AI & Signals

Image and biosignal data are becoming increasingly important in clinical diagnostics and research. Echocardiography sequences and longitudinal image studies for patient monitoring can be analyzed using new machine learning methods, for example, to extract relevant markers and use them for prediction models in cardiology. Self-supervised learning methods are also used to extract relevant markers from large image and signal data without expensive expert labels, as well as cross-modal learning methods that combine image data with sensor data or textual information (findings). The "AI and signals" cluster deals with the application and further development of AI methods for image, video and biosignals and time series. Building on this, the junior research groups Machine Learning for Non-Textual Data, Biomedical Image Recognition and AI in Oncology - Focus on Image Data described below will be established.