PhD Research Studentships
Data-Efficient AI for Cancer Detection from Medical Images
| Supervisor: | Shaheer U. SAEED |
| Apply by: | 27 March 2026 |
| Start in: | September (Semester 1) |
Description
Background
Modern AI systems often rely on large datasets with consistent labels. In medical imaging, such datasets are difficult to obtain, as data are often limited, variable across hospitals, and expensive to label given limited expert time. As a result, models trained using standard deep learning approaches often fail to work reliably on new patients or data from different clinical settings.
This fully funded PhD studentship will address a central challenge in modern AI:
How can AI systems learn effectively when data are limited, inconsistent, or difficult to label?
Project Overview
The project focuses on developing data-efficient learning approaches for medical image analysis, with a particular emphasis on cancer detection. Rather than relying on large labelled datasets, the research will explore new ways of training AI systems that enable models to learn more effectively from limited supervision.
A key theme is moving beyond fixed training pipelines toward systems that can adapt how they learn over time; for example through self-refinement of solutions, learning across related tasks, or making use of feedback-driven signals. In this context, the project will explore ideas from meta-learning and reinforcement learning. These concepts will be introduced as part of the PhD; prior experience is not required, although it will be considered a plus.
The work will be grounded in real medical imaging problems, such as MRI-based prostate cancer detection, with scope to extend to other imaging settings and cancer types. Clinical collaborators will provide access to real-world imaging data and problem context, while the research itself remains focused on AI method development.
Overall, this PhD aims to build AI systems that learn reliably from limited data, with the potential to make a meaningful impact on real-world medical imaging applications.
The student will be based at the Centre for Bioengineering at Queen Mary University of London, within a collaborative, interdisciplinary environment and with close links to the Digital Environment Research Institute and the Barts Cancer Institute.
The studentship is fully funded, covering UK tuition fees and providing a competitive stipend for the duration of the PhD.
Candidate Profile
We are seeking highly motivated candidates with a strong background in computer science, machine learning, engineering, mathematics, or related fields. Applicants should be comfortable with programming (e.g. Python and modern ML frameworks) and keen to pursue high-quality, publishable research.
Applicants with prior publications and/or strong academic records, particularly from leading universities, will be prioritised.
Funding
Funded by: Queen Mary ResearchUK students only.
Home students only are eligible to apply for this PhD studentship of £21,874 p.a.
Eligibility
- The minimum requirement for this studentship opportunity is a good honours degree (minimum 2(i) honours or equivalent) or MSc/MRes in a relevant discipline.
- If English is not your first language, you will require a valid English certificate equivalent to IELTS 6.5+ overall with a minimum score of minimum score of 6.0 in each of Writing, Listening, Reading and Speaking).
- Note for EPSRC studentships; these studentships are open to those with Home and International fee status; however, the number of students with International fee status which can be recruited is capped according to the EPSRC terms and conditions so competition for International places is particularly strong.
- Candidates are expected to start in September (Semester 1).
Contact
For informal enquiries about this opportunity, please contact Shaheer U. SAEED.
Apply
Start an application for this studentship and for entry onto the PhD FT Medical Engineering full-time programme (Semester 1 / September start):
Please be sure to quote the reference "SEMS-PHD-713" to associate your application with this studentship opportunity.
| Related website: | https://www.sems.qmul.ac.uk/staff/s.saeed/ | |
| SEMS Research Centre: | ||
| Keywords: | Artificial Intelligence, Computer Science - Other, Computer Vision, Machine Learning, Bioengineering, Biomedical Engineering, Medical Statistics, Anatomy, Pathology, Radiology |