Pectoral muscle identification in mammograms

Abstract

In most of the approaches of computer‐aided detection of breast cancer, one of the preprocessing steps applied to the mammogram is the removal/suppression of pectoral muscle, as its presence within the mammogram may adversely affect the outcome of cancer detection processes. Through this study, we propose an efficient automatic method using the watershed transformation for identifying the pectoral muscle in mediolateral oblique view mammograms. The watershed transformation of the mammogram shows interesting properties that include the appearance of a unique watershed line corresponding to the pectoral muscle edge. In addition to this, it is observed that the pectoral muscle region is oversegmented due to the existence of several catchment basins within the pectoral muscle. Hence, a suitable merging algorithm is proposed to combine the appropriate catchment basins to obtain the correct pectoral muscle region. A total of 84 mammograms from the mammographic image analysis database were used to validate this approach. The mean false positive and mean false negative rates, obtained by comparing the results of the proposed approach with manually‐identified (ground truth) pectoral muscle boundaries, respectively, were 0.85% and 4.88%. A comparison of the results of the proposed method with related state‐of‐the‐art methods shows that the performance of the proposed approach is better than the existing methods in terms of the mean false negative rate. Using Hausdorff distance metric, the comparison of the results of the proposed method with ground truth shows low Hausdorff distances, the mean and standard deviation being 3.85±1.07 mm.PACS numbers: 87.57.R, 87.57.nm, 87.59.ej, 87.85.Ng, 87.85.Pq

Pectoral Muscle Segmentation in Mammograms Based on Cartoon-Texture Decomposition

“…Another common performance measure pectoral muscle segmentation is the average rate of false positives (FP) and false negatives (FN) found in a segmentation. Both of these coefficients, as well as the average Hausdorff distance, for our method and the techniques suggested in [6], [7], [4], [8], and [5] are displayed in Table 3. We see that our method slightly outperforms the other techniques.…”

“…To take into account texture as well as intensity cues, filtering approaches have been designed, such as the method proposed in [6], where a Gabor wavelets filter bank is applied to emphasize the pectoral muscle edge. Region growing and merging techniques have also been explored, such as in [7], where the watershed segmentation method is applied to obtain an initial over-segmentation that is refined afterwards by means of an specialized region merging algorithm.…”

A Novel Approach for Removal of Pectoral Muscles in Digital Mammogram

“…In this approach they used graph cut based merging method and a Bezier curve algorithm for pectoral muscle identification. In another approach they used watershed transform method to identify pectoral muscles 14 .R. S. Chandra Boss et al propose a method to extract breast region and removal of pectoral muscles using histogram based 8-neighborhood connected component labeling method 15 .…”

A novel multistage system for the detection and removal of pectoral muscles in mammograms

“…Intensity-based approaches are based on the fact that the intensity range of a pectoral muscle region should be higher than the range of breast parenchyma. These approaches directly utilize the pixel intensities [2][3][4][5][6][7], image histograms [8][9][10], and image gradients [11], or they are applied to image gradients [12]. Additionally, there are also some studies that segment pectoral muscles in wavelet domain instead of spatial domain [13][14][15].…”