Improving early diagnosis of major diseases such as cancer and dementia is a top national healthcare priority. Improving screening programmes by making better use of data and digital technologies is a promising way to achieve this goal but there are questions around explainability and trustworthiness of automated screening decisions. A framework to assess the validity of such methods is needed to ensure they are reliable and of clinical use.
This project will develop a framework to assess the reliability of AI for predicting the risk of breast cancer. The OPTIMAM Database managed by the RSNFT contains data for over 150,000 women attending breast screening. The size of the database and the long-term longitudinal nature of this data resource make it ideally placed to aid in predicting risk of breast cancer. This project will use this data resource using AI applied to mammograms and other patient data such as age, breast density and ethnicity and, where possible, imaging data from other modalities such as MRI. The performance of an AI algorithm developed at RSNFT will be evaluated and compared with traditional models. It is critical that AI algorithms used in healthcare are reliable, explainable and not biased to any sub-group of the population. This project will investigate the effect of a variety of factors (e.g. image processing, measurements inferred from the image manufacturer, age and ethnicity) on the performance of the algorithm and to improve the generalisability.
This project will develop methodology to assess the generalisability of AI based tools applied to medical imaging. This requires the development of new knowledge and fundamental research in a way which is well-suited to a PhD project. The project brings together metrological analysis and data science skills with medical imaging, and involves working with specialists from several different disciplines, preparing the candidate for a career in either medical research or data-intensive metrology, and contributing to the growing need for trained experts in AI and big data in healthcare.
The project is a collaboration between the University of Surrey (Radiation and Medical Physics Group), the National Physical Laboratory (Data Science and Medical Physics) and the Royal Surrey NHS Foundation Trust (Scientific Computing). The student will be predominately based at the University of Surrey and RSNFT with possibility of placements at NPL for up to 3 months a year.
Entry Requirements
UK applicants who hold a First or 2:1 UK honours degree in a relevant subject area, or a 2:2 alongside a good masters degree (a distinction is usually required).
If English is not your first language, you will be required to have an IELTS Academic of 6.5 or above (or equivalent), with no sub-test score below 6.
How To Apply
Applications can be made through our Physics PhD course page (https://www.surrey.ac.uk/postgraduate/physics-phd)
Please state the project title and supervisor clearly on all applications
Application deadline: 1 July 2022 or when suitable candidate is found
Start Date
1st October 2022
Continue with Facebook
