融合Harris角点检测算法的肺实质分割方法
|
摘要
本文主要研究肺部CT图像中胸膜表面以及近胸膜肺结节的分割方法.由于胸膜粘附结点与肺实质周围的灰度值类似,因此通过边界跟踪获得的轮廓很可能会被过度分割.针对这个不足,本文提出了一种基于Graham扫描法和Harris角点检测算法的分割方法.该方法首先运用最大类间方差法将原CT图像转化为二值图像,并初步提取出肺实质部分的轮廓.然后运用凸包与凸缺陷以及角点检测方法对边界进行校正,从而得到完整的模板.最后根据校正后的模板分割出肺实质内部的所有结节候选点.本文对TCIA(The Cancer Imaging Archive)数据库中的263张CT样本进行实验并将实验结果与滚球算法、水平集方法以及边界逼近法得到的实验结果作对比.最后分析对比结果并证明本方法的有效性.
This paper discusses how to segment the juxtapleural nodule and the nodule closed to the pleura. As the nodule which adjoins pleura is the same as the region with pulmonary parenchyma in gray level. The contour gained by the method of tracking contour are likely to be over-segmented. For this,we employed a method based on the Graham scan and harris corner detection algorithm. First,we transformed the original CT image into a binary image by means of the maximum class inter-variance method and extracted the outline of the lung parenchyma. Then we used the Graham scan and harris corner detection algorithm to correct the boundary and got a complete template. Finally,all nodular candidates within the lung parenchyma were identified through the corrected template. In this paper,we chose 263 sample images in The Cancer Imaging Archive( TCIA) to implement the experiment and compared the result with the rolling ball algorithm,level set method and boundary approximation. At last,we analyse the result and prove the effectiveness of the method.
This paper discusses how to segment the juxtapleural nodule and the nodule closed to the pleura. As the nodule which adjoins pleura is the same as the region with pulmonary parenchyma in gray level. The contour gained by the method of tracking contour are likely to be over-segmented. For this,we employed a method based on the Graham scan and harris corner detection algorithm. First,we transformed the original CT image into a binary image by means of the maximum class inter-variance method and extracted the outline of the lung parenchyma. Then we used the Graham scan and harris corner detection algorithm to correct the boundary and got a complete template. Finally,all nodular candidates within the lung parenchyma were identified through the corrected template. In this paper,we chose 263 sample images in The Cancer Imaging Archive( TCIA) to implement the experiment and compared the result with the rolling ball algorithm,level set method and boundary approximation. At last,we analyse the result and prove the effectiveness of the method.
引文
[1]Huang Zhi-ding,Sun Hong.Lung CT image segmentation based on border approximation[J].Chinese Journal of Biomedical Engineering,2016,35(5):513-518.
[2]3Rd A S,Mclennan G,Mcnitt-Gray M F,et al.Lung image database consortium:developing a resource for the medical imaging research community[J].Radiology,2004,232(3):739-748.
[3]Samuel G.Armato III,Maryellen L.Giger,et al.Computerized detection of pulmonary nodules on CT Scans[J].Radio Graphics,1999,19(4):1303-1311.
[4]Pei X,Guo H,Dai J,et al.A novel lung segmentation and boundary correction method[C].International Conference on Biomedical Engineering and Informatics,Tianjin:IEEE,2009:1-4.
[5]Shen S,Bui AAT,Cong J,et al.An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy[J].Computers in Biology and M edicine,2015,57(C):139-149.
[6]Graham R L.An efficient algorithm for determining the convex hull of a finite planar set[J].Information Processing Letter,1972,1(4):132-133.
[7]Jarvis R A.On the identification of the convex hull of a finite set of points in the plane[J].Information Processing Letters,1973,2(1):18-21.
[8]Harris C.A combined corner and edge detector[C].Proc.of Fourth Alvey Vision Conference,1988:147-151.
[9]Chunming L,Chenyang X,Changfeng G,et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
[10]Pu J,Roos JC,Napel S,et al.Adaptive border marching algorithm:automatic lung segmentation on chest CT images[J].Computerized M edical Imaging&Graphics,2008,32(6):452-462.
[11]Zhou S,Cheng Y,Tamura S.Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images[J].Biomedical Signal Processing&Control,2014,13(5):62-70.
[12]Tasci E.Shape and texture based novel features for automated juxtapleural nodule detection in lung CTs[J].Journal of M edical Systems,2015,39(5):1-13.
[13]Keshani M,Azimifar Z,Tajeripour F,et al.Lung nodule segmentation and recognition using SVM classifier and active contour modeling:a complete intelligent system[J].Computers in Biology&M edicine,2013,43(4):287-300.
[14]Sensakovic W F,Starkey A,Armato S G.A general method for the identification and repair of concavities in segmented medical images[C].IEEE Nuclear Science Symposium Conference Record(NSS),Germany,2008:5320-5326.
[1]黄智定,孙红.基于边界逼近的肺实质分割方法[J].中国生物医学工程学报,2016,35(5):513-518.
[2]3Rd A S,Mclennan G,Mcnitt-Gray M F,et al.Lung image database consortium:developing a resource for the medical imaging research community[J].Radiology,2004,232(3):739-748.
[3]Samuel G.Armato III,Maryellen L.Giger,et al.Computerized detection of pulmonary nodules on CT Scans[J].Radio Graphics,1999,19(4):1303-1311.
[4]Pei X,Guo H,Dai J,et al.A novel lung segmentation and boundary correction method[C].International Conference on Biomedical Engineering and Informatics,Tianjin:IEEE,2009:1-4.
[5]Shen S,Bui AAT,Cong J,et al.An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy[J].Computers in Biology and M edicine,2015,57(C):139-149.
[6]Graham R L.An efficient algorithm for determining the convex hull of a finite planar set[J].Information Processing Letter,1972,1(4):132-133.
[7]Jarvis R A.On the identification of the convex hull of a finite set of points in the plane[J].Information Processing Letters,1973,2(1):18-21.
[8]Harris C.A combined corner and edge detector[C].Proc.of Fourth Alvey Vision Conference,1988:147-151.
[9]Chunming L,Chenyang X,Changfeng G,et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
[10]Pu J,Roos JC,Napel S,et al.Adaptive border marching algorithm:automatic lung segmentation on chest CT images[J].Computerized M edical Imaging&Graphics,2008,32(6):452-462.
[11]Zhou S,Cheng Y,Tamura S.Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images[J].Biomedical Signal Processing&Control,2014,13(5):62-70.
[12]Tasci E.Shape and texture based novel features for automated juxtapleural nodule detection in lung CTs[J].Journal of M edical Systems,2015,39(5):1-13.
[13]Keshani M,Azimifar Z,Tajeripour F,et al.Lung nodule segmentation and recognition using SVM classifier and active contour modeling:a complete intelligent system[J].Computers in Biology&M edicine,2013,43(4):287-300.
[14]Sensakovic W F,Starkey A,Armato S G.A general method for the identification and repair of concavities in segmented medical images[C].IEEE Nuclear Science Symposium Conference Record(NSS),Germany,2008:5320-5326.
[1]黄智定,孙红.基于边界逼近的肺实质分割方法[J].中国生物医学工程学报,2016,35(5):513-518.