29 Apr 19. £4.4m PICTURES study

PICTURES study to create new platform to help tackle major health issues.

Each year millions of clinical images are generated in Scotland through routine examinations at hospitals and stored in a huge database. The Scottish national imaging database currently has about 30 million different images collected since 2006.

Now a major new project led by the University of Dundee, working with partners including the University of Edinburgh, Abertay University and NHS Scotland, is aiming to turn that database into a powerful research tool that could help tackle health conditions including lung cancer and dementia.

The PICTURES project has been awarded £4.4 million in funding from the Medical Research Council and industry partners.

The PICTURES project builds upon previous work from the University of Dundee, the University of Edinburgh, and NHS Scotland, which has created a secure national database of anonymous data for use in research.  It will look at analysing the millions of clinical images that are already routinely collected, such as X-rays, CT, MRI, ultrasound and nuclear medicine and retinal image scans. These are generally used for the clinical care of individual patients. But researchers can see a huge additional benefit which technology can now unlock, searching for warning signs which can predict the development of diseases.

Clinical images are now core diagnostic technologies. These images can support many important areas of research to improve any or all of diagnosis, monitoring of disease progression and response to treatment.Access to the vast bank of `real world’ images can offer a huge boost to research into major diseases and conditions, and that is what we are looking to develop through the PICTURES study, initially using lung cancer and dementia as exemplar projects

The PICTURES project has three main elements. 

1. The Core Project, led by the University of Dundee (Dr Emily Jefferson of the Health Informatics Centre, Prof. Douglas Steele and Dr Alex Doney of the School of Medicine, and Prof. Emanuele Trucco of the School of Computing), in collaboration with Abertay University (Dr Natalie Coull of the School of Design and Informatics) and the University of  Edinburgh (Prof. Edwin Van Beek of Edinburgh Imaging Facility QMRI and Prof. Mark Parsons of the Parallel Computing Centre), will research and develop the underlying technologies, allowing researchers to work on vast amounts of data, in a secure environment and protecting individual patient information. 

This technology will support two medical exemplar projects, which will prove and showcase the capabilities of the research database.

2. The first clinical project will develop a method to detect warning signs of heart disease and lung cancer using AI to check patient’s chest scans. This project will work in partnership with international experts from an industry partner, Aidence, to convert the research into a clinical tool which can be used to support doctors on the front line in the NHS.

3. The second project will predict using AI methods individual patient risk of dementia in people with diabetes, using MRI brain scans, genetic data and medical records to find the most important variables found. The predictive tool will be validated on the large image dataset provided by the core programme.

It is very exciting to be able to develop software tools (also known as artificial intelligence) to enhance the diagnostic potential of CT scans in the chest and MRI scans of the brain, which currently don’t routinely assess cardiac or dementia risk in these patients. By having these tools provide information to clinicians, earlier treatment and management changes will improve health outcomes in the future. 

Access to these 'real world’ images will be extremely valuable for research, and the PICTURES project will break new ground in a number of areas:

• Primarily it will develop cybersecurity and privacy tools to guarantee patient confidentiality; researchers may access the data they need, but will never be aware of personal details.
• Secondly, the sheer size of these imaging datasets is technically challenging.
• Thirdly, PICTURES will allow researchers to search for sample data which exactly matches the problem they wish to study.
• Using the foundation blocks already in place from previous research, PICTURES will extend, scale and enhance innovative open source software to query a research copy of the Scottish National Imaging Database, securely hosted by the University of Edinburgh, and provide anonymised extracts of hundreds of thousands of images for research.
• PICTURES will also develop this software to query imaging data linked to genomic data securely hosted by the University of Dundee. 

Ultimately, this will position Scotland at the head position in these fields of medical research, as well as creating technical tools which other researchers may adopt and use world-wide.