基于图像模式的肺结节识别

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 463-467.

基于图像模式的肺结节识别

李阳^1,2, 史东承², 王珂¹, 王燕³, 魏艳芳⁴

1. 吉林大学通信工程学院,长春 130012;
2. 长春工业大学计算机科学与工程学院长春 130012;
3. 空军航空大学航空信息对抗系,长春130022;
4. 吉视传媒股份有限公司长春分公司,长春130000

收稿日期:2012-06-05 发布日期:2013-06-01
通讯作者: 王珂(1955-),男,教授.研究方向:图像处理、模式识别、无线通信及导航等.E-mail:wangke@jlu.edu.cn E-mail:wangke@jlu.edu.cn
作者简介:李阳(1979-),女,讲师,博士研究生.研究方向:医学图像处理、模式识别、信号与信息处理等.E-mail:liyangyaya1979@sina.com
基金资助:
吉林省科技发展计划青年科研基金项目(201201129);长春工业大学理工科基金项目(2011LG04).

Lung nodule recognition based on image pattern

LI Yang^1,2, SHI Dong-cheng², WANG Ke¹, WANG Yan³, WEI Yan-fang⁴

1. College of Communication Engineering, Jilin University, Changchun 130012, China;
2. College of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China;
3. Department of Aerial Information Rivalry, Aviation University of Air Force, Changchun 130022, China;
4. Changchun Branch, Jishi Media Company Limited, Changchun 130000, China

Received:2012-06-05 Published:2013-06-01

摘要/Abstract

摘要：

将矩阵化最小二乘支持向量机算法应用于肺结节识别的研究,将图像矩阵作为输入,可解决空间信息丢失问题。实验选用20套CT影像,用提取出的20个结节与20个假阳测试分类器性能。正则化参数用网格搜索方法进行交叉验证,从而得到线性核下的最优参数。实验结果验证了此种方法在肺结节检测中应用的可行性及有效性。

关键词: 信息处理技术, 肺结节识别, 最小二乘支持向量机, 矩阵模式, 交叉验证

Abstract:

To solve the spatial information loss problem,the least squares support vector machine based on matrix patterns was applied to the recognition of lung nodule using image matrix as input.20 sets of CT images were used in the experiments.The 20 true nodules and 20 false ones extracted were used to test the function of classifier.The cross validation of the regularization parameters was obtained by the grid searching method to get the optimal parameters of the linear kernel function.The experimental results show that this method is feasible and effective for the detection of lung nodule.

Key words: information processing technology, lung nodule recognition, least squares support vector machine (LS-SVM), matrix patterns, cross-validation

中图分类号:

TP391.4

李阳, 史东承, 王珂, 王燕, 魏艳芳. 基于图像模式的肺结节识别[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 463-467.

LI Yang, SHI Dong-cheng, WANG Ke, WANG Yan, WEI Yan-fang. Lung nodule recognition based on image pattern[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 463-467.

参考文献

[1] Greenlee R T,Murray T,Bolden S.Wingo PA:Cancer statistics,2000[J].CA Cancer J Clin 2000,50:7-33.

[2] Kunio D.Computer-aided diagnosis in medical imaging:historical review,current status and future potential [J].Computerized Medical Imaging and Graphics,2007,31:198-211.

[3] Giger M L,Chan H P,Boone J.Anniversary paper:history and status of CAD and quantitative image analysis:the role of medical physics and AAPM [J].Medical Physics,2008,35(12):5799-5820.

[4] Dehmeshki J,Amin H,Valdivieso M,et al.Segmentation of pulmonary nodules in thoracic CT scans:a region growing approach [J].IEEE Trans Med Imaging,2008,27(4):467-480.

[5] Liu L,Liu W Y.A method of pulmonary nodules detection with support vector [C]//Proceedings of the 2008 Eighth International Conference on Intel-ligent Systems Design and Applications Medical Physics,Kaohsiung,Taiwan:ISDA,2008:32-35.

[6] 孙斌,周云龙.基于支持向量机和小波包能量特征的气液两相流流型识别方法[J].中国电机工程学报,2005,25(17):93-99. Sun Bin,Zhou Yun-long.Identification method of gas-liquid two-phase flow regime based on support vector machine and wavelet packet energe feature[J].Proceedings of the CSEE,2005,25(17):93-99.

[7] 贺秋伟,王龙山,刘庆民,等.基于支持向量机回归的小尺寸零件精密测量[J].光学·精密工程,2007,15(4):557-563. He Qiu-wei,Wang Long-shan,Liu Qing-min,et al.Precision measurement for small size parts based on support vector regression[J].Opt Precision Eng,2007,15(4):557-563.

[8] Suzuki K,Armato S G III,Li F,et al.Massive training artificial neural network(MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography[J].MedPhys (S2222-2233),2003,30(6):1602-1617.

[9] 孙申申,任会之,康雁,等.基于遗传算法和支持向量机的肺结节检测[J].系统仿真学报,2011,23(3):497-501. Sun Shen-shen,Ren Hui-zhi,Kang Yan,et al. Lung nodule detection by GA and SVM[J].Journal of System Simulation,2011,23(3):497-501.

[10] 刘露,刘宛予,楚春雨,等.胸部CT图像中孤立性结节良恶性快速分类[J].光学精密工程[J].2009,17(8):2060-2067. Liu Lu,Liu Wan-yu,Chu Chun-yu,et al.Fast classification of benign and malignant solitary pulmonary nodules in CT image[J].Optics and Precision Engineering,2009,17(8):2060-2067.

[11] Wang Z,Chen S C.New least squares support vector machines based on matrix patterns[J].Neural Processing Letters,2007,26:41-56.

[12] Beymer D,Poggio T.Image representations for visual learning [J].Science,1996,272:1905-1909.

[13] Chen S C,Zhu Y L,Zhang D Q,et al.Feature extraction approaches based on matrix pattern:MatPCA and MatFLDA[J].Pattern Recog Lett,2005,26:1157-1167.

[14] Wang H,Ahuja N.Rank-R approximation of tensors:using image-as-matrix representation[C]//IEEE Conference on Computer Vision and Pattern Recognition,2005.

相关文章 15

[1]	苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[3]	黄勇,杨德运,乔赛,慕振国. 高分辨合成孔径雷达图像的耦合传统恒虚警目标检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1904-1909.
[4]	李居朋,张祖成,李墨羽,缪德芳. 基于Kalman滤波的电容屏触控轨迹平滑算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1910-1916.
[5]	应欢,刘松华,唐博文,韩丽芳,周亮. 基于自适应释放策略的低开销确定性重放方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1917-1924.
[6]	陆智俊,钟超,吴敬玉. 星载合成孔径雷达图像小特征的准确分割方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1925-1930.
[7]	刘仲民,王阳,李战明,胡文瑾. 基于简单线性迭代聚类和快速最近邻区域合并的图像分割算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1931-1937.
[8]	单泽彪,刘小松,史红伟,王春阳,石要武. 动态压缩感知波达方向跟踪算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1938-1944.
[9]	隗海林, 包翠竹, 李洪雪, 李明达. 基于最小二乘支持向量机的怠速时间预测[J]. 吉林大学学报(工学版), 2018, 48(5): 1360-1365.
[10]	姚海洋, 王海燕, 张之琛, 申晓红. 双Duffing振子逆向联合信号检测模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1282-1290.
[11]	全薇, 郝晓明, 孙雅东, 柏葆华, 王禹亭. 基于实际眼结构的个性化投影式头盔物镜研制[J]. 吉林大学学报(工学版), 2018, 48(4): 1291-1297.
[12]	陈绵书, 苏越, 桑爱军, 李培鹏. 基于空间矢量模型的图像分类方法[J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[13]	陈涛, 崔岳寒, 郭立民. 适用于单快拍的多重信号分类改进算法[J]. 吉林大学学报(工学版), 2018, 48(3): 952-956.
[14]	孟广伟, 李荣佳, 王欣, 周立明, 顾帅. 压电双材料界面裂纹的强度因子分析[J]. 吉林大学学报(工学版), 2018, 48(2): 500-506.
[15]	林金花, 王延杰, 孙宏海. 改进的自适应特征细分方法及其对Catmull-Clark曲面的实时绘制[J]. 吉林大学学报(工学版), 2018, 48(2): 625-632.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed