基于弱监督ECOC算法的肺结节辅助检测

被引:3
作者
苏志远 [1 ,2 ]
刘慧 [1 ,2 ]
尹义龙 [1 ,3 ]
机构
[1] 山东财经大学计算机科学与技术学院
[2] 山东省数字媒体技术重点实验室
[3] 山东大学计算机科学与技术学院
关键词
肺结节; 分类识别; 弱监督; 纠错输出编码; 肺部图像数据库联盟;
D O I
10.16337/j.1004-9037.2015.05.010
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
肺结节的准确分类与识别是计算机辅助诊断系统在肺癌诊断领域应用的关键,同时也面临巨大的挑战。该技术不仅在特征表示、样本标记等方面存在发展的瓶颈,而且目前缺少准确、有效的分类识别算法。本文提出了一种结合弱监督纠错输出编码(Error-correcting output codes,ECOC)算法和肺结节形状特征表达的肺结节多分类算法。为了提高分类识别的准确率,本文对肺结节的形状特征进行了详细的分析,并提出了一系列准确的形状特征描述向量。在分类识别阶段,算法训练学习了利用专家对肺结节标记信息标记的少量样本,并生成二类分类器,获得编码矩阵。最后,通过计算测试样本编码和编码矩阵每一行的汉明距离,确定样本所属类别。实验结果表明,本文方法能够获得更加准确的分类结果。
引用
收藏
页码:1003 / 1010
页数:8
相关论文
共 16 条
  • [1] Learning from partial labels. Cour, Timothee,Sapp, Benjamin,Taskar, Ben. Journal of Machine Learning Research . 2011
  • [2] Research on a pulmonary nodule segmentation method combining fast self-adaptive FCM and classification. Liu H,Zhang C M,Su Z Y,et al. Computational and Mathematical Methods in Medicine . 2015
  • [3] Disambiguation-free partial label learning. Zhang M L. Proceeding of the 14th SIAM International Conference on Data Mining (SDM14) . 2014
  • [4] Learning error-correcting output codes form data. Alpaydin E,Mayoraz E. Proceeding of the 9th Internet Conference on Artificial Neural Networks . 1999
  • [5] Image classification using SVMs One-against-one vs one-against-all. Anthony G,Gregg H,Tshilidzi M. Proceeding of the 28th Asian Conference on Remote Sensing . 2007
  • [6] Facial expression recognitionusing graph-based features and artificial neural networks. Tanchotsrinon C,Phimoltares S,Maneeroj S. Imaging Systems andTechniques (IST),2011IEEE International Conference on . 2011
  • [7] The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. Armato Samuel G,McLennan Geoffrey,Hawkins Drive,Bidaut Luc,McNitt-Gray Michael F,Meyer Charles R,Reeves Anthony P,Zhao Binsheng,Aberle Denise R,Henschke Claudia I,Hoffman Eric A,Kazerooni Ella A,MacMahon Heber,Van Beeke Edwin J R,Yankelevitz. Medical Physics . 2011
  • [8] Local Adaptive SVM for Object Recognition. Zaidi N.A,Squire. M. Digital Image Computing: Techniques and Applications (DICTA), International Conference on . 2010
  • [9] 一种基于多视图数据的半监督特征选择和聚类算法
    汪荆琪
    徐林莉
    [J]. 数据采集与处理, 2015, 30 (01) : 106 - 116
  • [10] Cancer statistics, 2014[J] . Rebecca Siegel,Jiemin Ma,Zhaohui Zou,Ahmedin Jemal. &nbspCA A Cancer Journal for Clinicians . 2014 (1)