Lesion segmentation in breast sonography

Abstract. Sonography is gainingpopularity as an adjunct screening tech-nique for assessing abnormalities in the breast. This is particularly true in cases where the subject has dense breast tissue, wherein widespread tech-niques like Digital Mammography (DM) fail to produce reliable outcomes. This article proposes anovel and fully automaticmethodology for breast le-sion segmentation in B-mode Ultra-Sound (US) images by utilizing region, boundary and shape information to cope up with the inherent artifacts present in US images. The proposed approach has been evaluated using a set of sonographic images with accompanying expert-provided ground truth