计算机科学 ›› 2014, Vol. 41 ›› Issue (9): 297-300.doi: 10.11896/j.issn.1002-137X.2014.09.057

• 图形图像与模式识别 • 上一篇    下一篇

基于MultiLayer水平集的脑MRI图像分割框架

朱晓舒,孙权森,夏德深,孙怀江   

  1. 南京理工大学计算机科学与技术学院 南京210094;南京师范大学分析测试中心 南京210046;南京理工大学计算机科学与技术学院 南京210094;南京理工大学计算机科学与技术学院 南京210094;南京理工大学计算机科学与技术学院 南京210094
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(60773172)资助

Framework of Brain MRI Images Segmentation Based on MultiLayer Level Set

ZHU Xiao-shu,SUN Quan-sen,XIA De-shen and SUN Huai-jiang   

  • Online:2018-11-14 Published:2018-11-14

摘要: 提出了一种新的自动初始化水平集的方法和基于MultiLayer水平集的活动轮廓模型。该模型同时进行偏移场去除和图像分割,因此可以有效地克服灰度不均匀性的影响。最后利用了大脑皮层的距离信息,在框架中增加了厚度约束项。实验结果显示,相比著名的LBF模型,该框架不但可以获得更高的分割精度,而且分割时间也大大减少。

关键词: 图像分割框架,LBF模型,MultiLayer水平集,变分法

Abstract: This paper proposed a new automated method to initialize level set function and a region-based active contour model based on MultiLayer level set formulation.Because of jointing segmentation and bias correction of images,the proposed model can overcome intensity inhomogeneity.Finally,considering the distance information of cerebral cortex,a thickness constraint item was added to segmentation framework.Experimental results show that our framework can segment images more precisely and much faster than the well-known LBF model.

Key words: Image segmentation framework, LBF model,MultiLayer level set method,Variational method

[1] Wells W,Grimson E,Kikinis R,et al.Adaptive segmentation of MRI data[J].IEEETrans.Med Imag,1996,15(4):429-442
[2] Leemput V,Maes K,Vandermeulen D,et al.Automated Model-Based Bias Field Correction of MR Images of the Brain [J].IEEETrans.Med Imag,1999,18(10):885-896
[3] Ahmed M,Yamany S,Mohamed N,et al.A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data [J].IEEETrans.Med Imag,2002,21(3):193-199
[4] Paragios N,Deriche R.Geodesic active regions and level setmethods for supervised texture segmentation [J].Int’l J.Comp.Vis,2002,46:223-247
[5] Chan T,Vese L.Active contours without edges [J].IEEETrans.Imag.Proc,2001,10:266-277
[6] Li C,Kao C K,Gore J C,et al.Implicit active contours driven by local binary fitting energy [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington D C,2007:1-7
[7] 王利,陈允杰,韦志辉,等.克服灰度不均匀性的脑MR图像分割模型 [J].计算机辅助设计与图形学学报,2009,21(11):1624-1631
[8] Chan T,Vese L.A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model[J].International Journal of Computer Vision,2002,0(3):271-293
[9] Chung G,Vese L.Energy minimization based segmentation and denoising using a multilayer level set approach [C]∥EMMCVPR 2005.2005,3757:439-455
[10] Chung G,Vese L.Image segmentation using a multilayer level-set approach [J].Computing and Visualization in Science,2009,12(6):267-285
[11] Li C,Li F,Kao C Y,et al.Image Segmentation with Simultaneous Illumination and Reflectance Estimation:An Energy Minimization Approach[C]∥Proceedings of the Eighth International Conference on Computer Vision (ICCV).2009
[12] http://www.bic.mni.mcgill.ca/brainweb/
[13] Shattuck D W,Sandor-Leahy S R,Schaper K A,et al.Magnetic resonance image tissue classification using a partial volume mo-del [J].Neuroimage,2001,13:856-876

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!