Using artificial intelligence to speed up cancer detection

The Secretary of State for Digital, Culture, Media and Sport visited the University today to hear how researchers are being trained to deploy artificial intelligence (AI) in the fight against cancer.

Baroness Nicky Morgan met PhD researchers involved in creating the next generation of intelligent technology that will revolutionise healthcare.

The University is one of 16 centres for doctoral training in AI funded by UK Research and Innovation, the Government agency responsible for fostering research and development.

The focus of the doctoral training at Leeds is to develop researchers who can apply AI to medical diagnosis and care.

Scientists believe intelligent systems and data analytics will result in quicker and more accurate diagnosis. Early detection is at the heart of the NHS plan to transform cancer survival rates by 2028. 

Baroness Morgan said: "We are committed to being a world leader in artificial intelligence technology and through our investment in 16 new Centres for Doctoral Training we are helping train the next generation of researchers.

"It was inspirational to meet some of the leading experts from medicine and computer science working in the new centre at Leeds University today. They are doing fantastic work to diagnose cancer quicker which could save millions of lives." 

Baroness Morgan spent time talking to the PhD researchers.

Baroness Nicky Morgan with Professor Lisa Roberts


Health data analytics

Anna Linton is a neuroscientist accepted onto the first cohort of the programme, which started in the autumn. 

She said: “The healthcare system can generate a vast quantity of information but sometimes it is assessed in isolation.

“I am interested in researching AI systems that can analyse medical notes, the results of pathology tests and scans and identify patterns in that disparate information and make order of it, to give a unified picture of a patient’s health status.

“That information will help the GP or other healthcare professional make a more precise diagnosis.”

Improving survival rates

Dr Emily Clarke is a hospital doctor specialising in histopathology, the changes in tissue caused by disease. She is an associate member of the doctoral training programme on a research scholarship from the Medical Research Council.

She wants to develop an AI system to improve the diagnosis of melanoma, a type of skin cancer whose incidence, according to Cancer Research UK, has more than doubled since the early 1990s. It has the fastest rising incidence of any cancer.

Melanoma is detected from the visual examination by a histopathologist of tissue samples taken during a biopsy. But up to one in six cases is initially misdiagnosed.

Dr Clarke said: “I am hoping we can develop an automated system that can help histopathologists identify melanoma. Diagnosing melanoma can be notoriously difficult – so it is hoped that in the future AI may help build a knowledge base of the types of cell changes that are suggestive of melanoma and provide a more accurate prediction of a patient’s prognosis."

Dr Emily Clarke


About 10 researchers will be recruited onto the training programme each year. When it is fully up and running, there will be 50 people studying for a PhD.

Professor Lisa Roberts, Deputy Vice-Chancellor: Research and Innovation, said: “The research at Leeds will ensure the UK remains at the forefront of an important emerging technology that will shape healthcare for future generations.

“There is little doubt that our researchers will be contribute to future academic and industrial breakthroughs in the field of AI, enabling industry in the UK to remain at the heart of innovation in AI.”

David Hogg, Professor of Artificial Intelligence and Director of the Leeds Centre for Doctoral Training, said: “The UK is a world leader in AI.

“But we can’t be complacent. We need to ensure there are enough talented and creative people with the skills and knowledge to harness and develop this powerful technology.

“The PhD researchers will be supervised by leading experts in computer science and medicine from the University and Leeds Teaching Hospitals NHS Trust. To harness the technology requires researchers with a strong understanding of medicine, biology and computing – and we aim to give that to them.”

The researchers joining the Leeds training programme come from a range of backgrounds: some are computer scientists and others are biologists or healthcare professionals but all are able to think computationally and are able to express problems and solutions in a form that can be executed by a computer.

The programme is hosted by the Leeds Institute for Data Analytics (LIDA), established with University investment to support innovation in medical bioinformatics, funded by the Medical Research Council, and Consumer Data, funded by the Economic and Social Research Council.

LIDA has now grown to support a portfolio in excess of £45 million of research across the University, bringing together over 150 researchers and data scientists. It supports the University’s partnership with the Alan Turing Institute, the UK’s national institute for data science and artificial intelligence.

The University has a strong track record in applying digital technologies to healthcare. In partnership with Leeds Teaching Hospitals NHS Trust, it is bringing together nine hospitals, seven universities and medical technology companies to create a digital pathology network which will allow medical staff to collaborate remotely and to conduct AI research. This is known as the Northern Pathology Imaging Co-operative and is supported by the Government's Industrial Strategy and UK Research and Innovation.

Leeds Teaching Hospitals NHS Trust is a leader in using digital pathology for cancer diagnosis.

Main photo shows some of the PhD researchers with - front, from left - Professor David Hogg, Director of the Leeds Centre for Doctoral Training, Baroness Nicky Morgan, Secretary of State for Digital, Media, Culture and Sport, and Professor Lisa Roberts, Deputy Vice-Chancellor: Research and Innovation.