Trustworthy AI will transform patient care in the coming years. In our research, we make sure that AI-enabled healthcare is safe and provides real benefit to patients and clinicians.

Dr. Lisa Koch

Lisa Koch is a group leader for machine learning in medical diagnostics in the Department of Data Science at the Hertie Institute for AI in Brain Health at the University of Tübingen. She works on machine learning for biomedical data analysis and has a background in academic research as well as developing machine learning products for medical devices. She focusses on research in trustworthy AI which can ultimately benefit patient health in a safe and effective way. Lisa Koch is an IMPRS-IS associated scientist.

Trustworthy AI will transform patient care in the coming years. In our research, we make sure that AI-enabled healthcare is safe and provides real benefit to patients and clinicians.

Wundram, A.M., Fischer, P., Wunderlich, S., Faber, H., Koch, L.M., Berens, P., Baumgartner C. F.

Dr. Lisa Koch

Leveraging Probabilistic Segmentation Models for Improved Glaucoma Diagnosis: A Clinical Pipeline Approach

Efficiently correcting patch-based segmentation errors to control image-level performance in retinal images

Distribution shift detection for the postmarket surveillance of medical AI algorithms: a retrospective simulation study

Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?

Sparse Activations for Interpretable Disease Grading

Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals

A Generative Model Reveals the Influence of Patient Attributes on Fundus Images

Hidden in plain sight: Subgroup shifts escape ood detection

Visual explanations for the detection of diabetic retinopathy from retinal fundus images