Label fusion for segmentation via patch based on local weighted voting

Kai ZHU; Gang LIU; Long ZHAO; Wan ZHANG

doi:10.1631/FITEE.1500457

Your Location：

Home >

Browse articles >

Label fusion for segmentation via patch based on local weighted voting

Regular Papers | Updated：2022-05-19

- Label fusion for segmentation via patch based on local weighted voting
- 基于图块的局部加权表决标记融合分割算法
- Frontiers of Information Technology & Electronic Engineering Vol. 18, Issue 5, Pages: 680-688(2017)
- Affiliations：
  
  1School of Automation Engineering, Shanghai University of Electrical Power, Shanghai 200090, China
  2Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA 02129, USA
- Author bio：
  
  E-mail:lukelg@gmail.com
- Funds：
- DOI：10.1631/FITEE.1500457
  CLC： TP391.4
- Received：16 December 2015，
  
  Accepted：25 May 2016，
  
  Published：2017-05
- Accepted：
Scan QR Code
Kai ZHU, Gang LIU, Long ZHAO, et al. Label fusion for segmentation via patch based on local weighted voting[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 680-688.
DOI：

Kai ZHU, Gang LIU, Long ZHAO, et al. Label fusion for segmentation via patch based on local weighted voting[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 680-688. DOI： 10.1631/FITEE.1500457.

摘要

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。

Abstract

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.

关键词

Keywords

references

AJ Asman , , , BA Landman . . Non-local statistical label fusion for multi-atlas segmentation . . Med. Image Anal. , , 2013 . . 17 ( ( 2 ): ): 194 - - 208 . . DOI: 10.1016/j.media.2012.10.002 http://doi.org/10.1016/j.media.2012.10.002 . .

BB Avants , , , NJ Tustison , , , G Song , , , 等 . . A reproducible evaluation of ANTs similarity metric performance in brain image registration . . NeuroImage , , 2011 . . 54 ( ( 3 ): ): 2033 - - 2044 . . DOI: 10.1016/j.neuroimage.2010.09.025 http://doi.org/10.1016/j.neuroimage.2010.09.025 . .

C Cocosco , , , A Zijdenbos , , , A Evans . . A fully automatic and robust brain MRI tissue classification method . . Med. Image Anal. , , 2003 . . 7 ( ( 4 ): ): 513 - - 527 . . DOI: 10.1016/S1361-8415(03)00037-9 http://doi.org/10.1016/S1361-8415(03)00037-9 . .

P Coupé , , , J Manjón , , , V Fonov , , , 等 . . Patch-based segmentation using expert priors: application to hippo- campus and ventricle segmentation . . NeuroImage , , 2011 . . 54 ( ( 2 ): ): 940 - - 954 . . DOI: 10.1016/j.neuroimage.2010.09.018 http://doi.org/10.1016/j.neuroimage.2010.09.018 . .

P Coupé , , , SF Eskildsen , , , JV Manjón , , , 等 . . Simultaneous segmentation and grading of anatomical structures for patient's classification: application to Alzheimer's disease . . NeuroImage , , 2012 . . 59 ( ( 4 ): ): 3736 - - 3747 . . DOI: 10.1016/j.neuroimage.2011.10.080 http://doi.org/10.1016/j.neuroimage.2011.10.080 . .

SF Eskildsen , , , P Coupé , , , V Fonov , , , 等 . . BEaST: brain extraction based on nonlocal segmentation technique . . NeuroImage , , 2012 . . 59 ( ( 3 ): ): 2362 - - 2373 . . DOI: 10.1016/j.neuroimage.2011.09.012 http://doi.org/10.1016/j.neuroimage.2011.09.012 . .

J Ghasemi , , , MRK Mollaei , , , R Ghaderi , , , 等 . . Brain tissue segmentation based on spatial information fusion by Dempster-Shafer theory . . J. Zhejiang Univ.-Sci. C (Comput. & Electron.) , , 2012 . . 13 ( ( 7 ): ): 520 - - 533 . . DOI: 10.1631/jzus.C1100288 http://doi.org/10.1631/jzus.C1100288 . .

I Isgum , , , M Staring , , , A Rutten , , , 等 . . Multi-atlas- based segmentation with local decision fusion-application to cardiac and aortic segmentation in CT scans . . IEEE Trans. Med. Imag. , , 2009 . . 28 ( ( 7 ): ): 1000 - - 1010 . . DOI: 10.1109/TMI.2008.2011480 http://doi.org/10.1109/TMI.2008.2011480 . .

JV Manjón , , , J Carbonell-Caballero , , , JJ Lull , , , 等 . . MRI denoising using non-local means . . Med. Image Anal. , , 2008 . . 12 ( ( 4 ): ): 514 - - 523 . . DOI: 10.1016/j.media.2008.02.004 http://doi.org/10.1016/j.media.2008.02.004 . .

T Rohlfing , , , R Brandt , , , R Menzel , , , 等 . . Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains . . NeuroImage , , 2004 . . 21 ( ( 4 ): ): 1428 - - 1442 . . DOI: 10.1016/j.neuroimage.2003.11.010 http://doi.org/10.1016/j.neuroimage.2003.11.010 . .

F Rousseau , , , PA Habas , , , C Studholme . . A supervised patch-based approach for human brain labeling . . IEEE Trans. Med. Imag . , , 2011 . . 30 ( ( 10 ): ): 1852 - - 1862 . . DOI: 10.1109/TMI.2011.2156806 http://doi.org/10.1109/TMI.2011.2156806 . .

MR Sabuncu , , , BTT Yeo , , , K van Leemput , , , 等 . . A generative model for image segmentation based on label fusion . . IEEE Trans. Med. Imag. , , 2010 . . 29 ( ( 10 ): ): 1714 - - 1729 . . DOI: 10.1109/TMI.2010.2050897 http://doi.org/10.1109/TMI.2010.2050897 . .

F Shi , , , J Yang , , , YM Zhu . . Automatic segmentation of bladder in CT images . . J. Zhejiang Univ.-Sci. A , , 2009 . . 10 ( ( 2 ): ): 239 - - 246 . . DOI: 10.1631/jzus.A0820157 http://doi.org/10.1631/jzus.A0820157 . .

HZ Wang , , , PA Yushkevich . . Multi-atlas segmentation with joint label fusion and corrective learning-an open source implementation . . Front. Neuroinform. , , 2013 . . 7 27 DOI: 10.3389/fninf.2013.00027 http://doi.org/10.3389/fninf.2013.00027 . .

HZ Wang , , , JW Suh , , , SR Das , , , 等 . . Multi-atlas segmentation with joint label fusion . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2013 . . 35 ( ( 3 ): ): 611 - - 623 . . DOI: 10.1109/TPAMI.2012.143 http://doi.org/10.1109/TPAMI.2012.143 . .

L Wang , , , F Shi , , , G Li , , , 等 . . Segmentation of neonatal brain MR images using patch-driven level sets . . NeuroImage , , 2014 . . 84 ( ( 1 ): ): 141 - - 158 . . DOI: 10.1016/j.neuroimage.2013.08.008 http://doi.org/10.1016/j.neuroimage.2013.08.008 . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰