Research

Where the next three years of this work comes from.

The work behind the systems: theses, projects, the methods they used and the questions they were built to answer.

• Predicting gene expression (molecular biology) from digital pathology images

  Gene-expression assays are slow, expensive and logistically painful. Whole-slide pathology images are fast and cheap. This thesis asks whether the second can stand in for the first — recovering molecular-biology signal directly from gigapixel pathology images, under a hard constraint on compute and latency. The approach combines graph neural networks, vision foundation models, large-language-model techniques adapted for this task, and statistical/probabilistic methods.

• Simulating human visual cognition and distinguishing real perception from hallucination

  A year-long study using generative models — autoencoders and GANs — to model how the human brain constructs visual understanding, and to distinguish genuine perception from hallucination.