Artificial Intelligence Is Helping Doctors Find Breast Cancer Risk 30 Times Faster

Sudanese radiologist Dr Hania Fadl speaks with reporters in 2015 at the Khartoum Breast Care Centre (KBCC), which she opened in 2010 and equipped with screening and anesthetic equipment despite financial advisers' warnings to abandon the project. The mammogram is one of medical science's best tools for detecting breast cancer, but when the typically painful test reveals a potential problem, women frequently undergo breast biopsies for a closer look--a practice that's all too often unnecessary, according to a group of artificial intelligence (AI) researchers, and which doctors may be able to significantly reduce thanks to a little insight from computers. Announced today, researchers from Houston Methodist have developed AI software that can interpret mammogram results a full 30 times quicker than doctors and with 99 percent accuracy, according to the team's recent study. Published in the journal Cancer, the study found that the software was able to intuitively translate patient charts into diagnostic information for human review at top speeds, which offers doctors reliable and seriously time-saving support when it comes to assessing patient cancer risk and the need for further tests. To determine the software's effectiveness for assessing breast cancer risk, the team provided its AI with mammogram and pathology reports of 500 breast cancer patients, as well as information on diagnostic features and correlated mammogram findings for breast cancer subtypes.