A new Swedish study suggests that artificial intelligence (AI) may be able to help with breast cancer screening. Researchers at Lund University led the study and found that a computer program could spot cancer in screening images at a similar rate to two human radiologists.
This means that AI has the potential to be used in breast cancer screening programs in general, but more research is most certainly needed. Experts in the UK also agree that AI shows great promise in the realm of breast cancer screening.
Other studies have looked into using AI to diagnose breast cancer in mammograms (X-rays of the breast) before, but they were mostly looking back at scans that doctors had already assessed. This study, however, evaluated the accuracy of AI-supported screening in direct relation to more widely-accepted methods used by radiologists.
Trial conducted for the study
The trial involved more than eighty thousand women from Sweden, with an average age of fifty-four. Half of them had their scans checked by two radiologists, which is the usual standard of care. The other half had their scans initially checked by the AI-supported tool followed by evaluations of two radiologists.
The results showed that 244 women using the AI-supported screening were found to have cancer, while only 203 women were diagnosed with cancer using the regular screening method.
The use of AI did not lead to more false positives, meaning scans incorrectly diagnosed as abnormal. The rate of false positives was the same in both the AI group and the group assessed by radiologists, at 1.5 percent.
More research required to tap the full potential
According to Dr. Kristina Lang, the lead author of the study, AI has the potential to be used in breast cancer screening. This could help deal with the worldwide shortage of radiologists.
However, Dr. Lang emphasized that more research is necessary to fully grasp the true potential and cost-effectiveness of AI in this area.
She pointed out that the most significant benefit of AI at the moment is that it could ease the burden on radiologists by reducing the overwhelming amount of reading they have to do for cancer detection.
She further said, “While our AI-supported screening system requires at least one radiologist in charge of detection, it could potentially do away with the need for double reading of the majority of mammograms, easing the pressure on workloads and enabling radiologists to focus on more advanced diagnostics while shortening waiting times for patients.”
A spokesperson from NHS England expressed enthusiasm about the research findings, stating that they are very encouraging. Plans are already underway to assess the best ways of incorporating this technology into the NHS Breast Screening Programme.
"Artificial intelligence boosts breast cancer screening safety, reducing radiologists' workload by nearly 50%.
Groundbreaking study proves the safety and efficiency of AI in breast cancer screening. Radiologists can now focus on more critical cases. pic.twitter.com/OI549qFpyE
— Global Observer X (@GlobalObserverX) August 2, 2023
Dr. Katharine Halliday, the president of the Royal College of Radiologists, said of AI that it holds tremendous promise. “AI holds huge promise and could save clinicians time by maximizing our efficiency, supporting our decision-making, and helping identify and prioritize the most urgent cases,” she maintained.
She further added that “there is a great deal of research interest in how AI could support reporting for mammograms because they are complex, requiring significant oversight and interpretation by clinical radiologists. The UK’s shortfall in radiologists, at 29%, makes this challenging.”
“While real-life clinical radiologists are essential and irreplaceable,” she continued, “a clinical radiologist with the data, insight and accuracy of AI will increasingly be a formidable force in patient care.”