Segmentation of the Thalamus in Multi-Spectral MR Images Using a Combination of Atlas-Based and Gradient Graph Cut Methods
文献类型: 会议论文
第一作者: Ryan Datteri
作者: Ryan Datteri 1 ; Christian Barillot 2 ; Benoit M. Dawant 1 ; Jeremy Lecoeur 2 ;
作者机构: 1.Department of Electrical Engineering and Computer Science, Vanderbilt University Nashville, TN 37235, USA
2.VisAGeS team, INRIA, IRISA, CNRS, INSERM, Rennes, France
关键词: ABA;non-rigid registration;thalamus segmentation;graph cut;spectral gradient
会议名称: Conference on image processing
主办单位:
页码: 76233N.1-76233N.9
摘要: Two popular segmentation methods used today are atlas based and graph cut based segmentation techniques. The atlas based method deforms a manually segmented image onto a target image, resulting in an automatic segmentation. The graph cut segmentation method utilizes the graph cut paradigm by treating image segmentation as a max-flow problem. A specialized form of this algorithm was developed by Lecoeur et al [1], called the spectral graph cut algorithm. The goal of this paper is to combine both of these methods, creating a more stable atlas based segmentation algorithm that is less sensitive to the initial manual segmentation. The registration algorithm is used to automate and initialize the spectral graph cut algorithm as well as add needed spatial information, while the spectral graph cut algorithm is used to increase the robustness of the atlas method. To calculate the sensitivity of the algorithms, the initial manual segmentation of the atlas was both dilated and eroded 2 mm and the segmentation results were calculated. Results show that the atlas based segmentation segments the thalamus well with an average Dice Similarity Coefficient (DSC) of 0.87. The spectral graph cut method shows similar results with an average DSC measure of 0.88, with no statistical difference between the two methods. The atlas based method's DSC value, however, was reduced to 0.76 and 0.67 when dilated and eroded respectively, while the combined method retained a DSC value of 0.81 and 0.74, with a statistical difference found between the two methods.
分类号: R312`R312
- 相关文献
[1]外源NO对NaCl胁迫下番茄幼苗生长及相关物质含量的影响. 吴雪霞,朱为民,陈建林,查丁石. 2008
[2]Effects of exogenous ABA and cytokinin on leaf photosynthesis and grain protein accumulation in wheat ears cultured in vitro. Xie, ZJ,Jiang, D,Dai, TB,Jing, Q,Cao, WX. 2004
[3]AtMYB12 regulates flavonoids accumulation and abiotic stress tolerance in transgenic Arabidopsis thaliana. Wang, Feibing,Peng, Rihe,Li, Zhenjun,Yao, Quanhong,Kong, Weili,Wong, Gary,Fu, Lifeng.
[4]OsAREB1, an ABRE-binding protein responding to ABA and glucose, has multiple functions in Arabidopsis. Jin, Xiao-Fen,Xiong, Ai-Sheng,Peng, Ri-He,Liu, Jin-Ge,Gao, Feng,Yao, Quan-Hong,Chen, Jian-Min.
[5]VvMYBA6 in the promotion of anthocyanin biosynthesis and salt tolerance in transgenic Arabidopsis. Sun, Miao,Feng, Xin-Xin,Wang, Liang-Ju,Sun, Miao,Gao, Jian-Jie,Peng, Ri-He,Yao, Quan-Hong.
[6]Isolation and characterization of a harvest-induced promoter of an alfalfa gene, hi7. Zhang, Jian,Yu, Wen-Jin,Bahramnejad, Bahman,Erickson, Larry R.,Xiong, Ai-Sheng,Bahramnejad, Bahman,Yu, Wen-Jin,Erickson, Larry R..
[7]A grape bHLH transcription factor gene, VvbHLH1, increases the accumulation of flavonoids and enhances salt and drought tolerance in transgenic Arabidopsis thaliana. Wang, Feibing,Li, Zhenjun,Peng, Rihe,Yao, Quanhong,Zhu, Hong,Chen, Dahu.
作者其他论文 更多>>
-
Multi-compartment model of brain tissues from T2 relaxometry MRI using gamma distribution
作者:Sudhanya Chatterjee;Olivier Commowick;Onur Afacan;Simon K. Warfield;Christian Barillot
关键词:Lesions;Estimation;Axons;Magnetic resonance imaging;Optimization;Brain modeling;Probability density function
-
Morphological changes in the corpus callosum: A study using joint Riemannian feature spaces
作者:Meena Mani;Anuj Srivastava;Christian Barillot
关键词:Riemannian metrics;shape analysis;DTI;multiple sclerosis
-
Adaptive Multi-modal Particle Filtering for Probabilistic White Matter Tractography
作者:Aymeric Stamm;Olivier Commowick;Patrick Perez;Christian Barillot
关键词:
-
Denoising arterial spin labeling MRI using tissue partial volume
作者:Jan Petr;Jean-Christophe Ferre;Jean-Yves Gauvrit;Christian Barillot
关键词:
-
Improving arterial spin labeling data by temporal filtering
作者:Jan Petr;Jean-Christophe Ferre;Jean-Yves Gauvrit;Christian Barillot
关键词:
-
Multi Channel MRI Segmentation With Graph Cuts Using Spectral Gradient And Multidimensional Gaussian Mixture Model
作者:Jeremy Lecoeur;Jean-Christophe Ferre;D. Louis Collins;Sean Morrissey;Christian Barillot
关键词:MRI;RGB;tissues
-
Restoration of 3D medical images with total variation scheme on wavelet domains (TVW)
作者:Arnaud Ogier;Pierre Hellier;Christian Barillot;SPIE-The International Society for Optical Engineering
关键词:denoising;wavelets;total variation;restoration;ultrasound