Automatic Segmentation of Ultrasound Tomography Image. (10th September 2017)

• Record Type: Journal Article
• Authors: Wu, Shibin; Yu, Shaode; Zhuang, Ling; Wei, Xinhua; Sak, Mark; Duric, Neb; Hu, Jiani; Xie, Yaoqin
• Other Names: Corsi Cristiana Academic Editor.
• Is Part Of: BioMed research international. Volume 2017(2017)
• Publication Date: 2017-09-10
• Subjects: Medicine -- Periodicals; Biology -- Periodicals; Biotechnology -- Periodicals; Life sciences -- Periodicals; 610.5
• DOI: 10.1155/2017/2059036
• Languages: English
• ISSNs: 2314-6133

Abstract

Abstract : Ultrasound tomography (UST) image segmentation is fundamental in breast density estimation, medicine response analysis, and anatomical change quantification. Existing methods are time consuming and require massive manual interaction. To address these issues, an automatic algorithm based on GrabCut (AUGC) is proposed in this paper. The presented method designs automated GrabCut initialization for incomplete labeling and is sped up with multicore parallel programming. To verify performance, AUGC is applied to segment thirty-two in vivo UST volumetric images. The performance of AUGC is validated with breast overlapping metrics (Dice coefficient (D ), Jaccard (J ), and False positive (FP)) and time cost (TC). Furthermore, AUGC is compared to other methods, including Confidence Connected Region Growing (CCRG), watershed, and Active Contour based Curve Delineation (ACCD). Experimental results indicate that AUGC achieves the highest accuracy (D = 0.9275 and J = 0.8660 and F P = 0.0077 ) and takes on average about 4 seconds to process a volumetric image. It was said that AUGC benefits large-scale studies by using UST images for breast cancer screening and pathological quantification.