Google’s Newest A.I. Development Identifies Breast Cancer on Mammograms
According to an article recently published in the journal Nature, “artificial intelligence can help doctors do a better job of finding breast cancer on mammograms,” The New York Times reported.
While this new system is currently widely available, the tests show promise with the A.I. program performing better than radiologists. “On scans in the United States, the system produced a 9.4% reduction in false negatives, in which a mammogram is mistakenly read as normal and a cancer is missed,” and “also provided a lowering of 5.7% in false positives, where the scan is incorrectly judged abnormal but there is no cancer,” Denise Grady writes. In Britain, the system also outperformed radiologists, reducing false negatives by 2.7% and false positives by 1.2%.
The authors of this recent study taught the system to recognize cancer using mammograms from about 76,000 women in Britain and 15,000 in the United States, whose diagnoses were already known. They then tested the computers using images from about 25,000 other women in Britain and 3,000 in the United States and compared the A.I. system’s performance to that of the radiologists who had already read the mammograms.
An additional test compared the A.I.’s analysis against six radiologists in the United States using 500 mammograms to be interpreted. While the A.I. ultimately outperformed the human radiologists, there were still some instances where A.I. missed cancer that the six radiologists found.
“There’s no denying that in some cases our A.I. tool totally gets it wrong and they totally get it right,” Dr. Mozziyar Etemadi, an author of the study from Northwestern University, said. “Purely from that perspective, it opens up an entirely new area of inquiry and study. Why is it that they missed it? Why is it that we missed it?”
The next step is to see how the technology performs in the real world. “We have to see what happens when radiologists have it, see if they do better,” Dr. Etemadi said.