Computer-aided polyp detection in CT colonography using an ensemble of support vector machines

Abstract

In this paper, we propose a new classification scheme for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The scheme involves an ensemble of support vector machines (SVMs) for classification, a smoothed leave-one-out (SLOO) cross-validation method for obtaining error estimates, and the use of a bootstrap aggregation method for training and model selection. Our use of an ensemble of SVM classifiers with bagging (bootstrap aggregation), built on different feature subsets, is intended to improve classification performance when compared to single SVMs and to reduce the number of false positive detections. The bagging technique has the effect of a virtual increase in the training set size and, as a consequence, also helps to reduce the bias of error estimates when combined with a leave-one-out cross-validation approach. The bootstrap-based model selection technique is used for tuning the SVM parameters.