AI Wins in Cancer Detection Contest
A group of researchers from Beth Israel Deaconess Medical Center (BIDMC) and Harvard Medical School (HMS) have developed a way to train artificial intelligence to read and interpret pathology images.
Scientists tested the artificial intelligence (AI) during a competition at the annual International Symposium of Biomedical Imaging, where it was tasked to look for breast cancer in images of lymph nodes. It turns out it can detect breast cancer accurately 92 percent of the time and won in two separate categories during the contest.
Andrew Beck from BIDMC says they used the deep learning method, which is commonly used to train AI to recognize speech, images and objects. They fed the machine with hundreds of slides marked to indicate which parts have cancerous cells and which have normal ones. The AI had difficulty identifying some samples, but scientists fed it more difficult samples until it learned its lesson.
AI + Humans = Win
Despite this success, AI is still no match for human pathologists, who are accurate 96 percent of the time. However, this contest clearly shows that there is much to be gained with further study and innovation.
Beck says what’s remarkable is when they combined pathologists' analysis with those of the AI, the results showed 99.5 percent accuracy. "Our results in the ISBI competition show that what the computer is doing is genuinely intelligent and that the combination of human and computer interpretations will result in more precise and more clinically valuable diagnoses to guide treatment decisions."
No one who has ever said that two heads are better than one, specified that both heads had to be human.