Can AI serve as an independent second reader of mammograms? A simulation study

Rodríguez-Ruiz A, Lång K, Gubern-Merida A, Broeders M, Gennaro G, Clauser P, Helbich T, Mertelmeier T, Chevalier M, Wallis M, Andersson I, Zackrisson S, Mann R, Sechopoulos I
Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115130O (22 May 2020); doi: 10.1117/12.2564114

Aim and Objective
Simulate the impact of replacing one radiologist by Transpara®, a deep learning-based artificial intelligence (AI) decision support system in a double reading setting.

Materials and Method
We used a large previously built database of 2,892 mammograms and 31,650 single mammogram radiologists’ assessments. The double human reading scenario and the double hybrid reading scenario (second reader replaced by Transpara) were simulated via bootstrapping using different combinations of mammograms and radiologists from the database. The main outcomes of each scenario were sensitivity, specificity and workload (number of necessary readings).

Results
Using Transpara as a second reader, workload can be reduced by 44%, sensitivity remains similar (difference -0.1%; 95% CI = -4.1%, 3.9%), and specificity increases by 5.3% (P<0.001).

Conclusion
Using Transpara as a second reader in a double reading setting as in screening programs could be a strategy to reduce workload and false positive recalls without affecting sensitivity.