Automatic detection of suspicious lesions in mammograms by histogram-peak-analysis based K-means
Ilhame Ait Lbachir, Imane Daoudi, Saadia Tallal · 2018
Mammography is currently the most powerful technique for early detection of breast cancer. To better interpret mammogram images and assist radiologists in their decision, Computer-Aided-Detection (CAD) systems have been proposed. In this paper, we present a novel algorithm for abnormalities segmentation in mammograms. The proposed method combines global thresholding and K-means algorithms to extract suspicious lesions in mammogram images. The algorithm has been tested on 170 mammograms in the Mammographic Image Analysis Society MIAS database. The experimental results show that the proposed method outperforms other state-of-the-art methods for lesions detection in mammography.