A Computer Aided Diagnosis System for Breast Cancer Using Support Vector Machine

Abstract

This article introduces a computer aided diagnosis scheme using support vector machine, in conjunction with moment-based feature extraction. An application of ultrasound breast cancer imaging has been chosen and computer aided diagnosis scheme have been applied to see their ability and accuracy to classify the breast cancer images into two outcomes: cancer or non-cancer. The introduced scheme starts with a preprocessing phase to enhance the quality of the input breast ultrasound images and to reduce speckle without destroying the important features of input ultrasound images for diagnosis. This is followed by performing the seeded-threshold growing region algorithm in order to identify the region of interest and to detect the boundary of the breast pattern. Then, moment-based features are extracted. Finally, a support vector machine classifier were employed to evaluate the ability of the lesion descriptors for discrimination of different regions of interest to determine whether they represent cancer or not. To evaluate the performance of presented scheme, we present tests on different breast ultrasound images. The experimental results obtained, show that the overall accuracy offered by the employed support vector machine was 98.1%, whereas classification ratio using neural network was 92.8%.