Explainable AI models could help trust and learn from machine decisions. But what makes a good vs a bad explainable model? What types of explainable models are there and which ones can make an impact? Join us in this discussion this Thursday with Bas:

Join us this Thursday 12th for a discussion with Shandong Wu, Radiology Professor at University of Pittsburgh on his current research on applications of AI in breast MRI. For more information and future speakers:

Continuing the topic of personalized screening: Can we use AI to help decide which patients could benefit more from taking an MRI on top of mammography? More information at:

How well does ML solve the problem of risk prediction of breast cancer based on mammography? Can we personalize screening? Join us this Thursday Dec 8th at 11AM (ET) on a conversation with Dr. Yala More information at:

Many ML models are published for clinical applications, but how many would really be used? Join us on this talk about a new pipeline for Triage of Breast Cancer that can help a radiologist take better and personalized decisions for patient care.

How to train Deep Learning models when lacking enough labeled data? Join this Thursday's conversation to discuss how to use self-supervised learning to improve result with partially annotated data. See the speakers and more at

Join us for the second talk in the AI for breast MRI seminar, where we will be discussing the importance of data sharing for clinical benchmarks and common issues. This Thursday 29th, 11AM (ET) on Zoom:

For the first talk in the AI for breast MRI seminar, Jan Witowski will present latest results on Deep Learning for diagnosis of breast cancer on MRI and how it compares with radiologists, as well as the path and issues on the way.