COMPUTER-AIDED DETECTION OF CLUSTERED MICROCALCIFICATIONS IN DIGITIZED MAMMOGRAMS

Rationale and Objectives. We investigated a computer-aided detection ( CAD) scheme for clustered microcalcifications in digitized mammograms. Methods. A multistage CAD scheme was developed and tested. To increas e sensitivity, the scheme uses a Gaussian band-pass filter and nonline ar threshold. A multistage local minimum searching routine and a multi layer topographic feature analysis are used to reduce the false-positi ve detection rate. One hundred ten digitized mammograms were used in t his preliminary test, with 55 images containing one or two verified mi crocalcification clusters. Results. The CAD scheme achieved 100% sensi tivity and had an average false-positive detection rate of 0.18 per im age. Conclusion. The CAD scheme performs as well as many published sch emes and has some unique advantages to further improve detection sensi tivity and specificity of future CAD schemes.