Development of image analysis methods and software to study musculoskeletal diseases using artificial intelligence (AI)

Musculoskeletal (MSK) diseases affect an increasing number of the population globally. In the UK, on average 3 in 10 people are affected, which increases to 1 in 2 in the age group 65+. MSK diseases are a major cost to healthcare systems world-wide. Large numbers of medical images are collected daily as part of clinical practice as well as by population-based studies (e.g. UK Biobank). Currently, medical images are often underutilised in clinical practise and research into musculoskeletal diseases. To effectively use the bone shape information provided by the images, the image information needs to be quantified. Traditionally, a small set of lengths and angles served this purpose, discarding potentially useful shape information.

This project builds on the team’s extensive experience in the field of quantifying bone shape using Statistical Shape Models (SSMs). The student will explore advanced machine learning and neural network techniques to locate and measure bones in medical images. The result will be an automated software pipeline for both obtaining geometric measurements of bones and quantifying bone shape using SSMs. This may lead to the identification of novel MSK biomarkers.

The student will join a well-established research group, and will gain extensive experience of working in an interdisciplinary team. They will learn about state-of-the-art machine vision algorithm development for clinical imaging problems. The student will be placed in the translational space, and will have the opportunity to learn more about the pathway of progressing research towards impact in clinical practice.

Training/techniques to be provided:
The supervisors will enable the student to receive training in computer vision and machine learning techniques as well as in quantitative data analysis. Transferable skills training will be provided by the dedicated researcher development team of the host faculty. A researcher development framework is in place to help the student decide what training they need at each stage of their research journey.

Entry Requirements:
Applicants are expected to hold, or about to obtain, a minimum upper second class undergraduate degree (or equivalent) in a scientific subject such as Physics, Engineering, Mathematics, Computer Science or equivalent. A Master’s degree in a relevant subject and/or experience in computer vision or machine learning is desirable.

For international students we also offer a unique 4 year PhD programme that gives you the opportunity to undertake an accredited Teaching Certificate whilst carrying out an independent research project across a range of biological, medical and health sciences. For more information please visit www.internationalphd.manchester.ac.uk