For breast cancer screening, mammograms using single reading with computer-aided detection (CAD) offer an alternative to double reading, according to this study. The sensitivity of screening mammography for detecting small breast cancer has been shown to be higher when a mammogram is read by two readers as opposed to one, with studies suggesting that double reading increases the rate of cancer detection by 4-14 per cent and by 10 per cent according to a meta-analysis. Double reading is now standard practice in at least 12 European countries.
CAD systems use computer algorithms to analyse digital mammographic images, and identify and mark potentially suspicious regions that attract the radiologist’s attention to features that might otherwise be overlooked. In the US, where single reading is standard practice, CAD systems are used in 25-30 per cent of all mammogram readings.
This study set out to determine whether the performance of a single reader using a CAD system would match that achieved by two separate readers. Between September 2006 and August 2007, 31,057 women undergoing routine screening by film mammography at centres in England were randomly assigned to one of three reading regimens.
In the study, group A (with a planned number of 1,000 subjects) was assigned to receive double reading only, group B (with a planned number of 1,000 subjects) was assigned to receive single reading with CAD and group C (with a planned number of 28,000 subjects) was assigned to receive a single reading with CAD and a double reading.
Overall results show that for group C, 227 cancers were detected among 28,204 subjects. When double reading was considered separately, the proportion of cancers detected was 199 out of 227 (87.7 per cent) and when single reading with CAD was considered separately, the proportion of cancers detected was 198 out of 227 (87.2 per cent), providing a p value of 0.89.
The results produced cancer detection rates of 7.02 per 1,000 for the single reader using CAD and 7.06 per 1,000 for two readers. Additionally, the overall recall rates were 3.9 per cent for the single reading group with CAD and 3.4 per cent for the double reading group (p <0.001).
For single reading with CAD, estimated sensitivity was 87.2 per cent, specificity, 96.9 per cent, and positive predictive value, 18.0 per cent. For double reading, the figures were 87.7 per cent, 97.4 per cent and 21.1 per cent, respectively.
The authors concluded that single reading with CAD offers an alternative to double reading. They also recommended that the performance of CAD in full-field digital mammography and its performance in film mammography, used in the current study, should be investigated.
Gilbert FJ, Astley SM, Gillan MCG et al. Single reading with computer-aided detection for screening mammography. N Engl J Med 2008;359:1675-84
Originally published in the November 2008 edition of MIMS Oncology & Palliative Care.