Breast Skin Line Segmentation on Digital Mammogram using Fractal Approach

Objective: To develop an algorithm for the identification of breast skin line in mammographic images and evaluate its performance against ground truth images. Methods/Analysis: A three stage processing pipeline was developed to segment the breast skin line. The first part of the segmentation used a pre-processing stage to remove artifacts and reduce image noise. The second stage employed a fractal based approach for segmentation and the third step detects the border region from the segmented image. Findings: The performance of the method has been evaluated using bench mark datasets from MIAS and DDSM. The results of the findings reveal that fractal based approach is an effective method to improve the skin line segmentation from mammogram images in the computer aided diagnosis. The algorithmic results of the segmentation were validated against the ground truth generated by manual segmentation. Improvement: The proposed method shows the importance of fractal analysis for breast skin line segmentation.