About the Project

X-ray Computed Tomography (XCT) is a critical non-destructive imaging tool used in fields ranging from materials science and biology to cultural heritage and forensics. Standard high-quality imaging requires a full 180 or 360-degree rotation of an object to acquire a massive number of radiographs. However, real-world experiments often face "limited data" conditions caused by strict time constraints, radiation dose concerns, or experimental rigs that physically block certain imaging angles.

This PhD project aims to create advanced XCT workflows by developing Artificial Intelligence (AI) and Machine Learning (ML) tools to support imaging before the reconstruction phase. The research will focus on:

• Data Upscaling: Using ML U-Net and latent diffusion models to generate synthetic projections that interleave with real data to improve image quality.
• Artifact Reduction: Developing paired and unpaired (e.g. Cycle GAN) models to remove noise and reconstruct artifact-free images from incomplete datasets.
• Software Integration: Incorporating these advances into the Collaborative Image Library (CIL) software using PyTorch, making the tools immediately accessible to the wider scientific community.

The student will work across the University of Warwick (WMG) and the Harwell Science and Innovation Campus, utilising high-performance computing (HPC) servers and data from large-scale facilities such as Diamond Light Source and ISIS Neutron and Muon Source.

Essential and Desirable Criteria

Essential:

• Applicants should hold or expect to gain a minimum of a 2:1 bachelor’s degree or equivalent in Computer Science, Engineering, Physics or Mathematical Sciences
• An MSc (merit or distinction) in a relevant subject would also be advantageous.
• Knowledge and experience with AI/Machine Learning in Python, preferably with images
• Location flexibility – to split time between University of Warwick and Harwell Science and Innovation Campus, Oxfordshire.

Desirable:

• Knowledge and experience with imaging systems (X-ray CT, MRI or similar)

Supervisors: Dr Jay Warnett (WMG); Prof Kurt Debattista (WMG); Prof Genoveva Burca (Diamond Light Source); Dr Edo Pasca (STFC Computing)

For informal enquiries please contact Dr Jay Warnett j.m.warnett@warwick.ac.uk

Funding Notes

Sponsor/ Supporting Company: Ada Lovelace Centre, STFC

3-year funding period

Standard UKRI Stipend – PGR Stipend & Fee Rates

Stipend Top-up £1,000 per year