Mammographic density classification

The purpose of this study is to develop mammographic density classification, which consists of three major steps. Firstly, the digitization of mammographic images module for images and data archiving. Secondly, a morphological segmentation algorithm is proposed to detect the segment of mammographic masses with salt-and-pepper noise. Thirdly, the percentage of fibroglandular tissue in the total of breast tissue area is calculated and classified with BI-RADS criteria. The experimental results show that the proposed algorithm is more efficient for medical image denoising and segmentation than the usually used template-based segmentation algorithms. The overall accuracy of computerized method classification is 75%. The Kappa coefficient (0.67) indicates the good relationship and Chi-square value (7.69, p=0.053) shows no statistically significant difference. In conclusion, the computerized method based on the morphological segmentation is useful as the radiologist assistant for classifying mammographic density and is suitable for mammographic density classification.