Interim analysis from MASAI (Mammography Screening with Artificial Intelligence) found that AI detected 20 per cent more cancers compared with standard screening, without affecting false positives. The trial, led by researchers from Lund University in Sweden, has been published in The Lancet Oncology.
Screening examinations currently undergo a double reading, which is a review by two breast radiologists to ensure a high sensitivity. Workforce shortages, however, can put the screening service at risk. In January 2023, the National Breast Imaging Academy in England reported that 12 per cent of mammographic workforce posts were vacant and staffing had not increased in line with demand.
MORE FROM MEDICAL & HEALTHCARE
“In our trial, we used AI to identify screening examinations with a high risk of breast cancer, which underwent double reading by radiologists. The remaining examinations were classified as low-risk and were read only by one radiologist. In the screen reading, radiologists used AI as detection support, in which it highlighted suspicious findings on the images”, said Kristina Lång, lead researcher and associate professor in diagnostic radiology at Lund University.
The 80,033 women aged 40-80 included in the safety analysis were randomly allocated into two groups: 40,003 women in the intervention group that underwent AI-supported screening and 40,030 in the control group that underwent standard double reading without AI support.
As well as detecting 20 per cent more cancers compared with standard screening, the screen-reading workload for radiologists was reduced by 44 per cent. The number of screen readings with AI-supported screening was 46,345 compared with 83,231 with standard screening.
On average, a radiologist reads 50 screening examinations per hour, and the researchers estimated that it took approximately five months less of a radiologist’s time to read the roughly 40,000 screening examinations in the AI group.
A total of 100,000 women have now been enrolled in the MASAI trial. The research team’s next step is to investigate which cancer types that were detected with and without AI support. The primary endpoint of the trial is the rate of interval-cancer, which is a cancer diagnosed between screenings and generally has poorer prognosis than screen-detected cancers. The interval-cancer rate will be assessed after the 100,000 women in the trial have had at least a two-year follow up.
“The results from our first analysis shows that AI-supported screening is safe since the cancer detection rate did not decline despite a substantial reduction in the screen-reading workload. The planned analysis of interval cancers will show whether AI-supported screening also leads to a more accurate and effective screening programme,” says Kristina Lång.
Commenting on the research, Professor Fiona Gilbert, Professor of Radiology and head of department at Cambridge University said: “This exciting, large, prospective mammography study shows that one reader using AI is comparable or better than the standard of two expert readers. There are considerable manpower savings which will translate favourably to the UK to help address our workforce issues. These findings will help plan the testing and implementation of AI into the UK national breast screening programme.”
Poll: Should the UK’s railways be renationalised?
Correlation does not equal causation! That's a hugely simplified view of things and ignores things like increasing car ownership, increasing commuting...