AI system outperforms radiologists in first reading of breast cancer screening, study claimsBMJ 2020; 368 doi: https://doi.org/10.1136/bmj.m16 (Published 03 January 2020) Cite this as: BMJ 2020;368:m16
- Elisabeth Mahase
- The BMJ
An artificial intelligence (AI) system designed to read mammogram images and identify breast cancer “outperformed” radiologists in the first reading, a study has claimed.1
The research, funded by Google and carried out by Google employees (who own stock) and consultants, tested the AI model using two datasets from the UK (25 856 mammograms) and US (3097 mammograms) and found it reduced the number of false negatives and positives, compared with radiologists.
The study, published in Nature, said that in the UK, where mammograms are read by two radiologists during screening, this model could reduce the workload for the second reader by 88%.
The Royal College of Radiologists said that while AI programmes can be helpful as a “second pair of eyes,” it will not solve the workforce crisis because “radiologists and imaging teams do far more …