Applying novel imaging methods and machine learning techniques to advance in-vivo knee biomechanics analysis

3 years full time start date July/October 2024

Project Summary

This is an opportunity to work on an exciting project focussed on machine learning applied to in-vivo knee biomechanics working with Cardiff University, Imperial College, Katholieke Universiteit Leuven and University of Florida.

Osteoarthritis (OA) is a serious disease of the joints. It is the leading cause of disability globally, with increasing burden with the aging population. In the UK, 100,000 patients/year require total knee replacement to treat their OA with one-in-four awaiting treatment being medically defined as living in a state worse than death. Despite the prevalence of total knee replacement globally, unfortunately,

one-in-five patients are dissatisfied after their surgery. Knee function during activities of daily living is 30% worse for these dissatisfied patients, for example, knee instability leads to disability and can lead to falls.

 Current methods rely on marker-based motion capture to measure knee function (motion and loading) however this technique is not capable of measuring the translations at the knee due to soft tissue errors. As an innovative response to this limitation, Dynamic Biplane X-Ray Imaging (DBX), developed at Cardiff, captures real time moving images of a volunteers knee joint during different activities. This combined with 3D models of bones or implants, through 3D to 2D image registration, enables direct measurement of in-vivo knee biomechanics. However current manual registration techniques limit efficiencies in data processing. For this studentship, a machine learning approach will be applied to develop a robust image registration pipeline working with University of Florida.

As part of a large EPSRC project, “Multi-platform pipeline for engineering human knee joint function” (ENGIN KNEE) working with Imperial College London, we will be recruiting healthy volunteers, patients undergoing total knee arthroplasty and patients experiencing post-surgical instability. Novel machine learning techniques will be applied towards automating the image registration pipeline.

 In year 1 the student will conduct a literature review, gain experience in in-vivo kinematics protocols (MRI/Motion Capture/DBX), working on integrating machine learning approach developed by University of Florida and produce research abstracts reported at international conferences (the International Society of Biomechanics/Orthopaedic Research Society). Year 2 will focus on in-vivo data collection and applying machine learning techniques to the image registration pipeline. Year 3 will focus on verification on the applied machine learning pipeline to understand knee kinematics and how it is affected by instability, and this is expected to produce at least 3 high quality research papers. The candidate would have funded for 3 years which may lead to further opportunities for post-doctoral research positions.  

Research Environment

This studentship will be a part of a international team between Cardiff University, Imperial College London, KU Leuven and University of Florida. The successful applicant will join an international team, based in the world-leading Musculoskeletal Biomechanics Research Facility (MSKBRF) at Cardiff. The student will have regular supervisory meetings and will work alongside other PhD researchers within the research team and the School of Engineering to ensure good networking and support opportunities.

Learning and Development Opportunities

The studentship will be enhanced through training in-vivo X-Ray data collection and analysis (at Cardiff), with access to training courses in the Doctoral Training Academy.  Training throughout the PhD will focus on developing the necessary skills to complete the PhD as well as transferable skills that will be of benefit within the wider engineering community.

Amount of Funding

Tuition fees at the home/EU rate (£4,806 in 2024/5) and an annual stipend equivalent to current Research Council rates (£19,237 stipend for academic year 2024/5), plus support for travel/conferences/consumables.

Academic Criteria

Candidates should hold a good bachelor’s degree (first or upper second-class honours degree) or a MSc/MEng degree in an area of Mechanical Engineering, Biomedical Engineering, Computer Science, or other relevant areas.

Knowledge of machine learning for image processing is desired. Previous laboratory or field experience, MATLAB/Python coding and an interest in applying this technology to the field of biomechanics to understand joint function would be advantageous.

Applicants whose first language is not English will be required to demonstrate proficiency in the English language (IELTS 6.5 or equivalent)

Contact for further information

Please contact Dr Williams [Email Address Removed] or Prof Holt [Email Address Removed] to informally discuss this opportunity

How to apply

Applicants should submit an application for postgraduate study via the Cardiff University webpages (http://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/engineering ) including;

·        an upload of your CV

·        a personal statement/covering letter

·        two references (applicants are recommended to have a third academic referee, if the two academic referees are within the same department/school)

·        Current academic transcripts

Applicants should select Doctor of Philosophy (Engineering), with a start date of July or October 2024

In the research proposal section of your application, please specify the project title and supervisors of this project and copy the project description in the text box provided. In the funding section, please select "I will be applying for a scholarship / grant" and specify that you are applying for advertised funding, reference CH- MSKBRF-24

Deadline for applications

12th June 2024. We may however close this opportunity earlier if a suitable candidate is identified.