Radiologists typically detect one case of cancer for every 200 mammograms reviewed. However, these evaluations often result in false positives, leading to unnecessary patient recalls for additional testing, which not only causes patient anxiety but also consumes valuable medical resources. Now, a new study has shown how artificial intelligence (AI) can improve the accuracy of breast cancer screening by minimizing these false positives without missing true positives.

The study by researchers at Washington University School of Medicine in St. Louis (St. Louis, MO, USA) and Whiterabbit.ai (Santa Clara, CA, USA) builds on their previous collaboration for the development of an AI algorithm to help radiologists assess breast density on mammograms for identifying people who stand to benefit from additional or alternative screening. That algorithm is marketed by Whiterabbit.ai as WRDensity after receiving clearance from the Food and Drug Administration (FDA) in 2020.

In the current study, the team developed an algorithm to identify normal mammograms with extremely high sensitivity. They went on to run a simulation on patient data to see what would have happened if all of the very low-risk mammograms were taken off the radiologists’ plates, allowing the doctors to focus on the more questionable scans. The results of this simulation indicated that such an approach would reduce the number of unnecessary patient callbacks for additional testing, yet maintain the same rate of cancer detection.

“At the end of the day, we believe in a world where the doctor is the superhero who finds cancer and helps patients navigate their journey ahead,” said Jason Su, co-founder and chief technology officer at Whiterabbit.ai. “The way AI systems can help is by being in a supporting role. By accurately assessing the negatives, it can help remove the hay from the haystack so doctors can find the needle more easily. This study demonstrates that AI can potentially be highly accurate in identifying negative exams. More importantly, the results showed that automating the detection of negatives may also lead to a tremendous benefit in the reduction of false positives without changing the cancer detection rate.” 

http://www.gzjiayumed.com/en/index.asp .