Advanced subcellular imaging analyses using AI and machine learning
Contact persons: Cinzia Anita Maria Progida , Jonas Paulsen, Rein Aasland
Keywords: Imaging, chromatin, microscopy, AI, machine learning
Research groups: Physiology and Cell Biology (FYSCELL), Genetics and Evolutionary Biology (EVOGENE)
Department of Biosciences
Today's advanced super-resolution microscopy assays offer exceptional levels of detail and accuracy to reveal new facets of cellular function and architecture. These assays permit tracking positional data through multiple wavelengths over time, generating multidimensional imaging. The automatic interpretation of these vast high-resolution image data using pattern recognition, machine learning and AI, represents a largely untapped domain, offering a potential in uncovering novel insights into the behaviour and function of cells in a range of settings. This research theme focuses on using advanced computational tools, machine learning and AI to capture the intricate structures within subcellular structures such as chromatin, nucleoli and subnuclear organelles. The goal is to derive new insights into cellular behavior and its dynamic responses to external stimuli. These could include compressive forces that mimic the tumor environment or the confinement encountered by immune cells as they migrate through dense tissues.
External partners:
- Oslo University Hospital (OUH)
- Akershus University Hospital (AHUS)
- The Norwegian Computing Centre (NR)
