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.

Kennedy Trust Prize Studentships

Project overview

A major hurdle in the development of disease modifying osteoarthritis (OA) drugs is that there is no robust quantitative biomarker for the disease.  To address this, we have developed a radio-contrast agent that will allow cartilage, the main tissue damaged, to be visualised by computed tomography (CT) scans. Image processing methods are required to consistently extract quantitative cartilage measurements and features from the high resolution CT scans, which will allow disease progression or treatment efficacy to be monitored. The development of an automated (or semi-automated) pipeline for the quantification of the change in cartilage morphology is critical in the development of the current imaging technique as the biomarker for OA. 

In this project, several computational aspects of longitudinal volumetric (3D) image analysis will be investigated to develop this pipeline to be robust, for example, to changes in resolution and to different scanners. Firstly, the correct alignment of the joints in the consecutive scans will need to be estimated to compensate for any differences in positioning and growth. Secondly an accurate segmentation of the articular cartilage from the bone is required to localise the tissues of interest. Finally, (bio-) feature extraction from the high spatial resolution imaging to derive quantitative biomarkers that can be validated against the current gold standard of post-mortem histology. This project has potential to both investigate machine learning approaches to medical image analysis in addressing clinical problem and finding image-derived markers to monitor subtle changes apparent during disease progression and or treatment as a radiographic biomarker for OA.

Training Opportunities

The student will attend bi-weekly reading group meetings on machine learning in medical image analysis, and will be expected to attend relevant seminars within the wider University. Subject-specific training will be received through the group's weekly supervision meetings. Exposure to the wider OA field will be through the weekly meetings of the ARUK Centre of Excellence for Osteoarthritis Pathogenesis. Additionally, the group participates in the yearly Oxford Biomedical Imaging Festival, which encompasses the broader range of diseases and imaging applications. It is expected that the student will present their research in at least one international conference (e.g. Medical Image Computing & Computer Assisted Intervention).


The department accepts applications throughout the year but it is recommended that, in the first instance, you contact the relevant supervisor(s) or the Directors of Graduate Studies who will be able to advise you of the essential requirements.

Interested applicants should have or expect to obtain a first or upper second class BSc degree or equivalent, and will also need to provide evidence of English language competence. The University requires candidates to formally apply online and for their referees to submit online references via the online application system.

The application guide and form is found online and the DPhil or MSc by research will commence in October 2019.

When completing the online application, please read the University Guide.


Ngee Han Lim, Kennedy Institute, University of Oxford

External Supervisor

Bartlomiej PapiezBig Data Institute, NDPH

Project reference number #201907