Reasoning in Efficient Medical Vision–Language Models for Trustworthy AI in Healthcare – PhD in Computer Science (PhD Funded, student worldwide) Ref: 5821

Supervisors

Dr Lei Zhang, Department of Computer Science, University of Exeter

Professor Xujiong Ye, Department of Computer Science, University of Exeter

Medical imaging is central to the diagnosis and management of lung and abdominal diseases, including lung cancer, pneumonia, liver disease, and gastrointestinal disorders. While recent advances in Vision–Language Models (VLMs) have shown strong potential for joint image–text learning (enabling automatic report generation, question answering, and clinical decision support), most existing models:

• Primarily rely on pattern matching rather than clinical reasoning
• Are computationally expensive and difficult to deploy in real-world healthcare settings
• Provide opaque predictions, limiting trust and clinical acceptance

This PhD will address these challenges by investigating how explicit reasoning mechanisms can be embedded into efficient, lightweight VLMs, enabling accurate, interpretable, and deployable AI systems for multimodal medical data, including imaging (e.g., CT, MRI) and clinical text.

Research Aims

The main aim of this PhD is to enhance reasoning capabilities in efficient medical VLMs under realistic computational constraints.

Key objectives include:

• Designing parameter-efficient and lightweight VLM architectures for medical imaging and clinical text
• Developing causal, anatomical, and contextual reasoning mechanisms aligned with radiologists’ diagnostic workflows
• Studying trade-offs between efficiency, reasoning quality, and interpretability
• Creating evaluation benchmarks for reasoning-aware and efficiency-aware medical AI

Expected Outcomes

• A reasoning-enhanced, efficient medical VLM prototype suitable for clinical deployment
• High-impact publications in medical AI and machine learning venues

Entry requirements

Applicants for this studentship 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 an appropriate area of Computer Science, Biomedical Engineering, Information Technology, or a related discipline.

·       Motivation to conduct research with real clinical impact

·       Have practical experience working on AI for healthcare projects, utilizing PyTorch and/or TensorFlow libraries.

·       Exhibit proficiency in programming languages such as Python, C++, C, or Java.

·       Preference will be given to candidates with prior experience in presenting or preparing scientific manuscripts for publication in journals or conferences.

·       Evidence of ability to engage in scientific research and to work collaboratively as part of a team, including excellent communication skills in both written and spoken English, is required

If English is not your first language you will need to meet the English language requirements and provide proof of proficiency. Click here for more information.

How to apply

Apply now

To apply, please click the ‘Apply Now’ button above. In the application process you will be asked to upload several documents

•            CV

•            Letter of application (outlining your academic interests, prior research experience and reasons for wishing to undertake the project).

•            Research proposal

•            Transcript(s) giving full details of subjects studied and grades/marks obtained (this should be an interim transcript if you are still studying)

•            Two references from referees familiar with your academic work. If your referees prefer, they can email the reference direct to PGRApplicants@exeter.ac.uk quoting the studentship reference number.

•            If you are not a national of a majority English-speaking country you will need to submit evidence of your proficiency in English.

The closing date for applications is midnight on 28^th  Feb 2026.  Interviews will be held virtually in the week commencing 9^th March 2026.

All application documents must be submitted in English. Certified translated copies of academic qualifications must also be provided.

Summary