The performance of the artificial intelligence system was promising for breast cancer detection in a large population-based mammography screening program. Key Results:• In this retrospective study of 122 969 examinations, mammograms were evaluated with an artificial intelligence (AI) system which predicts the risk of cancer on a scale from 1 (lowest risk) to 10 (highest risk). • A total of 87.6% (653 of 752) of screen-detected and 44.9% (92 of 205) of interval cancers had the highest AI score of 10; 0.7% (five of 752) screen-detected cancers had the lowest AI score of 1. • Interval cancers with high AI scores had favorable histopathological tumor characteristics compared to cancers with low AI scores; the opposite was observed for screen-detected cancers.

Objectives Artificial intelligence (AI) has shown promising results when used on retrospective data from mammographic screening. However, few studies have explored the possible consequences of different strategies for combining AI and radiologists in screen-reading. Methods A total of 122,969 digital screening examinations performed between 2009 and 2018 in BreastScreen Norway were retrospectively processed by an AI system, which scored the examinations from 1 to 10; 1 indicated low suspicion of malignancy and 10 high suspicion. Results were merged with information about screening outcome and used to explore consensus, recall, and cancer detection for 11 different scenarios of combining AI and radiologists. Results Recall was 3.2%, screen-detected cancer 0.61% and interval cancer 0.17% after independent double reading and served as reference values. In a scenario where examinations with AI scores 1–5 were considered negative and 6–10 resulted in standard independent double reading, the estimated recall was 2.6% and screen-detected cancer 0.60%. When scores 1–9 were considered negative and score 10 double read, recall was 1.2% and screen-detected cancer 0.53%. In these two scenarios, potential rates of screen-detected cancer could be up to 0.63% and 0.56%, if the interval cancers selected for consensus were detected at screening. In the former scenario, screen-reading volume would be reduced by 50%, while the latter would reduce the volume by 90%. Conclusion Several theoretical scenarios with AI and radiologists have the potential to reduce the volume in screen-reading without affecting cancer detection substantially. Possible influence on recall and interval cancers must be evaluated in prospective studies. Key Points • Different scenarios using artificial intelligence in combination with radiologists could reduce the screen-reading volume by 50% and result in a rate of screen-detected cancer ranging from 0.59% to 0.60%, compared to 0.61% after standard independent double reading • The use of artificial intelligence in combination with radiologists has the potential to identify negative screening examinations with high precision in mammographic screening and to reduce the rate of interval cancer

Background: Digital breast tomosynthesis (DBT) improves breast cancer (BC) detection compared to mammography, however, it is unknown whether this reduces interval cancer rate (ICR) at follow-up. Methods: Using individual participant data (IPD) from DBT screening studies (identified via periodic literature searches July 2016 to November 2019) we performed an IPD meta-analysis. We estimated ICR for DBTscreened participants and the difference in pooled ICR for DBT and mammography-only screening, and compared interval BC characteristics. Two-stage meta-analysis (study-specific estimation, pooled synthesis) of ICR included random-effects, adjusting for study and age, and was estimated in age and density subgroups. Comparative screening sensitivity was calculated using screen-detected and interval BC data. Findings: Four prospective DBT studies, from European population-based programs, contributed IPD for 66,451 DBT-screened participants: age-adjusted pooled ICR was 13.17/10,000 (95%CI: 8.25À21.02). Pooled ICR was higher in the high-density (21.08/10,000; 95%CI: 6.71À66.27) than the low-density (8.63/10,000; 95%CI: 5.25À14.192) groups (P = 0.03) however estimates did not differ across age-groups (P = 0.32). Based on two studies that also provided data for 153,800 mammography screens (age-adjusted ICR 17.69/10,000; 95%CI: 13.22À23.66), DBT's pooled ICR was 16.83/10,000 (95%CI: 11.89À23.82). Comparative meta-analysis showed a non-significant difference in ICR (-0.44/10,000; 95%CI: -11.00À10.11) and non-significant difference in screening sensitivity (6.79%; 95%CI: -0.73À14.87%) between DBT and DM but a significant pooled difference in cancer detection rate of 33.49/10,000 (95%CI: 23.88À43.10). Distribution of interval BC prognostic characteristics did not differ between screening modalities except that those occurring in DBT-screened participants were significantly more likely to be negative for axillary-node metastases (P = 0.005). Interpretation: Although heterogeneity in ICR estimates and few datasets limit recommendations, there was no difference between DBT and mammography in pooled ICR despite DBT increasing cancer detection.