Breast Density Classification Using Histogram-Based Features

The risk of having cancer in dense breast on mammogram is higher compared to those who have less. This is due to presence of glandular cells in the breast parenchyma. Therefore, it is important for radiologists to pay more attention to denser breasts in order to detect abnormalities. Denser breast has tendency to hide breast lesions and therefore reduces the sensitivity of the radiologists to diagnose the condition. The aim of this paper is to explore a novel quantitative method to categorize breast density by using digital mammogram images. The suggested method works based on the statistical parameters including kurtosis, skewness, median and mean. The system evaluated 180 mammogram images and it was found to be 92.8% accurate with a strong correlation between the system and radiologists’ estimation (K=0.87, p=0.0001).