Our mission is to reduce health inequalities, democratize rare healthcare expertise, and to develop novel, computationally efficient techniques for the analysis of health data like medical imaging.
July 2025 — Salt Lake City, Utah
A team from the IDEA Lab made a strong showing at the Medical Imaging with Deep Learning (MIDL) 2025 conference, presenting their most recent research on generative models.
Among the highlights:
“Generate to Ground” introduced a novel use of text-t...
This June, Mischa Dombrowski, one of our PhD students, traveled to Nashville to present his latest research at CVPR 2025.
His paper, titled “Image Generation Diversity Issues and How to Tame Them,” delves into the often-overlooked problem of diversity in synthetic image datasets and proposes novel ...
Bernhard Kainz (Senior Member, IEEE) has been appointed as Senior Area Editor for IEEE TRANSACTIONS ON MEDICAL IMAGING (TMI), the premier scientific journal in the field of medical image analysis.
Our group showcased multiple research papers at the premier conference for medical image analysis, highlighting our latest advancements and contributions to the field.
This October, our team gathered for the Borderless Symposium, an event where we connect in person to discuss our latest research and strategic directions. Meeting regularly throughout the year in Erlangen and other locations fosters collaboration across institutions and disciplines, allowing us to e...
UKER and IDEA lab Researchers have developed an ML tool to improve the diagnosis and assessment of severe complications in patients with Fontan circulation, a surgical treatment for various single-ventricle congenital heart conditions. While survival rates have improved, patients remain at risk for complications like protein-losing enteropathy and plastic bronchitis, often due to lymphatic system congestion.
We are thrilled to announce that this week, Mischa had the fantastic opportunity to present our paper 'Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability' as an oral presentation at the AAAI Conference on Artificial Intelligence as part of the main conference - Safe, Rob...
