(BRC) AI in medical imaging: addressing the issue of equity (Non-Clinical)

   Faculty of Biology, Medicine and Health

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof Sue Astley, Prof T Cootes, Dr Matthew Sperrin, Prof A Barton  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Artificial intelligence (AI) algorithms have been developed for many applications, including healthcare, where AI is used to interpret images, monitor patients and predict outcomes. The algorithms learn from examples, so high quality training data is essential for success. Data from participants in clinical studies is frequently used as this provides mechanisms for obtaining informed consent, controlled acquisition, high standards of reporting, and the availability of additional information. However, a weakness of this approach is that certain ethnic, age and gender groups participating in trials are under-represented in comparison to the wider population [Duma 2018]. Analysis of the participants in the UK Biobank, one of the world’s largest prospective cohort studies, has shown that they are not representative of the sampling population in terms of age, ethnicity or socio-economic status, and indicate a “healthy volunteer” bias [Fry, 2017].

This PhD project will investigate, across a range of medical applications of AI, whether algorithms trained on such datasets perform equally well on under-represented patient groups, and whether inequality in performance can be reliably identified and addressed so that their use in the wider population is fair. The student will work with four domain experts assessing the performance of previously developed AI methods for predicting breast density from x-ray mammograms, measuring the shape of bones in the hip, and analysing skin lesions. In particular, they will identify and benchmark performance in relation to ethnicity, age and gender, as appropriate for each application.

In the second phase of the project, the student will select the application domain that shows the highest degree of inequality of outcome, and develop methods to address this. Initially, the student will explore fair training strategies such as altering sampling of examples for training, selective data augmentation [Sharma 2020] and other bias mitigation approaches [Xu 2020].


Applicants must have obtained or be about to obtain a First or Upper Second class UK honours degree, or the equivalent qualifications gained outside the UK, in a relevant discipline.

Applicants must make direct contact with the primary supervisor before applying to discuss their interest in the project. It is your responsibility to make arrangements to meet with potential supervisors, prior to submitting a formal online application.  

How to Apply 

To be considered for this project you MUST submit a formal online application form - full details on how to apply can be found on the BRC website https://www.bmh.manchester.ac.uk/study/research/funded-programmes/manchester-brc-phd-studentships/ 

Your application form must be accompanied by a number of supporting documents by the advertised deadlines. Without all the required documents submitted at the time of application, your application will not be processed and we cannot accept responsibility for late or missed deadlines. Incomplete applications will not be considered. If you have any queries regarding making an application please contact our admissions team.

Equality, Diversity and Inclusion  

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. The full Equality, diversity and inclusion statement can be found on the website https://www.bmh.manchester.ac.uk/study/research/apply/equality-diversity-inclusion/  

Biological Sciences (4) Computer Science (8) Mathematics (25) Medicine (26) Physics (29)


Representation of Minorities and Women in Oncology Clinical Trials: Review of the Past 14 Years Narjust Duma, Jesus Vera Aguilera, Jonas Paludo, Candace L. Haddox, Miguel Gonzalez Velez, Yucai Wang, Konstantinos Leventakos, Joleen M. Hubbard, Aaron S. Mansfield, Ronald S. Go, and Alex A. Adjei Journal of Oncology Practice 2018 14:1, e1-e10
Sharma, Shubham, Yunfeng Zhang, Jesús M. Ríos Aliaga, Djallel Bouneffouf, Vinod Muthusamy, and Kush R. Varshney. "Data augmentation for discrimination prevention and bias disambiguation." In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 358-364. 2020.
Xu, Tian, et al. "Investigating bias and fairness in facial expression recognition." European Conference on Computer Vision. Springer, Cham, 2020.
Fry A, Littlejohns TJ, Sudlow C, Doherty N, Adamska L, Sprosen T, Collins R, Allen NE. "Comparison of Sociodemographic and Health-Related Characteristics of UK Biobank Participants With Those of the General Population". American Journal of Epidemiology, 2017;186(9):1026–1034, DOI: 10.1093/aje/kwx246

 About the Project