A Scottish consortium of partners from academia, industry, and the NHS has been awarded £4.4M for a project entitled InterdisciPlinary Collaboration for efficienT and effective Use of clinical images in big health care RESearch (PICTURES). Led by the University of Dundee, in partnership with the University of Edinburgh, Abertay University, NHS Scotland, and industry collaborators, the project received funding through an MRC Industry Collaboration Agreement, with additional support from EPSRC and as part of HDR UK.
The PICTURES project will leverage “big data” from Scotland’s national medical imaging archive to develop new clinical tools for disease diagnosis and risk prediction. Its core will research and develop underlying technologies, allowing researchers to work on vast amounts of medical imaging data in a secure environment and protect individual patient information. This activity will support two exemplar projects to prove and showcase the capabilities of a research database comprising approximately 30 million images from routine clinical scans across Scotland since 2006:
- Development of a method (in collaboration with industry partner Aidence) to detect warning signs of coronary artery disease and lung cancer using artificial intelligence to check patients’ CT chest scans, which can be converted into a clinical tool to support doctors on the front line in the NHS.
- Validation of a predictive tool using artificial intelligence methods to predict individual risk of future dementia among diabetic patients using MRI brain scans, genetic data and medical records.
By enabling research access to routinely collected and linked medical imaging data for the Scottish population, established simultaneously with foundational cybersecurity and privacy tools to guarantee patient confidentiality, PICTURES will ultimately develop a service to provide anonymised extracts of hundreds of thousands of clinical images for research.