A review led by UCLA investigators found that AI can help radiologists identify subtle signs of breast cancers missed during mammograms, but significant limitations still exist.
Some AI systems were even able to identify patterns associated with an increased risk of cancer before they become visible on a mammogram.
Interval cancers, for instance, are breast cancers diagnosed after a negative screening mammogram but before a woman's next scheduled screening. These cancers are often more aggressive than those detected through routine screening. Ultimately, the goal is to eliminate these interval cancers and catch as many as possible as early as possible.
Some interval cancers develop rapidly, but others leave subtle signs that were present on the earlier mammogram. So, researchers tested both whether AI could identify interval cancers that were retrospectively visible on a previous mammogram, and whether AI could identify subtle patterns on a mammogram that appeared normal but were associated with an increased risk of developing breast cancer in the future.
AI was able to identify a substantial proportion of interval cancers with subtle signs visible on a mammogram. The researchers emphasize, however, that these findings represent potential detection, not proven reduction in interval cancer rates.
