Computational Methods and AI Models for Medical Image Analysis Using Generative and Foundation Models

Project Overview

This PhD project aims to develop advanced AI technologies that improve healthcare—enhancing clinical workflows, supporting diagnosis, and ultimately improving patient outcomes. The research will focus on designing deep learning models that are not only accurate and innovative, but also robust, explainable, and suitable for deployment in real clinical environments.

You will explore state-of-the-art methods in:

• Multimodal learning
• Generative models
• Foundation models
• Digital twins
• Vision–language models (VLMs)
• Medical Large language models (LLMs)

These techniques will be applied to diverse medical data types, including medical imaging, clinical text, and electronic health records.

What You Will Do

You will specialise depending on your expertise in developing reliable machine learning models using foundation models, generative techniques, and/or multimodal learning approaches. The project involves working with diverse medical imaging modalities such as ultrasound, MRI, CT, microscopy, OCT, and more. Collaboration with clinicians and healthcare providers ensures research translates to real-world clinical applications.

Expected Outcomes

The research will yield robust, adaptive AI algorithms capable of providing accurate diagnoses and personalised treatment plans. The models developed will be explainable and deployable in clinical settings, helping to bridge domain and knowledge gaps in medical imaging data.

Why This Matters

The project's innovations promise to revolutionise medicine by applying cutting-edge AI models to healthcare, driving improvements in diagnosis accuracy and patient outcomes while supporting clinicians with reliable digital tools backed by interdisciplinary and international collaboration.