全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于EM和Mean-shift的肺结节分割

DOI: 10.11834/jig.20091015

Keywords: 肺结节,期望最大,均值漂移,梯度法向方向分布特征

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对结节与血管相连且两者CT值相近造成分割困难的问题,提出了一种基于期望最大(estimationmaximum,EM)的自适应带宽参数选择的方法,并采用均值漂移(Mean-shift)算法解决结节分割。与基于统计分析规则的带宽选择方法和基于最优化的带宽选择方法相比,该方法能直接求得正确带宽参数,且时间复杂度低。应用血管梯度的法向量方向服从正态分布,而结节梯度的法向量方向服从均匀分布,建立血管粘连型结节模型,并用期望最大估计模型参数,根据均匀分布的权重和带宽选择定理确定带宽参数。该方法对仿真数据和CT数据(19个粘连血管性肺结节)进行评估实验,都取得了正确的分割结果。结果表明,该方法对分割粘连血管型结节是有效的。

References

[1]  Kostis W J,Reeves A P,Yankelewitz D F,et al.Three-dimensional segmentation and growth-rote estimation of small pulmonary nodules in helical CT images[J].IEEE Transactions on Medical Imaging,2003,22(10):1259-1274.
[2]  Okada K,Comaniciu D,Krishnan A.Robust anisotropic Gaussian fitting for volumetfie characterization of pulmonary nodules in multislice CT[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25 (2):281-288.
[3]  Li Q,Sons S,Doi K.Selective enhancement filters for nodules,vessels,and airway walls in two-and three-dimensional CT scans[J].Medical Physics,2003,30(8):2040-2051.
[4]  Gady A,Samuel G,Armato I I I,et al.Vessel tree reconstruction in thoracic CT scans with application to nodule detection[J].IEEE Transactions on Medical Imaging,2005,2,4(4):486-499.
[5]  Jun Z,James W M,Fellow,et al.Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentation[J].IEEE Transactions on Image Processing,1994,3 (4):404-420.
[6]  Comaniciu D.An algorithm for data-driven bandwidth selection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(2):281-288.
[7]  Ning X,Narendra A,Ravi B.Automated lung nodule segmentation using dynamic programming and EM based classification[J].SPIE Medical Imaging,2002,4684 (5):666-676.
[8]  Sun Shen-shen,Li Hong,Hou Xin-ran,et al.Automatic segmentationof pulmonary nodules in CT images[A].In:Proceedings of the IEEE International Conference on 1st Bioinformatic and Biomedical Engineering[C],Wuhan,2007:790-793.
[9]  Gady A,Changhua W.Probabilistic modeling based vessel enhancement in thoracic CT scans[A].In:Proceedings of International Conference on Computer Vision and Pattern Recognition[C],San Diego,CA,USA,2005,2:684-689.
[10]  Comaniciu D,Meer P.Mean shift:A robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24 (5):603-619.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133