Join a cutting-edge research project at the crossroads of computer vision, deep learning, and cell biology.

Super-resolution fluorescence microscopy allows scientists to observe molecular processes in living cells with unprecedented spatial and temporal precision. Extracting meaningful scientific insights from these data, however, requires accurate statistical analysis of large collections of time-lapse images.

In this thesis project, you will develop and evaluate advanced machine learning methods for analyzing dynamic biological processes - such as endocytosis and exocytosis - captured through super-resolution microscopy. The overarching goal is to connect modern deep learning techniques with real-world biomedical research.

Key research directions include: Super-resolution image reconstruction, Multi-object tracking in time-lapse microscopy, Few-shot learning for object detection and classification, and Data-driven validation of biological hypotheses.

You will work with real experimental data from leading biological laboratories and collaborate within an interdisciplinary research team from UTIA, Czech Academy of Sciences, the University of Cambridge, and Masaryk University.

Supervisor: Filip Šroubek

Co-supervisor: Zuzana Kadlecová, University of Cambridge