SCOTTISH scientists hope to use artificial intelligence to help diagnose skin cancer.

Researchers from the University of Dundee and NHS Tayside have developed an AI system which can detect common skin cancers with 'state-of-the-art accuracy.'

The pilot project used selected and pre-processed skin images but now, thanks to a £150,000 grant as part of a £50 million Westminster investment in AI, the project is to be extended by working on improving the technology to use image data from NHS clinics.

Researchers hope to eventually integrate a learning AI system into everyday clinical care in NHS Tayside.

Project leader, profesor Stephen McKenna, of the university's computing department, said: “Our interdisciplinary group is uniquely positioned to exploit and develop this technology for NHS benefit.

“Success in this area will be gradual, starting with goals such as clinical decision support for the most common benign lesions.

"Skin disease naturally lends itself to automated image analysis. Lesions can be photographed easily and then analysed with the help of deep learning technology.”

Professor Colin Fleming, consultant dermatologist at Ninewells hospital, said the AI development would bring many benefits. “Patients are delighted to be reassured about benign lesions, GPs could enjoy immediate education from such a system, and fewer patients would need to attend hospital appointments,” he said.

“NHS Tayside has 20 years of experience of large-scale digital capture of images in primary care, with assessment by secondary care dermatologists providing fast remote diagnosis, resulting in fewer appointments and improved patient satisfaction."

He said one in five GP consultations were related to skin disease and £100 million a year in NHS Scotland was spent on secondary care services treating skin disease. "[This illustrates] there is a pressing need to concentrate resources in this area of disease,” he added.

The 'Deep learning for effective triaging of skin disease in the NHS' project was one of 42 technologies and projects to receive funding as the first winners of the AI in Health and Care Awards.

Announcing the awards, Health Secretary Matt Hancock said: “AI has huge potential for transforming healthcare and freeing up medical professionals’ time - these awards are just the start of an exciting pipeline of new technology that will identify new ways to diagnose, screen and treat illnesses ranging from dementia and sepsis to antibiotic resistant infections and problems in pregnancy.”

The awards aim to support the NHS to become a 'world leader in the use of machine learning to harness benefits including faster and more personalised diagnosis and potential screening service efficiencies.'

Skin cancer is the most common cancer, with cases rising five per cent per year in the UK.

A university spokesman said diagnosis and management of suspected skin cancer represented over half of the workload of any specialist dermatology service, with primary care practitioners, often untrained in skin cancer recognition, lacking the necessary experience to distinguish innocent from cancerous lesions.

The Dundee team also includes the university’s professor Emanuele Trucco, a renowned expert in computer vision and image processing, and Charlotte Proby, professor of dermatology at the School of Medicine.