Effect of adaptive-neighborhood contrast enhancement on the extraction of the breast skin-line in mammograms

Extraction of the breast skin-line is crucial in computer-aided analysis of mammograms. This paper presents an analysis of the effect of adaptive-neighborhood contrast enhancement (ANCE) [1] on skin-line extraction. ANCE is used to enhance the parenchyma of the breast and suppress the background noise. Suppression of the background noise can improve skin-line extraction. Our skin-line extraction method is based on the work by Ojala ef al. [2]. We use the Hausdorff distance [3, 4] for quantitative comparison of the skin-lines. Our work shows that ANCE improves the skin-line extraction due to its ability of suppressing noise while improving the contrast. We have defined an improvement factor based on the Hausdorff distance. The metric allows us to spot automatically the mammograms with significant improvement in the detection of the skin-line because of ANCE. We tested 83 images from the MIAS database [5], with the ground-truth skin-lines hand-drawn by a radiologist [6]. The average Hausdorff distance improvement with ANCE was 11 pixels (2.2 mm).