Computer-Aided Detection in Mammography

Abstract

In breast cancer imaging many innovations continue to take place. This article discusses computer-aided detection (CAD) of breast cancer in mammograms, which is the first large-scale application of independent computerized interpretation of radiological images. Thousands of systems have already been installed worldwide and use of CAD is rapidly expanding with the introduction of digital mammography. Radiologists are generally pleased with the new technology, in particular for its ability to mark clustered microcalcifications with high sensitivity. However, most believe that the performance of CAD for mass detection should still be improved to make it more useful. Most clinical studies indicate that CAD is effective in practice, both for detection of masses and microcalcifications. Future developments show a trend towards using CAD not only for detection but also for characterization of lesions.