Use of Artificial Intelligence for Digital Breast Tomosynthesis Screening: A Preliminary Real-world Experience.

OBJECTIVE: The purpose of this study is to assess the "real-world" impact of an artificial intelligence (AI) tool designed to detect breast cancer in digital breast tomosynthesis (DBT) screening exams following 12 months of utilization in a subspecialized academic breast center. METHODS: Following IRB approval, mammography audit reports, as specified in the BI-RADS atlas, were retrospectively generated for five radiologists reading at three locations during a 12-month time frame. One location had the AI tool (iCAD ProFound AI v2.0), and the other two locations did not. The co-primary endpoints were cancer detection rate (CDR) and abnormal interpretation rate (AIR). Secondary endpoints included positive predictive values (PPVs) for cancer among screenings with abnormal interpretations (PPV1) and for biopsies performed (PPV3). Odds ratios (OR) with two-sided 95% confidence intervals (CIs) summarized the impact of AI across radiologists using generalized estimating equations. RESULTS: Nonsignificant differences were observed in CDR, AIR, and PPVs. The CDR was 7.3 with AI and 5.9 without AI (OR 1.3, 95% CI: 0.9-1.7). The AIR was 11.7% with AI and 11.8% without AI (OR 1.0, 95% CI: 0.8-1.3). The PPV1 was 6.2% with AI and 5.0% without AI (OR 1.3, 95% CI: 0.97-1.7). The PPV3 was 33.3% with AI and 32.0% without AI (OR 1.1, 95% CI: 0.8-1.5). CONCLUSION: Although we are unable to show statistically significant changes in CDR and AIR outcomes in the two groups, the results are consistent with prior reader studies. There is a nonsignificant trend toward improvement in CDR with AI, without significant increases in AIR.

Tomosynthesis Impact on Breast Cancer Screening in Patients Younger Than 50 Years Old.

OBJECTIVE: The question of benefits versus harms of breast cancer screening for women younger than 50 years old has been the subject of debate. We investigate if the addition of tomosynthesis to mammography improves screening performance outcomes for women in this age group. MATERIALS AND METHODS: Screening performance for 59,921 patients (41,542 digital mammography and 18,379 tomosynthesis) younger than 50 years old was collected from a community-based screening network from January 1, 2015, to December 31, 2015. Patients were offered tomosynthesis if it was available. Parameters including recall, biopsy, and cancer detection rates were compared. Mixed effects regression analysis was used to estimate rates with screening modality, age, and density as fixed effects and screening site as a random effect. Rates for patients with dense breast tissue were also evaluated. RESULTS: Model adjusted rates per 1000 screenings with digital mammography were compared with digital mammography plus tomosynthesis, respectively: recall rate decreased from 117 to 108 (difference, -8.3; p = 0.003); biopsy rate increased from 13.5 to 16.6 (difference, 3.1; p = 0.003); and cancer detection rate increased from 1.9 to 2.6 (difference, 0.8; p = 0.060). Model adjusted rates for patients with dense breast tissue were: recall rate decreased from 135 to 132 (difference, -3.2; p = 0.44); biopsy rate increased from 16.0 to 20.5 (difference, 4.5; p = 0.004); and cancer detection rate increased from 2.1 to 3.5 (difference, 1.3; p = 0.03). CONCLUSION: Tomosynthesis in a community setting resulted in decreased recall rates for patients younger than 50 years old. For the subgroup of women with dense breast tissue, cancer detection rates also increased.