The study was done to perform an external evaluation of 3 commercially available AI computer-aided detection algorithms as independent mammography readers and to assess the screening performance when combined with radiologists.
The study sample included 739 women who were diagnosed as having breast cancer and a random sample of 8066 healthy controls.
The cases positive for cancer comprised 618 screen-detected and 121 clinically detected within 12 months of the screening examination. The area under the receiver operating curve for cancer detection was 0.956 for AI-1, 0.922 for AI-2, and 0.920 for AI-3. At the specificity of the radiologists, the sensitivities were 81.9% for AI-1, 67.0% for AI-2, 67.4% for AI-3, 77.4% for first-reader radiologist, and 80.1% for second-reader radiologist. Combining AI-1 with first-reader radiologists achieved 88.6% sensitivity at 93.0% specificity. No other examined combination of AI algorithms and radiologists surpassed this sensitivity level.
The study concluded that a commercially available AI computer-aided detection algorithm can assess screening mammograms with a sufficient diagnostic performance to be further evaluated as an independent reader in prospective clinical trials.