高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于CT征象量化分析的肺结节恶性度分级

陈皓 段红柏 郭紫园 强永乾

陈皓, 段红柏, 郭紫园, 强永乾. 基于CT征象量化分析的肺结节恶性度分级[J]. 电子与信息学报. doi: 10.11999/JEIT200167
引用本文: 陈皓, 段红柏, 郭紫园, 强永乾. 基于CT征象量化分析的肺结节恶性度分级[J]. 电子与信息学报. doi: 10.11999/JEIT200167
Hao CHEN, Hongbai DUAN, Ziyuan GUO, Yongqian QIANG. Malignancy Grading of Lung Nodules Based on CT Signs Quantization Analysis[J]. Journal of Electronics and Information Technology. doi: 10.11999/JEIT200167
Citation: Hao CHEN, Hongbai DUAN, Ziyuan GUO, Yongqian QIANG. Malignancy Grading of Lung Nodules Based on CT Signs Quantization Analysis[J]. Journal of Electronics and Information Technology. doi: 10.11999/JEIT200167

基于CT征象量化分析的肺结节恶性度分级

doi: 10.11999/JEIT200167
基金项目: 国家自然科学基金(61876138, 61203311),陕西省自然科学基金 (2019JM-365),陕西省教育厅自然科学专项(17JK0701),陕西省网络数据分析与智能处理重点实验室开放课题基金(XUPT-KLND(201804)),西安邮电大学创新基金(CXJJLI2018017)
详细信息
    作者简介:

    陈皓:男,1978年生,博士,副教授,硕士生导师,主要研究方向为医疗大数据

    段红柏:男,1993年生,硕士生,研究方向为数据挖掘和模式识别

    郭紫园:女,1996年生,硕士生,研究方向为数据挖掘和进化计算

    强永乾:男,1965年生,博士,副教授,硕士生导师,研究方向为医学影像学

    通讯作者:

    陈皓 chenhao@xupt.edu.cn

  • 中图分类号: TN911.73; TP391.41

Malignancy Grading of Lung Nodules Based on CT Signs Quantization Analysis

Funds: The National Natural Science Foundation of China (61876138, 61203311), The Natural Science Basic Research Program of Shaanxi Province (2019JM-365), The Scientific Research Program Funded by Shaanxi Provincial Education Department (17JK0701), The Science Foundation of the Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing (XUPT-KLND (201804)), The Innovation Funds of Xi'an University of Posts and Telecommunications (CXJJLI2018017)
  • 摘要: 为了提高肺结节恶性度分级的计算精度及可解释性,该文提出一种基于CT征象量化分析的肺结节恶性度分级方法。首先,融合影像组学特征和通过卷积神经网络提取的高阶特征构造分析CT征象所需的特征集; 接着,在混合特征集的基础上利用进化搜索机制优化集成学习分类器,实现对7种肺结节征象的识别和量化打分; 最后,将7种CT征象的量化打分输入到一个利用差分进化算法优化产生的多分类器,实现肺结节恶性度的分级计算。在实验研究中使用LIDC-IDRI数据集中的2000个肺结节样本进行进化集成学习器和恶性度分级器的训练和测试。实验结果显示对7种CT征象的识别准确率可达0.9642以上,肺结节恶性度分级的准确率为0.8618,精确率为0.8678,召回率为0.8617, F1指标为0.8627。与多个典型算法的比较显示,该文方法不但具有较高的准确率,而且可对相关CT征象进行量化分析,使得对恶性度的分级结果更具可解释性。
  • 图  1  肺结节恶性度分级流程

    图  2  多特征融合流程

    图  3  基于进化搜索构造集成学习器的流程

    图  4  进化集成学习器的优化过程

    图  5  不同特征集合的聚类结果可视化对比

    表  1  不同征象的有效特征

    阈值特征总数量影像组学特征数CNN特征数
    精细度0.0050692841
    球形度0.003013623113
    边缘0.00351002872
    分叶征0.000920334169
    毛刺征0.0060552322
    纹理征0.0070391227
    钙化征0.0300682048
    下载: 导出CSV

    表  2  恶性度分级和CT征象量化的精度

    指标精细度球形度边缘分叶征毛刺征纹理征钙化征恶性度
    ACC0.96680.97640.96420.96930.97920.97280.98440.8618
    Pre0.96480.97720.96590.95220.96950.97330.96830.8678
    Rec0.96510.97850.93460.94970.97080.97360.96740.8619
    F10.96490.97780.94990.95090.97010.97350.96780.8627
    下载: 导出CSV

    表  3  恶性度分级模型的权重系数

    恶性度等级精细度球形度边缘分叶征毛刺征纹理征钙化征
    1–0.0703–0.85600.38350.29350.27510.0848–0.7668
    2–0.04520.30540.5043–0.00620.0069–0.6435–0.4618
    3–0.4187–0.35070.41510.33370.17592–0.03670.5758
    40.1984–0.19480.42210.03690.32170.01130.2751
    50.8548–0.47590.2756–0.29900.4641–0.11760.5337
    下载: 导出CSV

    表  4  不同集成学习器的量化计算结果对比

    对比分类器指标精细度球形度边缘分叶征毛刺征纹理征钙化征
    ETAcc0.96380.95260.94220.96030.93720.95720.9512
    Pre0.96370.95580.95060.96160.93720.95740.9507
    Rec0.96460.95320.89940.95900.93740.95720.9517
    F10.96380.95410.91970.95980.93650.95730.9511
    树个数112100881081527676
    XGBoostAcc0.96210.94280.94520.95600.92750.93120.9498
    Pre0.96190.94420.95040.95710.92760.93110.9489
    Rec0.96250.94370.92660.95660.92890.93110.9506
    F10.96210.94380.93770.95660.92820.93110.9496
    树个数18818019218817611080
    RFAcc0.95850.94110.94220.94910.94900.96370.9471
    Pre0.95830.94490.93990.94970.94920.96420.9466
    Rec0.95930.94220.91660.94880.95020.96370.9477
    F10.95860.94320。92700。94910。94880。96390。9470
    树个数12817218813612812872
    本文方法Acc0.96680.97640.96420.96930.97920.97280.9844
    Pre0.96480.97720.96590.95220.96950.97330.9683
    Rec0.96510.97850.93460.96970.97080.97360.9674
    F10.96490.97780.94990.95090.97010.97350.9678
    树个数77677854706023
    下载: 导出CSV

    表  5  相关文献的量化结果对比

    精细度球形度边缘分叶征毛刺征纹理征钙化恶性度
    文献[11]0.7190.52220.725//0.8340.9080.842
    文献[22]0.71630.73920.73320.72480.74220.76770.73900.8194
    文献[23]0.74310.76220.70130.80010.78280.9002/0.7556
    文献[24]0.89330.89330.89330.89330.89330.89330.89330.8933
    本文方法0.96680.97640.96420.96930.97920.97280.98440.8618
    下载: 导出CSV

    表  6  不同特征集合的聚类结果对比

    特征集均一性v-measure互信息
    影像组学特征0.32610.32330.3179
    CNN特征0.443420.42820.4118
    融合特征0.60850.59340.5771
    下载: 导出CSV
  • [1] MCWILLIAMS A, TAMMEMAGI M C, MAYO J R, et al. Probability of cancer in pulmonary nodules detected on first screening CT[J]. New England Journal of Medicine, 2013, 369(10): 910–919. doi:  10.1056/NEJMoa1214726
    [2] NAIDICH D P, BANKIER A A, MACMAHON H, et al. Recommendations for the management of subsolid pulmonary nodules detected at CT: A statement from the fleischner society[J]. Radiology, 2013, 266(1): 304–317. doi:  10.1148/radiol.12120628
    [3] GOULD M K, DONINGTON J, LYNCH W R, et al. Evaluation of individuals with pulmonary nodules: When is it lung cancer?: Diagnosis and management of lung cancer, 3rd ed: American college of chest physicians evidence-based clinical practice guidelines[J]. Chest, 2013, 143(5S): e93S–e120S. doi:  10.1378/chest.12-2351
    [4] TRAVIS W D, BRAMBILLA E, NOGUCHI M, et al. International association for the study of lung cancer/American thoracic society/European respiratory society: International multidisciplinary classification of lung adenocarcinoma[J]. Proceedings of the American Thoracic Society, 2011, 8(5): 381–385. doi:  10.1513/pats.201107-042ST
    [5] RODRIGUES M B, DA NÓBREGA R V M, ALVES S S A, et al. Health of things algorithms for malignancy level classification of lung nodules[J]. IEEE Access, 2018, 6: 18592–18601. doi:  10.1109/ACCESS.2018.2817614
    [6] DA NÓBREGA R V M, PEIXOTO S A, DA SILVA S S P, et al. Lung nodule classification via deep transfer learning in CT lung images[C]. Proceedings of the IEEE 31st International Symposium on Computer-Based Medical Systems, Karlstad, Sweden, 2018: 244–249.
    [7] ZUO Wangxia, ZHOU Fuqiang, LI Zuoxin, et al. Multi-resolution CNN and knowledge transfer for candidate classification in lung nodule detection[J]. IEEE Access, 2019, 7: 32510–32521. doi:  10.1109/ACCESS.2019.2903587
    [8] SHEN Shiwen, HAN S X, ABERLE D R, et al. An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification[J]. Expert Systems with Applications, 2019, 128: 84–95. doi:  10.1016/j.eswa.2019.01.048
    [9] WANG Huafeng, ZHAO Tingting, LI Lihong, et al. A hybrid CNN feature model for pulmonary nodule malignancy risk differentiation[J]. Journal of X-Ray Science and Technology, 2018, 26(2): 171–187. doi:  10.3233/XST-17302
    [10] 褚征, 于炯. 基于随机森林的流处理检查点性能预测[J]. 电子与信息学报, 2020, 42(6): 1452–1459. doi:  10.11999/JEIT190552

    CHU Zheng and YU Jiong. Performance prediction based on random forest for the stream processing checkpoint[J]. Journal of Electronics &Information Technology, 2020, 42(6): 1452–1459. doi:  10.11999/JEIT190552
    [11] NISHIO M, NISHIZAWA M, SUGIYAMA O, et al. Computer-aided diagnosis of lung nodule using gradient tree boosting and bayesian optimization[J]. PLoS One, 2018, 13(4): e0195875. doi:  10.1371/journal.pone.0195875
    [12] 吴艇帆, 张仁寿. 机器学习在肺内恶性磨玻璃密度结节的应用研究[J]. 广州大学学报: 自然科学版, 2018, 17(3): 33–39.

    WU Tingfan and ZHANG Renshou. Research on the application of machine learning in the malignant grinding glass density nodules of lung[J]. Journal of Guangzhou University:Natural Science Edition, 2018, 17(3): 33–39.
    [13] FERREIRA JR J R, OLIVEIRA M C, and DE AZEVEDO-MARQUES P M. Characterization of pulmonary nodules based on features of margin sharpness and texture[J]. Journal of Digital Imaging, 2018, 31(4): 451–463. doi:  10.1007/s10278-017-0029-8
    [14] WU Wenhao, HU Huihui, GONG Jing, et al. Malignant-benign classification of pulmonary nodules based on random forest aided by clustering analysis[J]. Physics in Medicine & Biology, 2019, 64(3): 035017. doi:  10.1088/1361-6560/aafab0
    [15] SHAUKAT F, RAJA G, ASHRAF R, et al. Artificial neural network based classification of lung nodules in CT images using intensity, shape and texture features[J]. Journal of Ambient Intelligence and Humanized Computing, 2019, 10(10): 4135–4159. doi:  10.1007/s12652-019-01173-w
    [16] 李双双, 侯震, 刘娟, 等. 影像组学分析与建模工具综述[J]. 中国医学物理学杂志, 2018, 35(9): 1043–1049. doi:  10.3969/j.issn.1005-202X.2018.09.010

    LI Shuangshuang, HOU Zhen, LIU Juan, et al. Review of radiomic analysis and modeling tools[J]. Chinese Journal of Medical Physics, 2018, 35(9): 1043–1049. doi:  10.3969/j.issn.1005-202X.2018.09.010
    [17] SHI Zhenghao, HAO Huan, ZHAO Minghua, et al. A deep CNN based transfer learning method for false positive reduction[J]. Multimedia Tools and Applications, 2019, 78(1): 1017–1033. doi:  10.1007/s11042-018-6082-6
    [18] 刘家辰, 苗启广, 曹莹, 等. 基于混合多样性生成与修剪的集成单类分类算法[J]. 电子与信息学报, 2015, 37(2): 386–393. doi:  10.11999/JEIT140161

    LIU Jiachen, MIAO Qiguang, CAO Ying, et al. Ensemble one-class classifiers based on hybrid diversity generation and pruning[J]. Journal of Electronics &Information Technology, 2015, 37(2): 386–393. doi:  10.11999/JEIT140161
    [19] ELYAN E and GABER M M. A fine-grained random forests using class decomposition: An application to medical diagnosis[J]. Neural Computing and Applications, 2016, 27(8): 2279–2288. doi:  10.1007/s00521-015-2064-z
    [20] MIAO Fen, CAI Yunpeng, ZHANG Yuxiao, et al. Predictive modeling of hospital mortality for patients with heart failure by using an improved random survival forest[J]. IEEE Access, 2018, 6: 7244–7253. doi:  10.1109/ACCESS.2018.2789898
    [21] PAUL A, MUKHERJEE D P, DAS P, et al. Improved random forest for classification[J]. IEEE Transactions on Image Processing, 2018, 27(8): 4012–4024. doi:  10.1109/tip.2018.2834830
    [22] WANG Qingfeng, CHENG Jiezhi, LIU Zhiqin, et al. Multi-order transfer learning for pathologic diagnosis of pulmonary nodule malignancy[C]. Proceedings of 2018 IEEE International Conference on Bioinformatics and Biomedicine, Madrid, Spain, 2018: 2813–2815.
    [23] YANG Jing, LI Na, FANG Shuai, et al. Semantic features prediction for pulmonary nodule diagnosis based on online streaming feature selection[J]. IEEE Access, 2019, 7: 61121–61135. doi:  10.1109/ACCESS.2019.2903682
    [24] WU Botong, ZHOU Zhen, WANG Jianwei, et al. Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction[C]. Proceedings of the IEEE 15th International Symposium on Biomedical Imaging, Washington, USA, 2018: 1109–1113.
  • [1] 张颖君, 陈恺, 鲍旭华.  一种基于程序执行时间量化分析的软件水印方法, 电子与信息学报. 2020, 42(8): 1811-1819. doi: 10.11999/JEIT190850
    [2] 夏平凡, 倪志伟, 朱旭辉, 倪丽萍.  基于双错测度的极限学习机选择性集成方法, 电子与信息学报. 2020, 42(0): 1-9. doi: 10.11999/JEIT190617
    [3] 张雄涛, 蒋云良, 潘兴广, 胡文军, 王士同.  基于迭代模糊聚类算法与K近邻和数据字典的集成TSK模糊分类器, 电子与信息学报. 2020, 42(3): 746-754. doi: 10.11999/JEIT190214
    [4] 谢涛, 吴恩斯.  一种鲁棒的基于集成学习的核相关红外目标跟踪算法, 电子与信息学报. 2018, 40(3): 602-609. doi: 10.11999/JEIT170527
    [5] 伊鹏, 王鹏, 申涓, 张校辉, 兰巨龙.  基于活跃度的分级映射解析系统, 电子与信息学报. 2017, 39(4): 832-839. doi: 10.11999/JEIT160526
    [6] 胡颖, 胡长军, 傅树深, 黄建一.  流行度演化分析与预测综述, 电子与信息学报. 2017, 39(4): 805-816. doi: 10.11999/JEIT160743
    [7] 徐涛, 郭威, 吕宗磊.  基于快速极限学习机和差分进化的机场噪声预测模型, 电子与信息学报. 2016, 38(6): 1512-1518. doi: 10.11999/JEIT150986
    [8] 徐涛, 杨奇川, 吕宗磊.  一种基于动态集成学习的机场噪声预测模型, 电子与信息学报. 2014, 36(7): 1631-1636. doi: 10.3724/SP.J.1146.2013.01410
    [9] 王丽艳, 韦志辉.  低剂量CT的线性Bregman迭代重建算法, 电子与信息学报. 2013, 35(10): 2418-2424. doi: 10.3724/SP.J.1146.2012.01650
    [10] 宋相法, 焦李成.  基于稀疏编码和集成学习的多示例多标记图像分类方法, 电子与信息学报. 2013, 35(3): 622-626. doi: 10.3724/SP.J.1146.2012.01218
    [11] 高洪博, 李清宝, 王炜, 谢晓东, 朱瑜.  基于抽象解释的二进制代码变量区间分析, 电子与信息学报. 2013, 35(8): 1927-1932. doi: 10.3724/SP.J.1146.2012.01341
    [12] 黄杰文, 祁海明, 李杨, 禹卫东.  DBF-SAR系统1 bit量化的可行性分析, 电子与信息学报. 2011, 33(5): 1107-1113. doi: 10.3724/SP.J.1146.2010.00928
    [13] 曾高荣, 裘正定, 章春娥.  失真补偿量化索引调制水印的性能分析, 电子与信息学报. 2010, 32(1): 86-91. doi: 10.3724/SP.J.1146.2008.01774
    [14] 徐丰, 金亚秋.  双站SAR图像的极化分析, 电子与信息学报. 2009, 31(1): 182-187. doi: 10.3724/SP.J.1146.2007.01104
    [15] 林雪纲, 许榕生, 熊华, 朱淼良.  一种信息系统生存性的量化分析框架, 电子与信息学报. 2006, 28(9): 1721-1726.
    [16] 方敏, 王宝树.  基于AdaBoost的改进模糊分类规则集成学习, 电子与信息学报. 2005, 27(5): 835-837.
    [17] 姬光荣, 王国宇, 谭锐, 冯天瑾, 陈霞.  尺度空间检测边缘特征的进化分析, 电子与信息学报. 2000, 22(2): 218-225.
    [18] 戚颂新, 杨铨让.  高速集成传输线不连续性的全波分析, 电子与信息学报. 1995, 17(4): 378-384.
    [19] 郝跃.  双极模拟集成电路的参数统计性分析, 电子与信息学报. 1991, 13(1): 78-82.
    [20] 刘政凯.  一种新的CT重建法, 电子与信息学报. 1989, 11(5): 532-535.
  • 加载中
  • 图(5) / 表ll (6)
    计量
    • 文章访问数:  10
    • HTML全文浏览量:  2
    • PDF下载量:  2
    • 被引次数: 0
    出版历程
    • 收稿日期:  2020-03-13
    • 修回日期:  2020-09-25
    • 网络出版日期:  2020-10-16

    目录

      /

      返回文章
      返回

      官方微信,欢迎关注