AN IMPROVED COMPUTER-ASSISTED DIAGNOSTIC SCHEME USING WAVELET TRANSFORM FOR DETECTING CLUSTERED MICROCALCIFICATIONS IN DIGITAL MAMMOGRAMS

Rationale and Objectives. We evaluated the potential usefulness of a c omputer-assisted diagnostic (CAD) scheme incorporating the wavelet tra nsform for detecting clustered microcalcifications in mammograms. Meth ods. A wavelet transform technique was applied to the detection of clu stered microcalcifications, We examined several wavelets to study thei r effectiveness in detecting subtle microcalcifications. We used a dat abase consisting of 39 mammograms containing 41 clusters of microcalci fications. The performance of the wavelet-based CAD scheme was evaluat ed using free-response receiver operating characteristic analysis. Res ults. The CAD scheme with the wavelet transform was useful in detectin g some of the subtle microcalcifications that were not detected by our previous scheme, which was based on the difference-image technique. W hen the two schemes were combined, the overall performance was improve d to a sensitivity of approximately 95%,with a false-positive rate of 1.5 clusters per image. Conclusion. The wavelet transform approach can improve the detection of subtle clustered microcalcifications.