The use of AI in breast cancer screening could save many lives, according to a landmark study.

The research, led by Imperial College London, involved 175,000 women – the largest NHS study to date. The findings clearly show the advantages of using AI to identify breast cancer earlier, reduce errors and help deliver life-saving treatment sooner.

Breast cancer is the most common cancer in the UK, with one woman diagnosed every 10 minutes and roughly 55,000 new cases per year. Diagnosis usually follows a mammogram or breast screening, with images assessed by clinical radiologists.

The NHS is under pressure as there is currently a 29% shortfall of radiologists in the UK – almost 2,000 – and this is predicted to rise to 39% by 2029.

The study looked at the potential of using AI technology to assess these scans and reduce radiologists’ workload.

According to Professor Deborah Cunningham, a consultant radiologist at Imperial College Healthcare NHS Trust and study co-author, the technology could help free up a radiologist’s time to perform more hands-on tasks and allow them to “spend more time deploying their skills and working with colleagues and patients to improve cancer diagnosis and outcomes”.

In the UK, breast cancer scans are typically assessed by two radiologists. Each reads the scan separately, with the second reader either knowing or not knowing the first reader’s decision. The research looked at how two human readers compared to one human reader plus one AI reader, using AI software developed by Google.

There were three parts to the study. The first was a retrospective study of 125,000 women, aged 50 to 70, from five NHS screening services. They were screened in 2015-16 over a 39-month follow-up period. The final analysis included 115,973 breast cancer scans. 

AI as the second reader achieved better results than the first human reader, with the cancer detection rate (CDR) rising from 7.54 (human) to 9.33 (AI) per 1,000 women. AI also identified more invasive cancers, significantly reduced false positives and detected 25% of interval cancers (cancers detected between healthy scans). The technology performed particularly well for first screens, with 39.3% fewer recalls and a 8.8% higher CDR. AI also reduced the time taken to read a scan by almost a third.

The second part of the study looked at 9,266 current cases at two screening services at 12 sites in London. AI consistently demonstrated a higher recall rate than the humans did and demonstrated significant time savings by completing a read in about 17.7 mins compared to 2.08 days for the first human reader.

The third part of the study looked at the use of AI in arbitration in 50,000 women. Arbitration is when the first and second readers don’t agree on the diagnosis and a third reader analyses the scan and makes a final decision. This is the first time AI has been used in this scenario. It found that AI fared comparably to the humans but, on balance, reduced the overall screening workload.

The researchers suggest that further development of the AI tool could potentially lead to the detection of cancers earlier than with two human readers. 

Study co-author Dr Hutan Ashrafian from the Institute of Global Health Innovation said: “This is the closest AI has ever come to helping reduce breast cancer deaths within the NHS, so the potential for the NHS to take this forward is significant.”

Dr Susan Thomas, clinical director at Google and study co-author, said: “Early detection is our most powerful tool in the fight against breast cancer, and these findings mark a genuine turning point. This is the first time that we’ve been able to rigorously test doctors and AI working alongside each other in a clinical setting.”

The research was conducted by Imperial College London, Google, the universities of Cambridge and Surrey, NHS Trusts at Cambridge University Hospitals, Imperial College Healthcare, the Royal Marsden, the Royal Surrey and St George’s University Hospitals, and the AIMS public engagement group. 

The findings are published in two linked papers – Prospective evaluation of artificial intelligence integration into breast cancer screening in multiple workflow settings: the GEMINI study – published in the journal Nature Cancer.