By Stephen Beech via SWNS
Robot technology can save lives by detecting more breast cancers, suggests new research.
Radiologists improved breast cancer screening performance and reduced the rate of false-positive findings by using artificial intelligence (AI).
Current mammography techniques successfully reduce deaths from breast cancer but also carry the risk of false-positive findings.
Danish scientists have been studying the use of AI systems in screening compared to current methods with the results published in the journal Radiology.
Dr Andreas Lauritzen, of the University of Copenhagen, said: “We believe AI has the potential to improve screening performance.”
When used to triage likely normal screening results or assist with decision support, he said AI also can substantially reduce radiologist workload.
Dr. Lauritzen, who is also a researcher at Gentofte Hospital in Hellerup, Denmark, said: “Population-based screening with mammography reduces breast cancer mortality, but it places a substantial workload on radiologists who must read a large number of mammograms, the majority of which don’t warrant a recall of the patient.
“The reading workload is further compounded when screening programs employ double reading to improve cancer detection and decrease false-positive recalls.”
Dr. Lauritzen and his colleagues compared workload and screening performance in two groups of women, aged 50 to 69, who underwent biennial mammography screening before and after AI implementation.
In the first group, two radiologists read the mammograms of women screened between October 2020 and November 2021 before the implementation of AI.
The screening mammograms of the second group of women conducted between November 2021 and October 2022 were initially analyzed by AI.
Mammograms deemed likely to be normal by AI were then read by one of 19 specialized full-time breast radiologists, called a “single-read”.
The rest of the mammograms were read by two radiologists – called a “double-read” – with AI-assisted decision support.
The commercially available AI system used for screening was trained by deep learning models to highlight and rate suspicious lesions and calcifications within mammograms.
All the women who underwent mammographic screening were followed for at least 180 days.
Invasive cancers and ductal carcinoma in situ (DCIS) detected through screening were confirmed through needle biopsy or surgical specimens.
A total of 60,751 women were screened without AI, and 58,246 women were screened with the AI system.
In the AI implementation group, 66.9 percent of the screenings were single-read, and 33.1 percent were double-read with AI assistance.
Compared to screening without AI, screening with the AI system detected “significantly” more breast cancers, 0.82 percent compared to 0.70 percent, and had a lower false-positive rate of 1.63 percent compared to 2.39 percent.
Dr. Lauritzen said: “In the AI-screened group, the recall rate decreased by 20.5 percent, and the radiologists’ reading workload was lowered by 33.4 percent.”
The findings showed that the positive predictive value of AI screening (33.5 percent) was also greater than that of screening without AI (22.5 percent).
In the AI group, a higher proportion of invasive cancers detected were one centimeter or less in size (44.93 percent) compared to traditional methods (36.60 percent).
Dr. Lauritzen said: “All screening performance indicators improved except for the node-negative rate which showed no evidence of change.”
He says more research is needed to evaluate long-term outcomes and ensure overdiagnosis does not increase.
Dr. Lauritzen added: “Radiologists typically have access to the women’s previous screening mammograms, but the AI system does not.
“That’s something we’d like to work on in the future.”
