Massive-Training Support Vector Regression With Feature Selection in Application of Computer-Aided Detection of Polyps in CT Colonography

Abstract

A major challenge in the latest computer-aided detection (CADe) of polyps in CT colonography (CTC) is to improve the false positive (FP) rate while maintaining detection sensitivity. Radiologists prefer CADe system produce small number of false positive detections, otherwise they might not consider CADe system improve their workflow. Towards this end, in this study, we applied a nonlinear regression model operating on CTC image voxels directly and a nonlinear classification model with extracted image features based on support vector machines (SVMs) in order to improve the specificity of CADe of polyps. We investigated the feasibility of a support vector regression (SVR) in the massive-training framework, and we developed a massive-training SVR (MTSVR) in order to reduce the long training time associated with the massive-training artificial neural network (MTANN) for reduction of FPs in CADe of polyps in CTC. In addition, we proposed a feature selection method directly coupled with an SVM classifier to maximize the CADe system performance. We compared the proposed feature selection method with the conventional stepwise feature selection based on Wilks' lambda with a linear discriminant analysis classifier. The FP reduction system based on the proposed feature selection method was able to achieve a 96.0% by-polyp sensitivity with an FP rate of 4.1 per patient. The performance is better than that of the stepwise feature selection based on Wilks' lambda (which yielded the same sensitivity with 18.0 FPs/patient). To test the performance of the proposed MTSVR, we compared it with the original MTANN in the distinction between actual polyps and various types of FPs in terms of the training time reduction and FP reduction performance. The CTC database used in this study consisted of 240 CTC datasets obtained from 120 patients in the supine and prone positions. 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).