UK researchers have secured government funding to study the use of artificial intelligence (AI) for breast cancer screening in NHS hospitals.

The project, which will involve clinicians from St George’s, builds on previous research which showed that artificial intelligence could be as effective as human radiologists in spotting breast cancer from X-ray images. These early findings demonstrated the potential for this technology to assist clinicians in practice and hopefully improve outcomes for patients through early diagnosis.

Backed by funding through the Artificial Intelligence in Health and Care Award, the next stages of the project will aim to assess the diagnostic AI tool in a clinical setting to see how the technology could be integrated into the national screening programme in the future.

The partnership, which includes Imperial College London, Google Health, Imperial College Healthcare NHS Trust, St George’s University Hospitals NHS Foundation Trust, and the Royal Surrey NHS Foundation Trust, builds on previous work in which the researchers trained the algorithm on depersonalised patient data and mammograms from patients in the UK and US.

The findings, published in Nature in January 2020, showed the AI system was able to correctly identify cancers from the images with a similar degree of accuracy to expert radiologists.

Clinical setting

The funding has been awarded to Imperial College London and the three NHS Trusts for studies to determine the accuracy and fairness of an AI-model, to examine how radiologists and clinicians interact with the system, and assess its use in a clinical setting.

All research will be subject to National Research Ethics approval before commencing, and the AI system would not be used in patient care or to make clinical decisions during the study. Clinicians will remain in full control of patient care pathways at all times.

One in eight women in the UK will be diagnosed with breast cancer in their lifetime, with the risk increasing with age. Early detection and treatment provide the best outcome for women, but accurately detecting and diagnosing breast cancer remains a significant challenge.

The funding of this project is one of a number announced today by the Department of Health and Social Care, NHSX and the National Institute for Health Research. The Artificial Intelligence in Health and Care Award is making £140 million available over four years to accelerate the testing and evaluation of artificial intelligence technologies which meet the aims set out in the NHS Long Term Plan.

The AI Award is one of the programmes that make up the NHS AI Lab, led by NHSX and delivered in partnership with the Accelerated Access Collaborative (AAC) and National Institute for Health Research (NIHR). The Award is part of the £250 million funding given by the Department for Health and Social Care to NHSX to establish an AI Lab aimed at improving the health and lives of patients.

Next steps

Professor the Lord Ara Darzi of Denham, Director of the Institute of Global Health Innovation at Imperial College London and chief investigator on the project, said: “Our early work in this area has shown that using algorithms to screen for breast cancer is feasible. This next step will be our first real life test of AI as part of a national screening programme.

“AI is not designed to replace healthcare workers, whose clinical training and experience are invaluable to the NHS. Ultimately, we hope these tools could help to reduce the current burden on radiologists and the NHS, improving outcomes for patients through earlier detection and treatment of cancer.”

Dr Mamatha Reddy and Dr Lisanne Khoo, Consultant Radiologists leading the study at St George’s, said: “St George’s is home to the South West London National Breast Screening Programme, where up to 52,000 screening mammograms are undertaken every year. We hope that the study, which will assess how AI could be safely implemented to assist our screening programme, will improve early breast cancer diagnosis in the longer term, while also ensuring we continue to provide the best possible service for our patients.”

Dr Deborah Cunningham, Consutant Radiologist at Imperial College Healthcare NHS Trust, said: “We are very excited to be able to work with colleagues assessing this new AI tool in screening mammogram interpretation in a real-world situation for the first time. There is a national shortage of clinicians qualified to interpret screening mammography and this product has the potential to mitigate this problem, while improving early breast cancer diagnosis, benefiting a large number of asymptomatic well women.”

Susan Thomas, Clinical Director at Google Health said: “Artificial intelligence has shown great potential to dramatically improve both access and quality of healthcare, and the next step is to assess how this technology could be safely implemented in real-world clinical settings. The NHS is a global leader in providing a high-quality national screening programme for breast cancer. These studies will help provide a comprehensive evaluation of a technology that has potential to improve the consistency and sustainability of breast cancer screening programmes around the world.”

Lord Darzi added: “It is only through these kinds of partnerships, which bring together expertise from academia, healthcare and the commercial sector, that we can leverage the very best technology for the greatest benefit to global health.”