A novel feature for polyp detection in wireless capsule endoscopy images

Wireless capsule endoscopy (WCE) has been widely used in hospitals in the last few years due to its advantage of non-invasive and painless nature. However, this new technology produces about 55,000 images for each patient and poses a great burden on the professional clinicians to review these images, thus an automatic computer-aided diagnosis technique is in high demand. In this paper, we propose a new feature integrating the Gabor filter and Monogenic-Local Binary Pattern (M-LBP) methods in color components for polyp detection. The new feature not only can represent shape and edge information under multi-resolution, but also preserve color information. The proposed method is composed of the following steps: the first step is to transform the original WCE images into different color space and extract the corresponding Gabor responses of the color components. Next the M_LBP descriptors applied on the resulting Gabor responses are concatenated together to characterize the images. Finally we apply Linear Discriminant Analysis (LDA) to reduce feature dimensions and conduct experiments with the Support Vector Machine (SVM) classifier on a set of images containing 436 polyp images and 436 normal images. The experimental results achieved an encouraging polyp detection accuracy of 91.43%, showing that the new feature provides a good characterization and description of the WCE images for polyp classification tasks. To compare the performance of the proposed method, several traditional features have been considered and the proposed method has surpassed the alternative techniques significantly.