Peter Kühn

This paper introduces an automated method to detect rare events in liquid biopsies without prior knowledge of their signatures, demonstrating its effectiveness on immunofluorescence microscopy data.

This paper introduces a contrastive learning framework for single-cell phenotyping in whole slide imaging of liquid biopsy samples, achieving high accuracy and enabling automated identification of rare cell phenotypes.

This study shows that polyaneuploid cancer cells (PACCs) are pro-metastatic in vivo, based on in vitro and in vivo experiments in mouse models.

The paper identifies polyploid cancer cells as markers of chemotherapy resistance and recurrence in prostate cancer, linking them to poorer survival outcomes.

GeTMoR enables simultaneous genomic, transcriptomic, and morphological profiling of rare single cells, linking phenotype to molecular features.