AI-Driven Decision Support for Diagnostic Imaging

Full Description

Accurate interpretation of radiological images is central to effective disease diagnosis and treatment planning.

However, modern medical imaging data are increasingly complex, and even experienced radiologists face challenges arising from subtle visual patterns, inter-observer variability, cognitive bias, and workload pressure.

These factors can lead to diagnostic uncertainty or error, with significant consequences for patient care.

This PhD project aims to develop next-generation artificial intelligence (AI) and machine learning (ML) methods that act as robust decision-support tools for diagnostic imaging.

The overarching goal is not to replace clinicians, but to augment radiologists’ expertise, improving diagnostic accuracy, consistency, and efficiency across a range of clinical imaging tasks.

Aims:

To design and develop advanced AI/ML models for automated analysis and interpretation of radiological images.

To create clinically meaningful decision-support outputs that align with real-world diagnostic workflows.

To investigate model reliability, interpretability, and generalisation in clinically realistic settings.

Methods:

The project will involve close collaboration with practising radiologists to curate high-quality, anonymised medical imaging datasets.

State-of-the-art techniques in deep learning, computer vision, representation learning, uncertainty modelling, and explainable AI will be explored and extended.

Emphasis will be placed on clinically grounded evaluation, including performance benchmarking, robustness analysis, and human–AI interaction.

Indicative Deliverables:

Novel AI/ML algorithms tailored for diagnostic imaging.

Validated decision-support models with interpretable outputs.

Open-source software prototypes and peer-reviewed publications.

Contributions to translational AI research with real clinical impact.

The research will be conducted within the internationally recognised Visual Computing Research Group at Cardiff University, with clinical collaboration from the Department of Clinical Radiology at the University Hospital of Wales and Great Ormond Street Hospital for Children NHS Foundation Trust.

The project offers an exceptional opportunity to work at the interface of AI, medical imaging, and healthcare innovation.

Keywords:

Artificial Intelligence, Machine Learning, Computer Vision, Medical Imaging, Diagnostic Radiology, Deep Learning, Explainable AI

Contact for information on the project:

Professor Hantao Liu (LiuH35@cardiff.ac.uk)

Studentship information

The School of Computer Science and Informatics Studentships are for 3.5 years full time UK Home and EU Students only.

This covers fees and stipend at the standard UKRI rate.

Please note however that if you are EU applicant the following postgraduate research fee discount scheme for EU students is available, however does not apply to part time students.

If EU applicants intending to study full time wish to apply for this discount, they will need to ensure they are fully eligible.

To enquire further as to whether or not you are eligible, please contact the central admissions team via: admissions@cardiff.ac.uk as the School will only pay the Home Fee rate

The project is open to both Home and EU students, however the School will only fund the Home Fee rate

Mode of Study

Full-time only.

How to Apply

You can apply online - consideration is automatic on applying for a PhD with a 1st July 2026 start date.

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In the funding field of your application, indicate “I am applying for 2026 COMSC funded PhD Studentship in Computer Science and Informatics”, and specify the project title and supervisors of this project in the text box provided.

Please be aware that you cannot apply for multiple COMSC Studentship projects as part of one application via the application portal, you have to apply for each project in one separate individual application.

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or another subject with significant quantitative component e.g. maths, engineering, economics, psychology.

Applicants with appropriate professional experience are also considered.

Applicants must demonstrate English language proficiency. Students who do not have English as a first language must prove this by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. A full list of accepted qualifications is available here: https://www.cardiff.ac.uk/study/international/english-language-requirements/postgraduate

If you are interested, please contact [Professor Hantao Liu; LiuH35@cardiff.ac.uk] sending your CV in the first instance.

The application process requires you to develop a research proposal jointly with the supervision team, prior to the deadline.

If needed, we can make further suggestions for specific research projects within the above areas.

Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below.

Please submit your application via Computer Science and Informatics - Study - Cardiff University

In order to be considered candidates must submit the following information:

• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal. Your research proposal should not exceed 2000 words, including references and bibliography.

• A personal statement (as part of the university application form, or as a separate attachment, if you prefer).

• A CV. Guidance on CVs for a PhD position can be found on the FindAPhD website.

• Qualification certificates and Transcripts - original and English translation, if applicable.

• References x 2 which should be academic references. Please note you need to provide the reference documents as part of your application.

• Proof of English language (if applicable).

Interview – Candidates who demonstrate the best fit for the role will be invited to an interview (in person or remote).

Application Deadline

23:59 on 13th February 2026

Start Date: 1 July 2026