Automatic Extraction of Breast Region in Raw Mammograms Using a Combined Strategy

Abstract

Breast region segmentation is a preliminary task in computer-aided-diagnosis (CAD) systems for breast cancer detection. Its accurate extraction improves CAD performances in terms of false positive and computation time. This paper presents a method for automatic breast region extraction in raw mammograms using a two-step strategy. First, a contrast-correction is applied to uniform gray level in breast region then a clustering algorithm is used to assign pixels to their respective class distribution prior to breast region segmentation. The performances of the proposed method tested on images from MIAS database are 95.6%, 96.0% and 99.8% for accuracy, completeness and correctness respectively.