The efficacy of using CAD for detection of breast cancer in mammography screening A systematic review

Abstract
Purpose: The aim of this systematic review is to present an overview of the available studies concerning the use of computer-aided detection (CAD) systems in screening mammography for early detection of breast cancer and compare the diagnostic accuracy and recall rates of single reading with single reading + CAD and double reading with single reading + CAD.
Materials and methods: PRISMA guidelines were used as a review protocol. Only articles on clinical trials concerning the efficacy of computer-aided detection systems to detect breast cancer for use in a screening population were included. The literature search resulted in 1522 records after duplicates were removed. 1491 records were excluded by abstract and 18 were excluded after assessing the eligibility by full text reading. A total of 13 articles were included in this study.
Results: The results for the single reading vs. single reading with CAD group indicate that the addition of CAD increases sensitivity and cancer detection rate (CDR). For the double reading vs. single reading with CAD group none of the studies reported significant differences in sensitivity and CDR. Adding CAD to single reading increased the recall rates and decreased the specificity. For the double reading vs. single reading with CAD group only one study reported a significant difference in recall rate.
Conclusion: Single reading with CAD increases the recall rates, sensitivity and CDR in mammography screening compared to single reading alone. Compared to double reading no statistically significant differences in sensitivity or CDR were reported. Additional studies are needed to evaluate the effect of CAD in an organized population-based screening program.