Accurate Breast Region Detection in Digital Mammograms Using a Local Adaptive Thresholding Method
Maysam Shahedi, Rassoul Amirfattahi, Farah Torkamani Azar, Saeed Sadri · 2007
Recently computer aided diagnosis (CAD) systems have improved diagnosis of abnormalities in mammogram images. To improve the accuracy and reliability of such systems, the exact breast region as the region of interest (ROI), has to be segmented. Furthermore, focus on ROI can eliminates the effect of image background noise. Consequently it can reduce the detection algorithms execution time. Also, the accurate breast region detection ends to the accurate breast border detection, which can improve clinical diagnosis of abnormalities. Currently, new methods have been presented that achieve the accurate breast border detection. Nevertheless most of these methods are complicated and have undesirable effects on the execution time. In this paper we proposed a novel approach for accurate breast region segmentation in digital mammograms based on local thresholds. The suggested method can extract the breast region accurately.