Breast cancer detection is more effective with Artificial Intelligence (AI), according to research from Lund University in Sweden.
The study shows that AI can identify 20% more breast cancer cases and reduce radiologists’ workload by over 40%.
This progress is especially important because of the growing number of women who are called in for mammograms every year.
In Sweden alone, approximately a million women are asked to undergo the procedure annually. Traditionally, each exam had to be reviewed by not one, but two breast radiologists for accuracy – a process known as “double reading”.
However, due to a shortage of breast radiologists, there can be significant delays to diagnosis. This wait can be dangerous for patients. That’s where AI is coming in to play a crucial role.
In the study, more than 80,000 women were divided into two groups: around 40,000 underwent mammography with the support of AI, while the rest went through the traditional procedure without AI.
To everyone’s excitement, the AI-supported screenings demonstrated that AI is a safe alternative for double reading.
Even better, the use of AI led to the detection of 20% more cancers compared to traditional screening methods, and it didn’t increase false positives, which occur when a woman is initially suspected but then cleared of cancer.
At the same time, the screen-reading workload for radiologists was reduced by 44 %. The number of screen readings with AI-supported screening was 46,345 compared with 83,231 with standard screening.
Kristina Lang, researcher and associate professor in diagnostic radiology at Lund University and consultant at Skane University Hospital, who led the study explains that the time aspect is important. On average, a radiologist reads 50 screening examinations per hour. 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.
“The study was conducted on a single site in a Swedish setting. We need to see whether these promising results hold up under other conditions, for example with other radiologists or other AI algorithms. There may be other ways to use AI in mammography screening, but these should preferably also need to be investigated in a prospective setting,” states Kristina.
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 interval-cancer rate.
An interval cancer is a cancer diagnosed between screenings and generally has a 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.
These findings point towards a promising future where AI helps to speed up mammography processes, leading to quicker diagnoses and improved outcomes. This advancement could save lives and reduce a lot of stress for millions of women globally.
