KI.SH: An open network for artificial intelligence in Schleswig-Holstein

Artificial intelligence applications and technologies are increasingly finding their way into our lives. This also opens up considerable economic opportunities for companies in the North. In order to make better use of these opportunities, KI.SH (Artificial Intelligence in Schleswig-Holstein) aims to provide an open network that promotes the spread of AI applications and technologies in Schleswig-Holstein and facilitates access to science and the latest research. Let's find out together at KI.SH how we can use the full potential of AI for specific challenges in order to find practical, tailor-made solutions together.  

Fraunhofer MEVIS will be represented with the following contribution:

Johannes Lotz

Talk

"Medical Foundation Models – A Basis for AI in Clinical Practice and a Tool for Discovering New Biomarkers" (in German)

Session 1.2 – KI im Labor (AI in the Laboratory)

October 9, 10:30 am

Room: MF-50-2

Foundation Models (FMs) are large AI base models that are pre-trained on extensive and diverse datasets, making them versatile for use across many domains. In medicine, they could support diagnoses or provide important prognoses, such as in cancer detection.

However, training these models is often highly energy-intensive: traditional methods process millions of image patches over many thousands of computing hours—resulting in high costs and significant CO₂ emissions. To address this, Fraunhofer MEVIS has developed a more efficient approach that leverages existing annotations in addition to image data. This makes it possible to achieve comparable results using only a fraction of the data, computing time, and energy consumption. It conserves resources, reduces costs, and makes the targeted use of such models in medical research and diagnostics more practical.