Artificial Intelligence could cut workload of radiologists in searching routine scans for breast cancer signs, a large study in Sweden suggested on Wednesday. The interim results were promising, but the authors cautioned that more research is needed before using AI for broader breast cancer screening.
What would the latest AI breakthrough mean for the human workforce engaged in the radiology and related medical works, remains unclear.
In 2020, over 2.3 million women were diagnosed with breast cancer and 685,000 deaths were attributed to breast cancer, according to World Health Organization.
How the study was conducted?
The medical community has been repeatedly asserting since long that regular screening is crucial for early cancer detection.
The current study involved 80,000 mammograms from four sites in southwest Sweden between April 2021 and July last year.
The AI-supported system predicted 20 per cent more cancers, reducing the workload for radiologists by 44 per cent, as only one person was needed to read the scans instead of two.
Despite the promising results, the study’s lead author said that more time and research are needed before implementing AI in mammography screening. The trial will assess AI’s impact on reducing interval cancers, detected between routine screenings, over the next two years.
Also watch | How AI and Automation will impact jobs in the future
“The greatest potential of AI right now is that it could allow radiologists to be less burdened by the excessive amount of reading,” Kristina Lang, a radiologist at Sweden’s Lund University and lead author of the study.
It will take two more years before the trial can say whether using AI leads to a reduction in what are called interval cancers, which are detected between routine screenings, the researchers have cautioned.
(With inputs from agencies)
recommended stories
recommended stories
You can now write for wionews.com and be a part of the community. Share your stories and opinions with us here.
