Skip to main content Skip to navigation

TIA Centre: Doctoral Studies

Do you have an interest in Computational Pathology?

Are you interested in utilising artificial intelligence models to explore the early detection and diagnosis of cancer and other diseases?

If so, a PhD aligned to the TIA Centre may be right for you!

The Department of Computer Science offers two PhD programmes which can be aligned to TIA Centre research themes and supervised by our academics. For more information about joining the Department on one of these programmes, including application advice, please go to the main Computer Science Centre for Doctoral Training and Research webpage.

Calls for Applications

There are no live calls for applications at the moment.

However, you can express interest in undertaking a PhD with one of our supervisors at any time using this form. If you require funding, please make sure you also check the deadlines for scholarship applications here.

Our PhD programmes

Computer Science

Cutting-edge research at the frontiers of Computer Science in a broad range of theoretical and applied topics.

Biomedical AI

An integrated pathway that combines technical excellence in AI with a deep understanding of biomedical data, regulatory challenges and translational impact. This pathway is available to applicants from varying fields, including medicine.

Our supervisors

Nasir Rajpoot

Research interests:

  • Multimodal AI for clinical decision support
  • Mechanistic AI for oncology
  • Multimodal learning with limited labels
  • Multimodal learning with distribution shift
Fayyaz Minhas

Research interests:

  • Multimodal Foundation Models for Biomedicine
  • Agentic AI for Scientific and Clinical Workflows
  • Spatial and Geometric Learning in Biology and Medicine
  • Interpretable, Causal, and Robust AI in Healthcare
  • Translational AI for Real Clinical Problems
Shan Raza

Research interests:

  • Computational Pathology
  • AI‑driven cancer diagnostics and prognostics
  • Tumour Microenvironment Characterisation using mIF imaging for biological discovery
  • Open‑source tools and infrastructure for pathology AI
  • Tumour–immune microenvironment modelling
Adam Shephard

Research interests:

  • Computational pathology
  • Multi-modal learning (e.g. combining histology, radiology, and clinical data)
  • Deep learning for early cancer detection and biomarker discovery
  • Head and neck cancer, including oral and laryngeal precancers
  • Breast cancer, including ductal carcinoma in situ

Let us know you agree to cookies