PhD in Computing
Imperial College London, October 2018 - December 2022
Machine learning for medical imaging, probabilistic modelling and causal inference.
Details
PhD in computing at Imperial College London focusing on machine learning for medical imaging. My research touched on computer vision, deep learning, probabilistic modelling and causal inference. Specifically, medical imaging segmentation, modelling uncertainty via deep probabilistic methods and causal/counterfactual inference for images using deep generative models. Additional topics include Bayesian statistics and generative models (VAEs, GANs, normalising flows).
Over 1,300 citations on Google Scholar (h-index 14), with publications in venues including NeurIPS, ICLR, ICML, and The Lancet Digital Health. Supervised a 5-student group project and a final-year individual project; the latter received a best-project award.
Selected publications
- Measuring axiomatic soundness of counterfactual image models
- Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty
- Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study
For a full list of publications see the publications page or my google scholar.
Thesis
Advancing probabilistic and causal deep learning in medical image analysis