Lucas Farndale

Thesis title: Self-Supervised Machine Learning as a Tool to Measure Cancer Prognosis

Biography

Qualifications

MSci Mathematics - University of Glasgow (2022)

First Class Honours

Undergraduate teaching

2022/23

Lectures

  • Machine Learning & Artificial Intelligence for Data Scientists (Masters)

2021/22

Tutorials

  • Maths 4H/5E Numerical Methods (Honours/Masters)
  • Maths 2A, 2C, 2D
  • Maths 1

2020/21

Tutorials

  • Science Fundamentals 1X, 1Y
  • Widening Participation Summer School (Maths)

Research summary

  • Self-Supervised Deep Learning
  • Immunology
  • Digital Pathology
  • Spatial Proteomics
  • Mathematical Modelling (particularly agent-based models)

Current research interests

My work focuses on developing self-supervised machine learning techniques to investigate whether there exist as yet undiscovered features in pathology imaging which predict cancer prognosis. These features can then be investigated with more standard laboratory techniques to better understand the mechanisms that drive cancer, and the immune system's response to cancer. Of particular interest are mechanisms of information transfer in the immune system, such as how antigen presenting cells prime the the immune response in the lymph node. My work focuses mainly on cancer, however, the methods developed are often broadly applicable to other areas of image analysis, both in medicine and further afield. I am also working on the integration of multiple different data modalities, particularly -omics data.
This article was published on