[1]徐亚楠,赵伟,李铭,等. 基于支持向量机的肺CT图像三维磨玻璃结节的提取和识别[J].中国医学物理学杂志,2019,36(4):425-430.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.011]
　XU Yanan,ZHAO Wei,LI Ming,et al.Support vector machine-based algorithm for the extraction and recognition of ground glass nodules in lung CT image[J].Chinese Journal of Medical Physics,2019,36(4):425-430.[doi:DOI:10.3969/j.issn.1005-202X.2019.04.011]
点击复制

 基于支持向量机的肺CT图像三维磨玻璃结节的提取和识别()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
36卷
期数:
2019年第4期
页码:
425-430
栏目:
医学影像物理
出版日期:
2019-04-25

文章信息/Info

Title:
Support vector machine-based algorithm for the extraction and recognition of ground glass nodules in lung CT image
文章编号:
1005-202X（2019）04-0425-06
作者:
 徐亚楠1; 赵伟2; 李铭2; 石宏理1
 1.首都医科大学生物医学工程学院， 北京 100069； 2.复旦大学附属华东医院CT室， 上海 200040
Author(s):
 XU Ya’nan1;  ZHAO Wei2;  LI Ming2;  SHI Hongli1
 1. School of Biomedical Engineering, Capital Medical University, Beijing 100069, China; 2. CT Room, Huadong Hospital Affiliated to Fudan University, Shanghai 200040, China
关键词:
肺; 磨玻璃结节; 支持向量机; CT; 三维图像
Keywords:
 ; Keywords: lung;  ground glass nodule;  support vector machine;  computed tomography;  three-dimensional image
分类号:
R318.13
DOI:
DOI:10.3969/j.issn.1005-202X.2019.04.011
文献标志码:
A
摘要:
 提出一种基于支持向量机的提取和识别肺CT图像三维磨玻璃结节（GGN）的算法。该算法首先根据肺实质三维图像的连通性，分割出肺实质区域，然后在肺实质区域内提取潜在GGN的孤立组织，并用三维形状特征和三维纹理特征建立识别结节的线性模型。依据临床医师标定的图像，通过支持向量机确定该线性模型参数。最后，采用该线性模型识别孤立组织中的结节。本研究采用139例临床医师标定的肺腺癌数据，其中100例作为训练集，39例作为测试集。测试结果表明，该算法可有效识别出肺CT图像的GGN，通过受试者工作特征曲线（ROC），得到ROC曲线下面积的值为0.937 2。
Abstract:
 Abstract: A new approach based on support vector machine is proposed to extract and recognize the ground glass nodules in three-dimensional (3D) lung computed tomography (CT) image. Firstly, the lung parenchyma regions are segmented according to the 3D connectivity of the lung parenchyma. Then the isolated tissues which may be ground glass nodules are extracted from the lung parenchyma region. After the 3D shape features and 3D texture features are calculated, a linear model is established using these features to recognize the ground glass nodules. The coefficients of the model are determined by support vector machine based on the CT images labeled by clinicians. Finally, the linear model is used to recognize ground glass nodules from the isolated tissues. Among the labeled lung CT images of 139 patients in this study, the images of 100 patients were used as training set and the others as test set. The test results show that the proposed approach can effectively recognize the ground glass nodules in lung CT image. The area under receiver operating characteristic curve reaches 0.937 2.

相似文献/References:

[1]苌飞霸,尹军,何庆华,等.病理性肺音信号的分析识别方法[J].中国医学物理学杂志,2016,33(7):739.[doi:10.3969/j.issn.1005-202X.2016.07.020]
　[J].Chinese Journal of Medical Physics,2016,33(4):739.[doi:10.3969/j.issn.1005-202X.2016.07.020]
[2]刘婷婷,刘志强,欧阳水根,等.乳腺癌根治术后调强放射治疗下不同硅胶设置的肺组织剂量评估[J].中国医学物理学杂志,2016,33(11):1121.[doi:10.3969/j.issn.1005-202X.2016.11.008]
　[J].Chinese Journal of Medical Physics,2016,33(4):1121.[doi:10.3969/j.issn.1005-202X.2016.11.008]
[3]王婷婷,张煜. 基于图像自相似性的多尺度稀疏表示肺4D-CT图像超分辨率重建[J].中国医学物理学杂志,2019,36(6):658.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.008]
　WANG Tingting,ZHANG Yu. Lung 4D-CT image super-resolution reconstruction using self-similarity-based multiscale sparse representation[J].Chinese Journal of Medical Physics,2019,36(4):658.[doi:DOI:10.3969/j.issn.1005-202X.2019.06.008]
[4]付俊泽,贾茜,李几雄,等.基于CT数据的肺部影像可视化系统设计[J].中国医学物理学杂志,2024,41(3):340.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.012]
　FU Junze,JIA Qian,LI Jixiong,et al.Design of a lung image visualization system based on CT data[J].Chinese Journal of Medical Physics,2024,41(4):340.[doi:DOI:10.3969/j.issn.1005-202X.2024.03.012]

备注/Memo

备注/Memo:
 【收稿日期】2018-11-19
【基金项目】北京自然科学基金（7142022）
【作者简介】徐亚楠，硕士研究生，研究方向：医学图像处理，E-mail: xyn19940215@126.com；赵伟，博士在读，研究方向：影像数据挖掘，E-mail: zbsasd@163.com
【通信作者】李铭，副主任医师，研究方向：胸部影像诊断和医学人工智能，E-mail: minli77@163.com；石宏理，副教授，研究方向：医学图像处理，E-mail：shl@ccmu.edu.cn
更新日期/Last Update: 2019-04-23