{"title":"A phase-based active contour model for segmentation of breast ultrasound images","authors":"Lingyun Cai, Yuanyuan Wang","doi":"10.1109/BMEI.2013.6746913","DOIUrl":null,"url":null,"abstract":"Due to the speckle noises, low contrast and blurry boundaries in breast ultrasound (BUS) images, extraction of the boundaries in BUS images is always a challenging task. To solve this problem, a novel phase-based active contour (PBAC) model is proposed. First, we utilize the local phase information and apply the phase asymmetry approach to form a new edge indicator, which dramatically increases the robustness to intensity inhomogeneous. Then, a novel phase-based edge indicator is incorporated into a various level set formulation with the local region-based segmentation energy. Experiments are performed on both synthetic and real BUS images. The results show that the proposed PBAC model outperforms the state-of-art methods both qualitatively and quantitatively.","PeriodicalId":163211,"journal":{"name":"2013 6th International Conference on Biomedical Engineering and Informatics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 6th International Conference on Biomedical Engineering and Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/BMEI.2013.6746913","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
Due to the speckle noises, low contrast and blurry boundaries in breast ultrasound (BUS) images, extraction of the boundaries in BUS images is always a challenging task. To solve this problem, a novel phase-based active contour (PBAC) model is proposed. First, we utilize the local phase information and apply the phase asymmetry approach to form a new edge indicator, which dramatically increases the robustness to intensity inhomogeneous. Then, a novel phase-based edge indicator is incorporated into a various level set formulation with the local region-based segmentation energy. Experiments are performed on both synthetic and real BUS images. The results show that the proposed PBAC model outperforms the state-of-art methods both qualitatively and quantitatively.