Improving mammogram screening using a bank of support vector machines (SVMs)

The focus of this study was to build and evaluate a new bank of SVM designs to address the problem of high false positives that currently results from mammogram screening,. The basis of the design is to partition the BIRADS™ varibles into three separate categories based on our understanding of the discriminating information contained in the mammogram BIRADS™ findings. That is, after ascertaining the presence of a suspecious finding on a mammogram that would be recommended for biopsy, the radiologist documents the BIRADS™ lesion descriptor values. This information, along with the clinical history, would be used as imput to this new bank of SVMs an aid to the physican for improving the specificity and positive predictive value PPV of the benign/malignant diagnosis task. Comparing the new SVM mass classifier with the previously configured single SVM that used all data base imputs provided significant classification accuracy improvemens for all performance measures. That is, overall Az improved by 11.6%, specificity and PPV improved by 110.6% and 31.6%, respecitvely, at 100% sensitivity (missing no cancers), while specificity and PPV improved by 54% and 35.9%, respectively, at 95% sensitivity (missing 5% of the cancers).

Duke Scholars

Author Joseph Yuan-Chieh Lo Radiology