University of Birmingham Featured PhD Programmes
University of Kent Featured PhD Programmes
University of Edinburgh Featured PhD Programmes
University of Glasgow Featured PhD Programmes
University of Bristol Featured PhD Programmes

Applying AI to quantifying gait and joint loading in a mouse model for knee osteoarthritis using biplanar X-Ray videography, machine learning and force recordings


Project Description

Osteoarthritis (OA) is a joint disease leading to impaired function and changes in gait. Several mouse models for OA exist, but exactly how gait and joint function is affected by the disease in these models is unknown. This is largely because the study of musculoskeletal biomechanics in mice is technically difficult and ideally uses X-Ray videography to visualise the skeleton.

The Institute of Ageing and Chronic Disease (IACD) houses a state-of-the-art biplanar X-Ray system allowing to record, at high frame rates, the 3D motions of the skeleton. Extracting useable kinematics data form the raw recordings is time-consuming and labour intensive, which is the challenge to be addressed by this PhD. Artificial intelligence (AI) such as deep learning (DL) techniques will be developed to automatically extract kinematics data from new recordings as well as from a large library of mice recordings already available.

The developed new DL models will allow us to study the gait in terms of kinetics and kinematics by combining the resulting data with 3D measurements of ground reaction forces of a sub-set of trials using a small force plate available at IACD.

This project will require good skills in machine learning and image processing techniques and programming, but also the capacity to learn locomotor biomechanics.

The aims of this project are two-fold. Firstly, it will develop a tool to automatically extract useable kinematic data from mouse X-Ray recordings with minimal manual input, allowing for a detailed analysis of large data sets. Secondly, it will quantify normal (knee) joint function as well as impaired function as a result of OA which will help to understand the disease much better, from a biomechanical point of view than we do to date.

This project fits into the University’s Key Research Themes of Healthy Living/Ageing and Digital.

The student will receive core training from the Liverpool Doctoral College as well as the IACD. This training spans all three years of the PGR programme, and includes Inductions (general and safety), E-learning (e.g. Good Research Practice), seminars (presenting as well as attending), outreach opportunities and journal clubs. The programme is flexible, and the student can tailor training to his/her needs to a large extent, including (but not limited to) opportunities detailed on the website of the Liverpool Doctoral College.

The student will have two academic advisors and progress will be monitored by them during yearly meetings. The student will also have recorded meetings with the supervisory team and will benefit from existing infrastructure to keep track of their activities.
The skills the student learns will make them highly employable in the field of biomechanics, artificial intelligence, medical imaging, and biosciences.

Dr Kris D’Aout,
Dr Yalin Zheng,
To apply please send CV and covering letter to Dr D’Aout with copy to

The Institute of Ageing and Chronic Disease is fully committed to promoting gender equality in all activities. In recruitment we emphasize the supportive nature of the working environment and the flexible family support that the University provides. The Institute holds a silver Athena SWAN award in recognition of on-going commitment to ensuring that the Athena SWAN principles are embedded in its activities and strategic initiatives.

Funding Notes

This is an IACD funded 3-year studentship that covers tuition fees for UK/EU students at the current rate of £4,327 per year, a stipend of £14,777 per year and total research costs of £19,500.

References

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-44.
Luo Y. LSTM Pose Machines. https://arxiv.org/abs/1712.06316
Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J. LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems. 2016;PP(99):1-11.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2019
All rights reserved.