Simultaneous segmentation and bias field estimation using local fitted images

PATTERN RECOGNITION

卷:74

Article

Wang, Lei^1,2  Zhu, Jianbing^3,4  Sheng, Mao⁵  Cribb, Adriena^1,2  Zhu, Shaocheng⁶  Pu, Jiantao^1,2 

[1] Univ Pittsburgh, Dept Radiol, Pittsburgh, PA 15260 USA

[2] Univ Pittsburgh, Dept Bioengn, Pittsburgh, PA 15260 USA

[3] Nanjing Med Univ, Suzhou Hosp, Suzhou 215153, Peoples R China

[4] Suzhou Sci & Technol Town Hosp, Suzhou 215153, Peoples R China

[5] Soochow Univ, Childrens Hosp, Dept Radiol, Suzhou 215003, Peoples R China

[6] Henan Prov Peoples Hosp, Dept Radiol, Zhengzhou 450003, Henan, Peoples R China

关键词: Level set;    Image segmentation;    Local fitted images;    Intensity inhomogeneity;    Bias field;   

DOI  :  10.1016/j.patcog.2017.08.031

来源: Elsevier

【 摘 要 】

Level set methods often suffer from boundary leakage and inadequate segmentation when used to segment images with inhomogeneous intensities. To handle this issue, a novel region-based level set method was developed, in which two different local fitted images are used to construct a hybrid region intensity fitting energy functional. This novel method enables simultaneous segmentation of the regions of interest and estimation of the bias fields from inhomogeneous images. Our experiments on both synthetic images and a publicly available dataset demonstrate the feasibility and reliability of the proposed method. (C) 2017 Elsevier Ltd. All rights reserved.

【 授权许可】

Free