Possible strategies for use of artificial intelligence in screen-reading of mammograms, based on retrospective data from 122,969 screening examinations.

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.

Artificial Intelligence Evaluation of 122 969 Mammography Examinations from a Population-based Screening Program.

Background Artificial intelligence (AI) has shown promising results for cancer detection with mammographic screening. However, evidence related to the use of AI in real screening settings remain sparse. Purpose To compare the performance of a commercially available AI system with routine, independent double reading with consensus as performed in a population-based screening program. Furthermore, the histopathologic characteristics of tumors with different AI scores were explored. Materials and Methods In this retrospective study, 122 969 screening examinations from 47 877 women performed at four screening units in BreastScreen Norway from October 2009 to December 2018 were included. The data set included 752 screen-detected cancers (6.1 per 1000 examinations) and 205 interval cancers (1.7 per 1000 examinations). Each examination had an AI score between 1 and 10, where 1 indicated low risk of breast cancer and 10 indicated high risk. Threshold 1, threshold 2, and threshold 3 were used to assess the performance of the AI system as a binary decision tool (selected vs not selected). Threshold 1 was set at an AI score of 10, threshold 2 was set to yield a selection rate similar to the consensus rate (8.8%), and threshold 3 was set to yield a selection rate similar to an average individual radiologist (5.8%). Descriptive statistics were used to summarize screening outcomes. Results A total of 653 of 752 screen-detected cancers (86.8%) and 92 of 205 interval cancers (44.9%) were given a score of 10 by the AI system (threshold 1). Using threshold 3, 80.1% of the screen-detected cancers (602 of 752) and 30.7% of the interval cancers (63 of 205) were selected. Screen-detected cancer with AI scores not selected using the thresholds had favorable histopathologic characteristics compared to those selected; opposite results were observed for interval cancer. Conclusion The proportion of screen-detected cancers not selected by the artificial intelligence (AI) system at the three evaluated thresholds was less than 20%. The overall performance of the AI system was promising according to cancer detection. © RSNA, 2022.

Interval breast cancer rates for digital breast tomosynthesis versus digital mammography population screening: An individual participant data meta-analysis.

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 DBT-screened 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: 8.25-21.02). Pooled ICR was higher in the high-density (21.08/10,000; 95%CI: 6.71-66.27) than the low-density (8.63/10,000; 95%CI: 5.25-14.192) 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: 13.22-23.66), DBT's pooled ICR was 16.83/10,000 (95%CI: 11.89-23.82). Comparative meta-analysis showed a non-significant difference in ICR (-0.44/10,000; 95%CI: -11.00-10.11) and non-significant difference in screening sensitivity (6.79%; 95%CI: -0.73-14.87%) between DBT and DM but a significant pooled difference in cancer detection rate of 33.49/10,000 (95%CI: 23.88-43.10). 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.