Full Text:   <985>

Summary:  <202>

CLC number: TP391.4

On-line Access: 2017-05-24

Received: 2015-12-16

Revision Accepted: 2016-05-25

Crosschecked: 2017-04-27

Cited: 0

Clicked: 2106

Citations:  Bibtex RefMan EndNote GB/T7714


Gang Liu


-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2017 Vol.18 No.5 P.680-688


Label fusion for segmentation via patch based on local weighted voting

Author(s):  Kai Zhu, Gang Liu, Long Zhao, Wan Zhang

Affiliation(s):  School of Automation Engineering, Shanghai University of Electrical Power, Shanghai 200090, China; more

Corresponding email(s):   lukelg@gmail.com

Key Words:  Label fusion, Local weighted voting, Patch-based, Background analysis

Kai Zhu, Gang Liu, Long Zhao, Wan Zhang. Label fusion for segmentation via patch based on local weighted voting[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 680-688.

@article{title="Label fusion for segmentation via patch based on local weighted voting",
author="Kai Zhu, Gang Liu, Long Zhao, Wan Zhang",
journal="Frontiers of Information Technology & Electronic Engineering",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T Label fusion for segmentation via patch based on local weighted voting
%A Kai Zhu
%A Gang Liu
%A Long Zhao
%A Wan Zhang
%J Frontiers of Information Technology & Electronic Engineering
%V 18
%N 5
%P 680-688
%@ 2095-9184
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1500457

T1 - Label fusion for segmentation via patch based on local weighted voting
A1 - Kai Zhu
A1 - Gang Liu
A1 - Long Zhao
A1 - Wan Zhang
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 18
IS - 5
SP - 680
EP - 688
%@ 2095-9184
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1500457

label fusion is a powerful image segmentation strategy that is becoming increasingly popular in medical imaging. However, satisfying the requirements of higher accuracy and less running time is always a great challenge. In this paper we propose a novel patch-based segmentation method combining a local weighted voting strategy with Bayesian inference. Multiple atlases are registered to a target image by an advanced normalization tools (ANTs) algorithm. To obtain a segmentation of the target, labels of the atlas images are propagated to the target image. We first adopt intensity prior and label prior as two key metrics when implementing the local weighted voting scheme, and then compute the two priors at the patch level. Further, we analyze the label fusion procedure concerning the image background and take the image background as an isolated label when estimating the label prior. Finally, by taking the Dice score as a criterion to quantitatively assess the accuracy of segmentations, we compare the results with those of other methods, including joint fusion, majority voting, local weighted voting, majority voting based on patch, and the widely used FreeSurfer whole-brain segmentation tool. It can be clearly seen that the proposed algorithm provides better results than the other methods. During the experiments, we make explorations about the influence of different parameters (including patch size, patch area, and the number of training subjects) on segmentation accuracy.


概要:标记融合是医学图像处理中越来越受欢迎的一种强大的图像分割策略。然而,同时满足高精度和快速分割却是对算法的一个极大的挑战。结合局部加权表决策略和贝叶斯推论,本文提出了一种新的基于图块的分割算法。通过ANTs(Advanced normalization tools)算法将训练图谱图像向目标图像进行配准,并将配准后的训练图谱标记映射到目标图像中来获得分割结果。首先在执行局部加权表决策略中将灰度先验概率和标记先验概率作为两个关键的指标,然后在图块水平上计算这两种先验概率。接着在分析标记融合的过程中,首次提出了把图像的背景区域作为单独的一个标记值来处理,再估算标记先验概率的方案。最后,利用Dice score作为评估分割精度的标准,将该算法分割的结果与其他一些方法进行了比较,如多数表决、局部加权表决、基于图块的多数表决以及广泛运用于整个大脑分割的工具FreeSurfer。实验结果证明本文提出的算法要优于其他分割方法。在实验中,本文还讨论了不同参数(包括图块大小、图块面积和训练图谱个数)对分割精度的影响。


Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article


[1]Asman, A.J., Landman, B.A., 2013. Non-local statistical label fusion for multi-atlas segmentation. Med. Image Anal., 17(2):194-208.

[2]Avants, B.B., Tustison, N.J., Song, G., et al., reproducible evaluation of ANTs similarity metric performance in brain image registration. NeuroImage, 54(3):2033-2044.

[3]Cocosco, C., Zijdenbos, A., Evans, A., 2003. A fully automatic and robust brain MRI tissue classification method. Med. Image Anal., 7(4):513-527.

[4]Coupé, P., Manjón, J., Fonov, V., et al., 2011. Patch-based segmentation using expert priors: application to hippo-campus and ventricle segmentation. NeuroImage, 54(2): 940-954.

[5]Coupé, P., Eskildsen, S.F., Manjón, J.V., et al., 2012. Simultaneous segmentation and grading of anatomical structures for patient’s classification: application to Alzheimer’s disease. NeuroImage, 59(4):3736-3747.

[6]Eskildsen, S.F., Coupé, P., Fonov, V., et al., 2012. BEaST: brain extraction based on nonlocal segmentation technique. NeuroImage, 59(3):2362-2373.

[7]Ghasemi, J., Mollaei, M.R.K., Ghaderi, R., et al., 2012. Brain tissue segmentation based on spatial information fusion by Dempster-Shafer theory. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 13(7):520-533.

[8]Isgum, I., Staring, M., Rutten, A., et al., 2009. Multi-atlas-based segmentation with local decision fusion— application to cardiac and aortic segmentation in CT scans. IEEE Trans. Med. Imag., 28(7):1000-1010.

[9]Manjón, J.V., Carbonell-Caballero, J., Lull, J.J., et al., 2008. MRI denoising using non-local means. Med. Image Anal., 12(4):514-523.

[10]Rohlfing, T., Brandt, R., Menzel, R., et al., 2004. Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains. NeuroImage, 21(4):1428-1442.

[11]Rousseau, F., Habas, P.A., Studholme, C., 2011. A supervised patch-based approach for human brain labeling. IEEE Trans. Med. Imag., 30(10):1852-1862.

[12]Sabuncu, M.R., Yeo, B.T.T., van Leemput, K., et al., 2010. A generative model for image segmentation based on label fusion. IEEE Trans. Med. Imag., 29(10):1714-1729.

[13]Shi, F., Yang, J., Zhu, Y.M., 2009. Automatic segmentation of bladder in CT images. J. Zhejiang Univ.-Sci. A, 10(2): 239-246.

[14]Wang, H.Z., Yushkevich, P.A., 2013. Multi-atlas segmentation with joint label fusion and corrective learning—an open source implementation. Front. Neuroinform., 7:27.

[15]Wang, H.Z., Suh, J.W., Das, S.R., et al., 2013. Multi-atlas segmentation with joint label fusion. IEEE Trans. Patt. Anal. Mach. Intell., 35(3):611-623.

[16]Wang, L., Shi, F., Li, G., et al., 2014. Segmentation of neonatal brain MR images using patch-driven level sets. NeuroImage, 84(1):141-158.

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE