We collect and use information about you, your devices and interactions to improve our services. For more information about how we collect your personal information and our use of cookies on our website, please see our Privacy Policy.

Webinar: Artificial Intelligence - A Clinical Perspective [9th March]

16.02.21

Join Dr Catherine Jones, Thoracic Radiologist and Chest Lead at annalise.ai and Dr Luke Oaken-Raynor, Director of Research, Medical Imaging, Royal Adelaide Hospital on Tuesday 9th March as they discuss some of the most pressing considerations surrounding the development of and implementation of medical ai today.

 

Tuesday 9th March | 6pm AEDT 

In partnership with RANZCR. Register your interest here.

This event is free to attend for both RANZCR members and non-members. Annalise is supporting the cost of this webinar for non-members. 

 
Presentation overviews

Part 1: AI and the CXR - developing and validating comprehensive AI

Presented by Dr Catherine Jones, annalise.ai 

Rapid advances in artificial intelligence modelling have led to the development of new and exciting AI tools to assist radiologists. Developing a comprehensive chest X-ray diagnostic tool is a complex process, requiring consideration of clinical use cases, workflow integration and hidden stratification. Dr Catherine Jones discusses the process of developing and validating Annalise CXR, the most comprehensive chest X-ray diagnostic support tool available.

Learning objectives:

  1. To understand the commonly used terms relating to artificial intelligence in radiology.
  2. To gain a deeper insight into the development of AI for the interpretation of chest radiographs.
  3. To develop a greater understanding of the clinical use cases of chest radiograph AI.

 

Part2: The basics of safe medical AI

Presented by Dr Luke Oaken-Rayner, Director of Research, Medical Imaging, Royal Adelaide Hospital, Researcher, Australian Institute for Machine Learning

Medical imaging AI systems are capable of incredible things, but they can also be unreliable, unpredictable, and even dangerous. In this talk, Dr Luke Oakden-Rayner will explain the intuition behind a key concept in medical ai safety, model underspecification, and discuss several approaches that developers can take to mitigate this problem.

Learning objectives:

  1. What is "underspecification" of an artificial intelligence model?
  2. How can underspecification lead to harm?
  3. How can we develop and test artificial intelligence in a way that mitigates the risks of underspecification?

 

Speakers biographies

Dr Catherine Jones Thoracic Radiologist and Chest Lead | annalise ai

Prior to her surgical and radiological training in the UK, Dr Jones earned degrees in mathematics and physics, then medicine at the University of Queensland. After a cardiothoracic radiology fellowship in Vancouver, Canada she returned to Australia to begin private practice with the I-MED Radiology Network. Now, as cardiothoracic lead at I-MED, Dr Jones is an executive member of the Australian and New Zealand Society of Thoracic Radiology and sits on multiple committees at the Royal Australian and New Zealand College of Radiologists. Her research interests include occupational lung disease imaging, artificial intelligence validation and diagnostic accuracy studies.

Connect with Catherine.

Dr Luke Oakden-Rayner MBBS FRANZCR | Director of Research, Medical Imaging, Royal Adelaide Hospital, Researcher, Australian Institute for Machine Learning

Luke Oakden-Rayner is the Director of Medical Imaging Research at the Royal Adelaide Hospital. A radiologist and medical researcher, he develops and tests artificial intelligence systems at the Australian Institute for Machine Learning. He is a passionate science communicator and writer, and advises leading national and international medical organisations on AI policy around issues including safety, regulation, ethics, and workforce development. 

Connect with Luke via his blog, Twitter @DrlukeOR or LinkedIn

Get in touch. See the possibilities.