Nuked The model, which scans X-ray images known as mammograms, reduces the number of false negatives by 9.4 percent-a hopeful leap forward for a test that currently misses 20 percent of breast cancers.
Early detection is the best defense most people have in identifying and treating the disease. Yet mammograms are the most common detection tool, but they miss a large number of cases.
Researchers used anonymized mammograms from more than 25,000 women in the UK and 3,000 in the US. The team first trained AI to scan X-ray images, then looked for signs of breast cancer by identifying changes in the breasts of the 28,000 women. They then checked the computer’s guesses against the women’s medical outcomes.
In the UK, the model cut down false negatives by 2.7 percent and reduced false positives by 1.2 percent. The model performed better than an individual radiologist in both the UK and the US.
Researchers found that ai outperformed doctors in identifying breast cancer in most cases. There were also instances where doctors flagged cancer that the model originally missed.
Google says it’s hopeful the system can eventually be used in clinical settings. The team is currently working to ensure the findings can be widespread across populations.
Google has been careful to frame this project as one that will help radiologists, not replace them.’they each bring their own strength, it’s complementary,’ says Shetty.
