A Region Growing-based Method for Pectoral Muscle Segmentation in Digital Mammograms

C. Lampasona and D. Roller (Germany)

Keywords

Medical image analysis, digital mammography, pectoral muscle, region-growing segmentation, edge detection.

Abstract

Previous works on the automatic detection of abnormalities in breast tissue from mammograms show that the feature extraction process may be affected by the presence of the pectoral muscle. It is therefore important to segment the mammogram into interesting regions. In this contribution a fully automatic method for pectoral muscle segmentation is presented, which profits of the special characteristics of full-field digital mammograms.

Important Links:



Go Back