Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.


Most machine learning methodologies require large datasets with high-quality labelling to effectively train and validate the developed models. However, as medical imaging repositories used for population health studies, such as the UK Biobank, continue to grow, the conventional manual annotation approaches by experts become impractical. On the other hand, the labelling process can be automated by extracting annotations from associated metadata or reports. In such scenarios, automated labelling can introduce errors due to ambiguities in the reports, resulting in large but noisy-labelled (or even mislabelled) datasets. Consequently, this can lead to poorer generalization or replicate human biases present in the data.

The primary objective of this project is to investigate machine learning strategies that can guide optimal annotation techniques to achieve high accuracy while mitigating biases in the developed model.


The project encompasses:

  • Ddveloping skills in AI/ML techniques with application to biomedical imaging
  • writing scientific reports and journal articles and presenting findings at the research conferences.


The student will have also opportunity to attend the research seminar offered at the NDPH, the BDI and the Institute of Biomedical Engineering (IBME) as the primary supervisor is a member of Imaging Hub at the IBME ( The student will be expected to attend relevant seminars within the department and those relevant in the wider University. Subject-specific training will be received through our group's weekly supervision meetings. Students will also attend external scientific conferences where they will be expected to present the research findings.


The ideal student would have:

  • a degree in computer science, statistics, engineering or a related discipline
  • strong programming skills (preferable Python, or Matlab/C++ and willing to learn Python)
  • experience or interest in machine learning (Deep Learning) and medical image analysis
  • experience or enthusiasm to work on clinically relevant problems.