Refresher Courses: Imaging Informatics / Artificial Intelligence and Machine Learning
RC 505-1
5 min
|
Chairperson's introduction
Federica Zanca, Leuven / Belgium
|
RC 505-2
15 min
|
AI may not injure a human being or, through inaction, allow a human being to come to harm
Andre Dekker, Maastricht / Netherlands
|
1. To learn about AI models creation strategies including the human in the loop.
2. To discover ways in which AI could lead to medical negligence of the radiologist. 3. To learn how to create stepwise AI models with quality checkpoints. |
|
RC 505-3
15 min
|
AI must obey the orders given it by human beings except where such orders would conflict with the First Law
Gaspard d'Assignies, Rénnes / France
|
1. To discover how radiologists should be able to accept, amend, or reject AI outputs.
2. To understand how humans can interact with AI to make the work better on a daily basis. 3. To learn about the roles that radiologists can undertake in the development of AI models. |
|
RC 505-4
15 min
|
AI must protect its own existence as long as such protection does not conflict with the First or Second Laws
Jonas Teuwen, Nijmegen / Netherlands
|
1. To learn how to focus AI models creation in maximising the clinical impact.
2. To review examples of AI integration in highly demanding environments. 3. To understand the current developments in AI modelling and future directions in healthcare. |
|
RC 505-5
10 min
|
Panel discussion: AI may not harm humanity, or, by inaction, allow humanity to come to harm
|
This session is accredited with 1 CME credit.