As part of the Berlin Initiative for Applied Foundation Model Research (Appl-FM), our team is developing cutting-edge AI-powered microscopy techniques to unlock the secrets of bacterial behavior. We're tackling one of biology's most challenging problems: extracting meaningful quantitative information from complex, imbalanced microscopy datasets. By combining advanced microscopy with machine learning foundation models, we're creating tools that can automatically detect, track, and analyze cells with unprecedented accuracy.
This five-year project (2024-2029) represents a paradigm shift in biological imaging, moving from manual analysis to intelligent, adaptive systems that can accelerate discovery and improve healthcare outcomes.
Our research addresses critical medical challenges:
Bacterial Infections: Rapid identification of pathogenic bacteria and their antibiotic resistance patterns
Personalized Medicine: Linking bacterial morphology to infection states for targeted treatment options
We employ state-of-the-art techniques including:
Fluorescence microscopy
Foundation models adapted for biomedical imaging
Active learning algorithms that minimize annotation effort
