Artificial intelligence systems can detect early signs of breast cancer up to six years before diagnosis and, in some cases, even ten years earlier, paving the way for earlier detection of the disease. This was the finding of a study published in “Radiology,” the journal of the Radiological Society of North America, with the participation of Greek scientists.
In the retrospective study, the researchers evaluated three commercially available and reliable artificial intelligence systems, which they trained using data from mammograms in Sweden. Specifically, the study included nearly 89,000 mammograms from 31,394 women, performed over a period of approximately ten years, between January 2008 and April 2019. During this period, 12,072 women—38.5% of the sample—were diagnosed with cancer by radiologists.
ΣΧΕΤΙΚΑ ΑΡΘΡΑ
The data came from the “Validation of Artificial Intelligence for Breast Imaging” database, which collects breast imaging data from volunteers in four regions of Sweden. It should be noted that under the country’s national screening program, women aged 40 to 74 are invited to undergo a mammogram every two years, and each mammogram is traditionally evaluated by two radiologists.
The researchers found that approximately 20% of breast cancer cases showed signs on mammograms that were already visible to artificial intelligence systems much earlier than they were detected by radiologists. In 20% of women, the systems identified signs six years before diagnosis; in 25%, four years earlier; and in 39%, two years before diagnosis. In approximately 15% of women, the systems detected the cancers as much as ten years earlier, although there were slight variations among the three systems within this timeframe. Furthermore, the systems achieved a very high ability to distinguish between true positive and negative results—90%.
The research was conducted by radiologist Pantelis Gialias as part of his doctoral studies at Linköping University Hospital in Sweden. Apostolia Tsirikoglou, a Greek researcher from the Swedish Karolinska Institute, also participated in the study.
As Mr. Gialias explained to the Athens-Macedonian News Agency (ANA-MPA), the cancer cases detected by artificial intelligence systems “are subtle changes that the human eye cannot definitively identify as suspicious. It could be a minor disruption in breast architecture or a gradual increase in breast density—that is, subtle signs that you cannot rely on, no matter how experienced a radiologist you may be.”
Originally from Chios, he studied at the Medical School of Comenius University in Bratislava and completed his residency in Radiology in Greece; Dr. Gialias specialized in breast imaging very early on and obtained relevant certification in Sweden. He describes how dramatically the effectiveness of Artificial Intelligence in Radiology has changed over the past decade. “When we first tested the usefulness of Artificial Intelligence in detecting breast cancer in 2015, the results were disappointing. However, over the years, the algorithms have improved and computers have become much more powerful, capable of processing a massive volume of scans, so the benefits they can offer have become apparent.”
In a previous study conducted by Mr. Gialias in 2022 and published in *Acta Radiologica*, it was found that artificial intelligence can reduce radiologists’ workload in the interpretation of mammograms by up to 34%. In a subsequent study published last year in “European Radiology,” it was found that the use of digital mammography with artificial intelligence during screening is also a cost-saving strategy compared to the traditional method of having results by two radiologists.
“When artificial intelligence first emerged, there was a fear that radiologists would lose their jobs. That is not the case. In essence, it is an additional tool, a tool we have for the early diagnosis of breast cancer. Of course, all decisions must be made with care and based on the necessary studies, and there must always be human oversight,” emphasizes Mr. Gialias, who is currently the director of the Breast Center at the Mediterranean Hospital in Cyprus.
He explains to the Athens-Macedonian News Agency (ANA-MPA) that the breast is a particularly complex organ—a gland—whose appearance changes significantly even in the same woman, depending on hormonal changes. The challenge now, he adds, is “to see to what extent we can use artificial intelligence systems under certain protocols so that women showing early signs can follow a different preventive screening regimen on a case, with the goal of detecting cancers much earlier.”
At the same time, he emphasizes the need for prospective studies, while the research team plans to continue the study, focusing on women with silicone breast implants, where imaging presents additional challenges.
Source: APE-MPE
