Abstract
Background Use of artificial intelligence (AI) as a stand-alone reader for digital mammography (DM) or digital breast tomosynthesis (DBT) breast screening could ease radiologists' workload while maintaining quality. Purpose To retrospectively evaluate the stand-alone performance of an AI system as an independent reader of DM and DBT screening examinations. Materials and Methods Consecutive screening-paired and independently read DM and DBT images acquired between January 2015 and December 2016 were retrospectively collected from the Tomosynthesis Cordoba Screening Trial. An AI system computed a cancer risk score (range, 1-100) for DM and DBT examinations independently. AI stand-alone performance was measured using the area under the receiver operating characteristic curve (AUC) and sensitivity and recall rate at different operating points selected to have noninferior sensitivity compared with the human readings (noninferiority margin, 5%). The recall rate of AI and the human readings were compared using a McNemar test. Results A total of 15 999 DM and DBT examinations (113 breast cancers, including 98 screen-detected and 15 interval cancers) from 15 998 women (mean age, 58 years ± 6 [standard deviation]) were evaluated. AI achieved an AUC of 0.93 (95% CI: 0.89, 0.96) for DM and 0.94 (95% CI: 0.91, 0.97) for DBT. For DM, AI achieved noninferior sensitivity as a single (58.4%; 66 of 113; 95% CI: 49.2, 67.1) or double (67.3%; 76 of 113; 95% CI: 58.2, 75.2) reader, with a reduction in recall rate (P < .001) of up to 2% (95% CI: -2.4, -1.6). For DBT, AI achieved noninferior sensitivity as a single (77%; 87 of 113; 95% CI: 68.4, 83.8) or double (81.4%; 92 of 113; 95% CI: 73.3, 87.5) reader, but with a higher recall rate (P < .001) of up to 12.3% (95% CI: 11.7, 12.9). Conclusion Artificial intelligence could replace radiologists' readings in breast screening, achieving a noninferior sensitivity, with a lower recall rate for digital mammography but a higher recall rate for digital breast tomosynthesis. Published under a CC BY 4.0 license. See also the editorial by Fuchsjäger and Adelsmayr in this issue.
Highlights
Ader of screening studies could be a cost-effective approach by removing all the workload of reading screening findings, allowing radiologists to focus on only the artificial intelligence (AI)-recalled findings
Performance Comparison We investigated whether AI alone as a screening tool for digital mammography (DM) or digital breast tomosynthesis (DBT) could achieve similar sensitivity with an acceptable recall rate in comparison with four original screening scenarios with radiologists: single reading of DM, double reading of DM, single reading of DBT, and double reading of DBT
We retrospectively investigated the potential use of an artificial intelligence (AI) system as the only reader of screening digital mammography (DM) or digital breast tomosynthesis (DBT) images, instead of human radiologists
Summary
Consecutive screening-paired and independently read DM and DBT images acquired between January 2015 and December 2016 were retrospectively collected from the Tomosynthesis Cordoba Screening Trial. Study Sample and Readings The study data were retrospectively collected from the Tomosynthesis Cordoba Screening Trial [6]. These data have been used in a publication studying the ability of AI to reduce the workload of reading screening [19]. The Tomosynthesis Cordoba Screening Trial was a paired trial that compared the screening performance of DM alone versus the performance of DBT for studies obtained in 16 067 women (age range, 50–69 years) from the screening program between January 2015 and December 2016 who agreed to participate in the trial. The participants underwent combined DM and DBT (two views of each breast) performed with a Selenia Dimensions device (Hologic)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
