Mammography supported by advanced technology results in fewer aggressive and advanced breast cancers, Lancet paper says
A major new study has found that more women with breast cancer were identified through AI-supported screening than through screening which didn’t have AI.
The trial of more than 100,000 women found that AI-supported breast cancer screening is more effective than standard mammography across many measures.
The researchers believe their findings support the implementation of AI in mammography screening programmes – particularly in the context of health professional workforce shortages.
The Swedish study, published this week in The Lancet, showed that mammography supported by artificial intelligence identifies more cancers during screening. It was also found to reduce the rate of breast cancer diagnosis by 12 per cent in following years.
“Widely rolling out AI-supported mammography in breast cancer screening programmes could help reduce workload pressures amongst radiologists, as well as helping to detect more cancers at an early stage, including those with aggressive subtypes,” said lead author Dr Kristina Lång from Lund University, Sweden
“However, introducing AI in healthcare must be done cautiously, using tested AI tools, and with continuous monitoring in place to ensure we have good data on how AI influences different regional and national screening programmes, and how that might vary over time.”
This study is the first randomised controlled trial investigating the use of AI in breast cancer screening, and the largest to date looking at AI use in cancer screening in general.
Previously published interim safety results of the MASAI trial found that AI-supported mammography led to a 44 per cent reduction in screen-reading workload for radiologists.
A separately published early analysis of the trial found a 29 per cent increase in cancer detection without an increase in false positives.
“Our study does not support replacing healthcare professionals with AI, as the AI-supported mammography screening still requires at least one human radiologist to perform the screen reading, but with support from AI,” said first author Jessie Gommers of Radboud University Medical Centre in the Netherlands.
“However, our results potentially justify using AI to ease the substantial pressure on radiologists’ workloads, enabling these experts to focus on other clinical tasks, which might shorten the waiting times for patients.”
Mammography screening has been associated with a lower breast cancer death rate, largely due to the early detection and treatment of the cancer. However, despite European guidelines recommending two radiologists read mammograms, some cancers still go undetected in screening.
Estimates suggest that 20-30 per cent of breast cancers diagnosed after a negative screen and before the next scheduled screen (interval cancers) could have been spotted at the preceding mammogram. Interval cancers are often more aggressive or advanced than cancers detected during routine screening, making them harder to treat effectively.
Between April 2021 and Dec 2022, over 100,000 women who were part of mammography screening at four sites in Sweden were randomly assigned to either AI-supported mammography or to standard screening, where two radiologists read each mammogram.
In the AI group, specialist technology analysed the mammograms and triaged low-risk cases to single reading and high-risk cases to double reading performed by radiologists. AI was also used as detection support to the radiologists, in which it highlighted suspicious findings in the image.
The AI system was trained, validated and tested with more than 200,000 examinations from multiple institutions across more than ten countries.
During the two years follow-up, there were 1.55 interval cancers per 1,000 women in the AI-supported mammography group, compared to 1.76 interval cancers per 1,000 women in the control group: a 12 per cent reduction in interval cancer diagnosis for the AI arm.
Additionally, there were 16 per cent fewer invasive, 21 per cent fewer large, and 27 per cent fewer aggressive sub-type cancers in the AI group compared to the control arm.
In the AI-supported mammography group, 81 per cent of cancer cases were detected at screening, compared to 74 per cent of cancer cases in the control group: a 9 per cent increase. The rate of false positives was similar for both groups, at 1.5 per cent in the AI group and 1.4 per cent in the standard group.
The authors note several limitations including that the analysis was conducted in one country, was limited to one type of mammography device, and one AI system, which might limit the generalisability of the results. Additionally, in this trial, radiologists were moderately to highly-experienced, which could limit the generalisability of the findings to less experienced radiologists. Lastly, information on race and ethnicity was not collected.
“Further studies on future screening rounds with this group of women and cost-effectiveness will help us understand the long-term benefits and risks of using AI-supported mammography screening,” added Dr Lång.
“If they continue to suggest favourable outcomes for AI-supported mammography screening compared with standard screening, there could be a strong case for using AI in widespread mammography screening, especially as we face staff shortages.”