A new study indicates that artificial intelligence has the potential to assist in breast cancer diagnosis, especially in countries facing a shortage of radiologists. Although it is still in the early stages, AI technologies, such as deep learning algorithms, have shown promise in aiding the analysis of medical images, including mammograms.
Doctors and scientists from Sweden's Lund University have found that AI-supported mammography screening "almost halved radiologists' workload" during a randomized trial under a Swedish national breast cancer screening program.
"An AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe," the researchers found.
"Interim findings from a cohort of over 80,000 women in Sweden reveal AI-supported screening detected 20% more cancers compared with the routine double reading of mammograms by two breast radiologists," the team explained.
But they added that the trial results would not be finalized "for several years."
The researchers, whose findings were published in the Lancet Oncology, said it remains to be established if using AI "reduces interval cancers" before deciding whether using AI in mammography screening "is justified."
"We still need to understand the implications on patients' outcomes, especially whether combining radiologists' expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology," said Kristina Lång of Lund University.
But the team said AI assistance could be needed in countries that do not have enough radiologists.
"There is a shortage of breast radiologists in many countries, including a shortfall of around 41 (8%) in the U.K. in 2020 and about 50 in Sweden, and it takes over a decade to train a radiologist capable of interpreting mammograms," they said.
