Precision Medicine and the PICTURES study

To improve healthcare and help people lead better lives, we work across disciplines to advance the capabilities of Precision Medicine. Precision Medicine is based on identifying subgroups of patients with distinct mechanisms of disease or responses to treatments. Combined with Artificial Intelligence, which can automate the analysis of vast amounts of health data and link it to genomics data, it is feasible to genotype whole populations. Precision Medicine has the potential to create clinical decision tools to optimise drug and treatment selection and predict disease risk.

Our Precision Medicine research unites our strengths in public and global health, genomics, translational and fundamental biology and medicine, computing and mathematics research, innovative clinical trials and access to the most comprehensive patient datasets and Safe Haven environments. In the PICTURES study, we bring our expertise to a collaboration with the Universities of Edinburgh and Abertay, the NHS Scotland and industry partners funded by the MRC and EPSRC.

The study makes use of a vast data resource of 30 million clinical images collected by the NHS from the entire Scottish population since 2006, such as X-rays, CT, MRI, ultrasound, nuclear medicine and retinal images, and applies Artificial Intelligence (AI) to recognise ‘warning signs’ in the images to predict the health of the patient and risks of disease.

Professor Emily Jefferson, Director of the Health Informatics Centre at Dundee, said, “Clinical images are now core diagnostic technologies. These images can support many important areas of research to improve any or all diagnosis, monitoring of disease progression and response to treatment."

To deal with the technical challenges posed by the sheer size of these imaging datasets, PICTURES is researching and developing systems which can scale up to handle ever-growing datasets and develop cybersecurity and privacy tools to guarantee patient confidentiality. It is combining the information of the imaging datasets with rich phenotype data from long-term comprehensive electronic healthcare records and extensive genomic data available to the GoDARTS bioresource. The results will give doctors clinical decision tools which make use of the full potential of the imaging data in routine care and greatly enhance the utility of routine scans for personalised treatment selection and disease prevention.

The project is integrated with other major research initiatives in this area, such as the £7M NIHR Global Health Chennai-Dundee Diabetes Unit and the £1.1M EPSRC Dundee-Edinburgh project using VAMPIRE (Vascular Assessment and Measurement Platform for Images of the REtina) to develop multimodal retinal biomarkers for vascular dementia, nationally within the HDR-UK programme which unites health data from across the whole UK and with the iCAIRD (The Industrial Centre for Artificial Intelligence Research in Digital Diagnostics) partnership.

Led by Professor Emmanuele Trucco, VAMPIRE is an international collaborative project of several image processing groups and clinical centres in Europe, Asia and the UK. The system aims to provide efficient and reliable detection of retinal landmarks (optic disc, retinal zones, main vasculature), and quantify key parameters used frequently in investigative studies, currently vessel width, vessel branching coefficients, and tortuosity. The ultimate vision is to enable efficient quantitative analysis of large collections of retinal images acquired from multiple instruments.

Using the foundation blocks already in place from previous research, PICTURES provides anonymised extracts of hundreds of thousands of images for research. The project develops the software to query imaging data linked to genomic data securely hosted at Dundee. Ultimately, this will position Scotland in a globally leading position in these fields of medical research, as well as creating technical tools which other researchers may adopt and use world-wide.