Automatic Pectoral Muscle Segmentation on Mediolateral Oblique View Mammograms

Abstract

Abstract-Mammograms are X-ray images of the breast which are used to detect breast cancer. When mammograms are analyzed by computer, the pectoral muscle should preferably be excluded from processing intended for the breast tissue. For this and other reasons, it is important to identify and segment out the pectoral muscle. In this paper, a new, adaptive algorithm is proposed to automatically extract the pectoral muscle on digitized mammograms; it uses knowledge about the position and shape of the pectoral muscle on mediolateral oblique views. The pectoral edge is first estimated by a straight line which is validated for correctness of location and orientation. This estimate is then refined using iterative "cliff detection" to delineate the pectoral margin more accurately. Finally, an enclosed region, representing the pectoral muscle, is generated as a segmentation mask. The algorithm was found to be robust to the large variations in appearance of pectoral edges, to dense overlapping glandular tissue, and to artifacts like sticky tape. The algorithm has been applied to the entire Mammographic Image Analysis Society (MIAS) database of 322 images. The segmentation results were evaluated by two expert mammographic radiologists, who rated 83.9% of the curve segmentations to be adequate or better.

A new computer‐aided detection approach based on analysis of local and global mammographic feature asymmetry

“…In the last preprocessing step, we remove the pectoral muscle using an algorithm described in Ref. The preprocessing phase yields an image containing the breast area alone, as shown in Fig. (b).…”

A fully automated complete segmentation scheme for mammograms

“…Pectoral muscle is a high-intensity, triangular region across the upper posterior margin of the image, appeared only in medio-Iateral oblique view mammograms, as it is obvious at The techniqu e used to segment it [7] can be divided into:…”

“…Automatic segmentation of the pectoral muscle can be useful in many ways [7]. One example is the reduction of the false positives of mass detection procedure, because of the similarity between the pectoral region and the mammographic parenchyma.…”

“…We implement the algorithm used in [8] to extract the breast boundary; we modify the algorithm in [7] to improve the pectoral muscle estimation; and we propose a new nipple detection technique for the mammograms, which include the nipple in profile, using the output of the breast boundary extraction procedure. The latter novel algorithm proposed in this work not only 10-cates the nipple point, but also can serve as an improvement for the existing breast boundary algorithm, which misses the nipple, if it is in profile.…”

Straight Line Approximation of Pectoral Muscle in Mammogram Using the Method of Optimum Thresholding

“…An efficient detection algorithm based on Gabor wavelet is employed in [9] to obtain a smooth pectoral edge. An iterative thresholding method is used in [10] to detect pectoral muscle. Two graph-based detection methods were realized in [11] and [12].…”