Dr Alan McWilliam, Dr Paul Bromiley, Dr Andrew Green, Prof T Cootes
No more applications being accepted
Competition Funded PhD Project (European/UK Students Only)
About the Project
Half of people born after 1960 will develop cancer at some point in their lives, the majority will undergo treatment with the intention of curing their disease. Modern cancer treatment takes many forms, including systemic therapies such as chemotherapy and targeted therapies such as radiotherapy. However, many patients are quite unwell as a result of their disease and their health may further deteriorate during treatment. Resultant weight loss, particularly the loss of skeletal muscle, sarcopenia, affects a patient’s ability to withstand treatment and, in chemotherapy, is known to be highly predictive of survival. Such a link is also expected in radiotherapy but has not yet been fully established. Assessment of sarcopenia before and during the care pathway would aid clinicians in selecting appropriate radiotherapy and supportive treatments to maximise quality of life and survival rates. However, current methods for sarcopenia assessment involve identifying a particular abdominal region on CT and manually drawing around the fat and muscle. This is extremely time-consuming and so sarcopenia screening is not currently a part of routine care.
The aim of this project is to develop state-of-the-art machine learning software that can automate the process of sarcopenia assessment. In previous work, we have developed software that can automatically identify the spine in 3D CT images, as part of a screening procedure for vertebral fractures. This method will be adapted to automatically identify the correct region of the abdomen for sarcopenia assessment by labelling particular vertebrae, and then utilizing machine learning to identify the fat and muscle in that region, from which a sarcopenia index will be derived. Evaluation will be performed on a database of several thousand lung cancer patients treated at the Christie Hospital, which is a patient group known to show significant frailties. This data would inform the first large scale analysis of the effect of sarcopenia on radiotherapy outcomes. Additionally, we will investigate changes sarcopenia scores for prostate patients from arm K of the STAMPEDE trial. Here we aim to providing a quantitative measure of the protective effects of metformin on muscle wasting due to hormone therapy.
The outcome will be a software package that clinicians can use to quickly perform sarcopenia assessment, allowing it to be integrated into routine radiotherapy care. The project is interdisciplinary and the student will be supervised by researchers in both the Division of Cancer Sciences and in the Division of Informatics, Imaging and Data Sciences.
Division of Cancer Sciences:
https://www.research.manchester.ac.uk/portal/en/facultiesandschools/division-of-molecular--clinical-cancer-sciences(0b0cf147-3dc8-4f46-a374-27dd6cca92f3).html
http://www.mcrc.manchester.ac.uk/
Division of Informatics, Imaging and Data Sciences:
https://www.research.manchester.ac.uk/portal/en/facultiesandschools/division-of-informatics-imaging--data-sciences(3508b831-4d64-4f79-8790-a50df943742c).html
Dr Bromiley’s personal page:
https://personalpages.manchester.ac.uk/staff/paul.a.bromiley/default.htm
Professor Cootes’ personal page:
https://personalpages.manchester.ac.uk/staff/timothy.f.cootes/personal.html
Entry Requirements
Applications are invited from UK/EU nationals only. Applicants must have obtained, or be about to obtain, at least an upper second class honours degree (or equivalent) in a relevant subject.
Funding Notes
This project is to be funded under the MRC Doctoral Training Partnership. If you are interested in this project, please make direct contact with the Principal Supervisor to arrange to discuss the project further as soon as possible. You MUST also submit an online application form - full details on how to apply can be found on the MRC DTP website www.manchester.ac.uk/mrcdtpstudentships
As an equal opportunities institution we welcome applicants from all sections of the community regardless of gender, ethnicity, disability, sexual orientation and transgender status. All appointments are made on merit.
Continue with Facebook
