NLP in healthcare and radiology, specifically.
It’s never too late to join the cohort of CAR members who are beginning their journey through this curriculum (and earning MOC credits under Section 3, Self-Assessment Program). Enroll today!
RAD Academy is an exclusive benefit of membership. Please email us for access.