EIBIR Session
EIBIR 24 - Artificial intelligence (AI), real impact: redefining clinical decision making based on medical images
Lectures
1
Chairperson's introduction
05:00Oliver Diaz, Barcelona / ES
2
RadioVal: international clinical validation of radiomics AI for breast cancer treatment planning
15:00Oliver Diaz, Barcelona / ES
3
ODELIA: open-source swarm learning for decentralised medical AI for breast cancer detection
15:00Daniel Truhn, Aachen / DE
4
Discussion
10:00Ulrike I. Attenberger, Bonn / DE, Georg Langs, Vienna / AT
5 min
Chairperson's introduction
Oliver Diaz, Barcelona / Spain
15 min
RadioVal: international clinical validation of radiomics AI for breast cancer treatment planning
Oliver Diaz, Barcelona / Spain
1. To learn about the FUTURE-AI guideline for trustworthy AI in healthcare.
2. To appreciate its advantages in guiding AI teams for building deployable AI tools in healthcare.
3. To understand its potential for building and validating trustworthy AI tools in breast cancer imaging.
2. To appreciate its advantages in guiding AI teams for building deployable AI tools in healthcare.
3. To understand its potential for building and validating trustworthy AI tools in breast cancer imaging.
15 min
ODELIA: open-source swarm learning for decentralised medical AI for breast cancer detection
Daniel Truhn, Aachen / Germany
1. To learn about collaborative training of AI algorithms.
2. To get up to date about the current progress of AI in MR breast imaging.
3. To learn about possibilities to contribute to collaborative AI development.
2. To get up to date about the current progress of AI in MR breast imaging.
3. To learn about possibilities to contribute to collaborative AI development.
15 min
AI-POD: trustworthy AI tools for the prediction of obesity-related vascular diseases
Ulrike I. Attenberger, Bonn / Germany
Georg Langs, Vienna / Austria
Georg Langs, Vienna / Austria
1. To learn about the potential of AI tools in obesity-related vascular disease.
2. To show how to build and validate AI tools in the prediction of obesity-related vascular disease.
2. To show how to build and validate AI tools in the prediction of obesity-related vascular disease.