Google Research·· 2026-03-18
Improving breast cancer screening workflows with machine learning
Improving breast cancer screening workflows with machine learning
AI summary
The AIMS collaboration between Google Research and several NHS organisations published two companion studies in Nature Cancer evaluating an AI breast cancer detection system within NHS screening workflows.
Selection record
Threshold 60Official, first-handFirst 71Second 71
AdmittedSum of both 142 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：AI用于乳腺癌筛查研究
- Why it was chosen
- The studies quantify benefits of AI image reading in real clinical workflows and limitations in the arbitration stage.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google