Our deep learning experts within the AI4HEALTH team have a strong background in medical image analysis. They are specialized in enhancing and quantifying model trustworthiness, as well as increasing model robustness and generalizability. 

A recent success story of the team is the development of a CE marked deep learning model that automatically detects diabetic retinopathy on fundus images. This is accompanied by the successful submission of two patent applications, which resulted in the creation of a new spin-off company called MONA

The current focus of the team is on developing tools and metrics that can help the transition to more trustworthy medical AI. The team goes well beyond the state-of-the-art by researching the required technology to enable new tools to significantly enhance the degree in which AI can be trusted in the clinical practice.