PRESCREENING ENTIRE MAMMOGRAMS FOR MASSES WITH ARTIFICIAL NEURAL NETWORKS - PRELIMINARY-RESULTS

Rationale and Objectives. The authors evaluated the feasibility of com bining wavelet transform and artificial neural network (ANN) technolog ies to prescreen mammograms for masses. Methods and Materials. Fifty-f ive mammograms (29) with masses and 26 without) were digitized to 100- mm resolution and processed by using wavelet transformation. These wav elets were subjected to a linear output sequential recursive auto-asso ciative memory ANN and cluster analysis with feature vector formation. These vectors were used in two separate experiments-one with 13 cases and another with seven cases held out in a test set-to train feed-for ward ANNs to detect the mammograms with a mass. The experiments were r epeated with rerandomization of the data, four and six times, respecti vely. Results. There was a statistically significant correlation (P < .01) between the network's prediction of a mass and the presence of a mass. With majority voting, the feed-forward ANNs detected masses with 79% sensitivity and 50% specificity. Conclusion. Although preliminary , the combination of wavelet transform and ANN is promising and may pr ovide a viable method to prescreen mammograms for masses with high sen sitivity and reasonable specificity.