Recent advances in 3D imaging techniques—particularly light-sheet microscopy—have dramatically increased the volume and complexity of biological data being generated. However, current tools and workflows often struggle to keep up, making it challenging to store, process, and extract meaningful insights from these large datasets.
This project will explore innovative strategies to better manage, visualize, and analyze 3D imaging data, helping bridge the gap between image acquisition and biological discovery. Example project areas include:
- AI-driven image analysis: Develop and evaluate machine learning models for tasks such as cell segmentation, tracking or classification
- Developing new algorithms/software: Developing or adapting algorithms or software for microscopy data
- Statistical & Quantitative Analysis: Apply statistical or machine learning methods to extract features and interpret measurements from biological experiments
- Data curation and foundation models for bioimage analysis: Develop workflows to curate and standardise large-scale microscopy datasets, and leverage this to evaluate existing or potentially new foundation-style models for robust, generalisable analysis.
