A new doctoral training centre at University College London will train the next generation of researchers to embed medical imaging into wider healthcare systems, rather than treating scans as standalone diagnostic tools. Medical imaging—from X-rays to MRI scans—already underpins most modern diagnosis and treatment. But its full potential remains untapped. Images are often analysed in isolation, separate from patient records, lab results, or real-time data from surgical robots. This fragmentation limits how effectively imaging can guide decisions, especially in complex cases involving cancer, cardiovascular disease, or infections. The centre addresses this gap by training researchers to combine imaging with machine learning, data science, robotics, and human-computer interaction. If successful, the centre will produce a critical mass of scientists and engineers who can develop integrated imaging systems that pull together diverse data sources—scans, electronic health records, sensor feeds—to support clinicians in real time. This could improve diagnostic accuracy, enable more precise interventions, and streamline care pathways in areas such as neuroimaging, ophthalmology, and paediatric medicine. The research is applied and clinically focused, with direct pathways to NHS adoption and commercial translation.
View original technical description
We propose to create the EPSRC Centre for Doctoral Training (CDT) in intelligent integrated imaging in healthcare (i4health) at University College London (UCL). Our aim is to nurture the UK's future leaders in next-generation medical imaging research, development and enterprise, equipping them to produce future disruptive healthcare innovations either focused on or including imaging. Building on the success of our current CDT in Medical Imaging, the new CDT will focus on an exciting new vision: to unlock the full potential of medical imaging by harnessing new associated transformative technologies enabling us to consider medical imaging as a component within integrated healthcare systems. We retain a focus on medical imaging technology - from basic imaging technologies (devices and hardware, imaging physics, acquisition and reconstruction), through image computing (image analysis and computational modeling), to integrated image-based systems (diagnostic and interventional systems) - topics we have developed world-leading capability and expertise on over the last decade. Beyond this, the new initiative in i4health is to capitalise on UCL's unique combination of strengths in four complementary areas: 1) machine learning and AI; 2) data science and health informatics; 3) robotics and sensing; 4) human-computer interaction (HCI). Furthermore, we frame this research training and development in a range of clinical areas including areas in which UCL is internationally leading, as well as areas where we have up-and-coming capability that the i4health CDT can help bring to fruition: cancer imaging, cardiovascular imaging, imaging infection and inflammation, neuroimaging, ophthalmology imaging, pediatric and perinatal imaging. This unique combination of engineering and clinical skills and context will provide trainees with the essential capabilities for realizing future image-based technologies. That will rely on joint modelling of imaging and non-imaging data to integrate diverse sources of information, understanding of hardware the produces or uses images, consideration of user interaction with image-based information, and a deep understanding of clinical and biomedical aims and requirements, as well as an ability to consider research and development from the perspective of responsible innovation. Building on our proven track record, we will attract the very best aspiring young minds, equipping them with essential training in imaging and computational sciences as well as clinical context and entrepreneurship. We will provide a world-class research environment and mentorship producing a critical mass of future scientists and engineers poised to develop and translate cutting-edge engineering solutions to the most pressing healthcare challenges.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know