False-Positive Reduction in Computer-Aided Detection of Polyps in CT Colonography: A Massive-Training Support Vector Regression Approach

Abstract

AbstractA massive-training artificial neural network (MTANN) has been investigated for reduction of false positives (FPs) in computer-aided detection (CADe) of polyps in CT colonography (CTC). A major limitation of the MTANN is a long training time. To address this issue, we investigated the feasibility of a support vector regression (SVR) in the massive-training framework and developed a massive-training SVR (MTSVR). To test the proposed MTSVR, we compared it with the original MTANN in FP reduction in CADe of polyps in CTC. With MTSVR, we reduced the training time by a factor of 190, while achieving a performance (by-polyp sensitivity of 94.7% with 2.5 FPs/patient) comparable to that of the original MTANN (which has the same sensitivity with 2.6 FPs/patient).Keywordscolorectal cancercomputer-aided detectionfalse-positive reductionpixel-based machine learningsupport vector regression