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.

Image-guided breast biopsies are safe, efficient, and reliable. However, patients are often anxious about these procedures, particularly those who have never undergone a prior biopsy. This prospective IRB-approved study surveyed 163 patients undergoing their first breast biopsy. Participants provided informed consent and completed a short written survey prior to and immediately after their procedure. Level of anxiety as well as anticipated and actual levels of pain prior to and following the procedure were assessed using a 0–10-point Likert scale. Correlation, bivariate, and regression analyses were performed. Regarding the biopsy experience, 133/163 (81.6%) of patients reported it as better than expected. Anxiety decreased significantly from a prebiopsy mean score of 5.52 to a postbiopsy mean score of 2.25 (P < 0.001). Average and greatest pain experienced during the procedure had mean scores of 2.03 and 2.77, respectively, both significantly lower compared to preprocedural expectation (mean 4.53) (P < 0.001). Lower pain scores were reported in US-guided procedures compared to stereotactic- and MRI-guided biopsies (P < 0.001). No significant differences in pain scores were seen in those undergoing single versus multiple biopsies, or when benign, elevated-risk, or malignant lesions were sampled. Positive correlations were seen with prebiopsy anxiety levels and procedural pain as well as with anticipated pain and actual procedural pain. Image-guided biopsies are often better tolerated by patients than anticipated. We stress the benefit of conveying this information to patients prior to biopsy, as decreased anxiety correlates with lower levels of pain experienced during the procedure.

Dense breast parenchyma obscures breast lesions and has been shown to be an independent risk factor for development of breast cancer. An ever-increasing number of states have approved laws requiring patient notification of dense breast tissue. Reviews of supplemental screening imaging modalities are available, but there is no consensus and little discussion regarding what radiologists are specifically doing to manage patients with dense breasts. Our goal was to survey breast imagers facing these issues in an effort to simplify dense breast management. A survey was administered via email to the Society of Breast Imaging member directory, designed to collect information regarding current practices in dense breast notification and supplemental screening. There were 223 surveys completed to entirety, including 38% from respondents in states without mandatory breast density reporting laws and 62% from states with reporting laws. A majority of respondents from both groups, 60% and 51% in those without and with laws, respectively, felt they lacked adequate resources to offer or sustain supplemental screening. In those offering supplemental imaging, the modalities offered varied widely as did the manner of offering a supplemental exam. Levels of satisfaction, concerns, and standard practices of respondents were also queried. Strategizing optimal imaging approaches and algorithms to handle dense breast management issues is important to maintain efficiency in breast imaging departments. Sharing current ideas and practices may facilitate a smoother workflow in mandatory dense breast reporting and supplemental imaging, allowing breast imagers to correct or prevent systems-based flaws.