Pectoral Muscle Removal in Digital Mammograms Using Region Based Standard Otsu Technique

Mammography is usually the first preference of imaging diagnostic modalities used for detection breast cancer in early stage. Two projections Cranio Caudal (CC) and Medio-Lateral Oblique (MLO) which depict different degrees visualizing are during digital mammogram acquisition MLO view shows more tissue Pectoral Muscle (PM) area when compared to CC view. Although, PM a criterion show proper positioning, it can result biased results mammographic analysis like: density estimation, because has similar or even higher intensity than lesions if present. This paper proposed Region Based Standard Otsu thresholding method elimination present mammograms. The algorithm was implemented using 322 mammograms from Mammographic Image Analysis Society (MIAS) database, difference between detected manually drawn region by an expert evaluated. showed average: Jaccard Similarity Index, False Positive Rate (FPR) Negative (FNR) 93.2%, 3.54% 5.68% respectively also acceptable rate 95.65%