Application of improved support vector machine in identification of pulmonary nodule

LI Yang; ZHAO Qing-dong; TIAN Ying

doi:10.3788/OPE.20172513.0215

您当前的位置：

首页 >

文章列表页 >

Application of improved support vector machine in identification of pulmonary nodule

更新时间：2020-08-13

- Application of improved support vector machine in identification of pulmonary nodule
- Optics and Precision Engineering Vol. 25, Issue 10s, Pages: 215-220(2017)
- 作者机构：
  
  1. 东北师范大学数学与统计学院, 吉林长春 130024
  2. 长春市妇产医院,吉林长春,130042
  3. 长春工业大学计算机科学与工程学院,吉林长春,130012
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172513.0215
  CLC： TP391.4
- Received：01 June 2017，
  
  Revised：22 June 2017，
  
  Published：25 November 2017
- 稿件说明：
移动端阅览
李阳, 赵庆东, 田颖. 改进的支持向量机算法在肺结节识别中的应用[J]. 光学精密工程, 2017,25(10s): 215-220

LI Yang, ZHAO Qing-dong, TIAN Ying. Application of improved support vector machine in identification of pulmonary nodule[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 215-220
李阳, 赵庆东, 田颖. 改进的支持向量机算法在肺结节识别中的应用[J]. 光学精密工程, 2017,25(10s): 215-220 DOI： 10.3788/OPE.20172513.0215.

LI Yang, ZHAO Qing-dong, TIAN Ying. Application of improved support vector machine in identification of pulmonary nodule[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 215-220 DOI： 10.3788/OPE.20172513.0215.

摘要

为了解决在肺结节识别过程中数据集正负样本分布不均衡以及参数寻优时间过长的问题，提出了一种PSO-CSVM算法。首先从肺CT中提取肺结节ROI图像，然后对其提取13维特征，最后利用提出的基于PSO的代价敏感型SVM算法进行识别。测试结果显示识别准确率达到91.11%，敏感度达到85.71%，特异度达到93.55%，参数寻优时间为54.37 s。将提出的算法与遗传寻优算法及网格寻优搜索算法相比较来验证算法的有效性，实验结果表明，PSO-CSVM算法运行时间较短，准确度和敏感度最优，而且具有运行时间短，识别准确率和检出率高的特点，能够满足医学影像学对肺结节的识别要求。

Abstract

In order to solve the problems of the unbalanced distribution of positive and negative samplesin data set in pulmonary nodule identification and overtime parameter optimization

a PSO-CSVM algorithm was proposed. ROI image of pulmonary nodule was extracted from the lung CT and then 13-dimensional characteristics was extracted from it. Finally

the proposed PSO-based cost-sensitive type SVM algorithm was used for identification. In the testing the accuracy rate of the identification reached 91.11% and the sensitivity reached 85.71%

specificity reached 93.55%

and the time of parameter optimization was 54.37 s. In order to further verify the effectiveness of the algorithm

the proposed algorithm was compared with the genetic optimizing algorithm and grid optimizing searching algorithm. The experimental result shows that the run-time of PSO-CSVM is shorter and the accuracy and sensitivity is optimal.It features short run-time

high accuracy rate of identification and detection rate and can meet the requirements of medical imaging for the identification of pulmonary nodule.

关键词

Keywords

references

CASCIO D, MAGRO R, FAUCI F, et al.. Automatic detection of lung nodules in CT datasets based on stable 3D mass-spring models.[J]. Computers in Biology & Medicine, 2012, 42(11):1098-109.

SHEN W, ZHOU M, YANG F, et al.. Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification[J]. Pattern Recognition, 2016, 61:663-673.

FROZ B R, FILHO A O D C, SILVA A C, et al.. Lung nodule classification using artificial crawlers, directional texture and support vector machine[J]. Expert Systems with Applications, 2017, 69:176-188.

CAO P, LIU X, YANG J, et al.. A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules[J]. Pattern Recognition, 2017, 64(C):327-346.

李勇,苗壮,王青竹,等. 纹理引导的稀疏张量表示及在肺CT图像中的应用[J]. 光学精密工程, 2015, 23(2):550-556. LI Y, MIAO ZH, WANG Q ZH, et al.. Sparse tensor representation of texture guidance and its application in lung CT images[J]. Opt. Precision Eng.,2015, 23(2):550-556.(in Chinese)

SUN S, LI W, KANG Y. Lung nodule detection based on GA and SVM//International Conference on Biomedical Engineering and Informatics, IEEE, 2016:96-100.

LI Y, WEN D, WANG K, et al.. Mixed Kernel Function SVM for Pulmonary Nodule Recognition. Image Analysis and Processing-ICIAP 2013. Springer Berlin Heidelberg, 2013:449-458.

EBERHART R, KENNEDY J. A new optimizer using particle swarm theory//International Symposium on MICRO Machine and Human Science, IEEE, 1995:39-43.

李姜, 郭立红. 基于改进支持向量机的目标威胁估计[J]. 光学精密工程, 2014, 22(5):1354-1362. LI J, GUO L H.Target threat estimation based on improved support vector machine[J]. Opt. Precision Eng.,2014, 22(5):1354-1362.(in Chinese)

ZHANG J, CAO M Y, GAI W, et al.. Performance comparison of ESVM and CSVM for classifying the Lung Nodules on CT Scans//Seventh International Conference on Image and Graphics, IEEE, 2013:409-413.

Views

267

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Elite particle swarm optimization algorithm and its application in robot path planning

Localization and profile error evaluation of freeform surface based on CAD model-directed measurement

Related Author

YAN Xue-song1

HU Cheng-yu1

YAO Hong1

WU Qing-hua2

WANG Dong-xia

WEN Xiu-lan

ZHAO Yi-bing

Related Institution

School of Computer Science, China University of Geosciences

School of Computer Science and Engineering, Wuhan Institute of Technology

Automation Department, Nanjing Institute of Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰