Mammographic film reading is a highly demanding task, particularly in screening programs where the reader must perform a detailed visual search of a large number of images for signs of abnormality that are often subtle or small, and which occur very infrequently. False-negative cases, in which signs of abnormality are missed by a film reader, are known to occur. Computer-aided detection (CAD) systems, which automatically detect potential abnormalities and indicate their locations to the reader, have the capacity to reduce the frequency of such errors by ensuring that all suspicious regions of the images are thoroughly searched and by increasing the weighting attached to subtle signs that may otherwise have been dismissed. CAD systems depend on suites of detection algorithms, but each algorithm has a different sensitivity and specificity and the effect of prompting errors on human performance with CAD is complex. This article is a brief review of CAD for screening mammography; it highlights both the strengths and the weaknesses of the approach, and describes some of the methodologies used to evaluate CAD in a clinical setting.