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.

external supervisors

Laura Coates, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford

William Tillett, University of Bath

BACKGROUND

Over one third of the UK population live with a musculoskeletal condition affecting the joints or spine. Amongst them, Psoriatic arthritis (PsA) and axial Spondyloarthritis (axSpA) are progressive and destructive forms of arthritis that affect 320,000 people in the UK. In the current diagnostic pathway, plain radiographs remain the mainstay of damage assessment as they are accessible, quick, require minimal radiation and are low cost compared to other imaging modalities such Magnetic Resonance Imaging.  Advances in Artificial Intelligence (AI) now open the opportunity to automate quantification of damage on radiographs. Machine Learning, and in particular Deep Learning (DL), has enabled artifact detection, grading medical imaging, and detection of pathological conditions. However, contrary to the state-of-the-art method in which imaging features are specified (hand-crafted) by the clinicians, DL offers opportunity to learn from data but in turn DL models are seen as ‘the black-box’ providing very limited interpretability. The exact mechanism (e.g. imaging features) cannot be explicitly isolated which in turn leads to difficulty to build clinical trust and subsequently it limits its rapid translation to routine clinical practice.

RESEARCH EXPERIENCE, RESEARCH METHODS AND TRAINING

The project encompasses:

  • Developing skills in AI/ML techniques with application to radiological imaging
  • Writing scientific reports and journal articles and presenting findings at the research conferences.

FIELD WORK, SECONDMENTS, INDUSTRY PLACEMENTS AND TRAINING

The Big Data Institute (BDI) is a world-renowned research centre and is housed in a brand new state-of-the-art research facility. Full training will be provided in a range of Health Data Science topics (Currently BDI is hosting CDT in Health Data Science for DPhil students). The student will have also opportunity to attend the research seminar offered at the BDI and the Institute of Biomedical Engineering (IBME) as the primary supervisor is a member of Imaging Hub at the IBME (https://eng.ox.ac.uk/biomedical-image-analysis/). 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.

PROSPECTIVE STUDENT

The ideal candidate will have:

  • A degree in Computer Science, 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 (in particular radiological imaging)
  • Experience or enthusiasm to work with clinicians.

Supervisor

  • Bartek Papiez
    Bartek Papiez

    Research Fellow (Medical Image Analysis and Machine Learning)