Breast Segmentation in Mammograms using Manual Thresholding

Ashutosh Kr. Chaubey

Breast segmentation is an important pre-process in mammogram image processing and computer-aided diagnosis of breast cancer. Limiting the area to be processed into a specific target region in an image would increase the accuracy and efficiency of processing algorithms. In this paper we are presenting a algorithm for estimating breast segmentation using manual thresholding and extracting the region based on area and Centroid and also briefing about different methods such as Fast marching, watershed algorithm, tracking etc. We have evaluated the performance of the algorithm by using 100 mammogram images taken from mini-MIAS database. The results obtained from the experimental evaluation indicate that this algorithm explains 98.6% of the ground truth breast region and accuracy of the segmentation is 90.1% .