A new classifier fusion method based on historical and on-line classification reliability for recognizing common CT imaging signs of lung diseases

Common CT imaging signs of lung diseases (CISL) play important roles in the diagnosis of lung diseases. This paper proposes a new method of multiple classifier fusion to recognize the CISLs, which is based on the confusion matrices of the classifiers and the classification confidence values outputted by the classifiers. The confusion matrix reflects the historical reliability of decision-making of a classifier, while the difference between the classification confidence values reflects the on-line reliability of its decision-making. The two factors are merged to determine the weights of the classifiers' classification confidence values. Then the classifiers are fused in a weighted-sum form to make the final decision. We apply the proposed classifier fusion method to combine five types of classifiers for CISL recognition, including support vector machine (SVM), back-propagation neural network (BPNN), Naïve Bayes (NB), k-nearest neighbor (k-NN) and decision tree (DT). In the experiments on lung CT images, our method not only brought stable improvements of recognition performance, compared with single classifiers, but also outperformed two well-known methods of classifier fusion, AdaBoost and Bagging. These results show that the proposed method is effective and promising.

[1]  M Thelen,et al.  Automatic detection and quantification of ground-glass opacities on high-resolution CT using multiple neural networks: comparison with a density mask. , 2000, AJR. American journal of roentgenology.

[2]  Vasileios Megalooikonomou,et al.  Classification of texture patterns in CT lung imaging , 2011, Medical Imaging.

[3]  Mandyam D. Srinath,et al.  Multichannel fusion models for the parametric classification of differential brain activity , 2005, IEEE Transactions on Biomedical Engineering.

[4]  Ke Wang,et al.  3D Matrix Pattern Based Support Vector Machines for Identifying Pulmonary Cancer in CT Scanned Images , 2010, Journal of Medical Systems.

[5]  Robi Polikar,et al.  An ensemble based data fusion approach for early diagnosis of Alzheimer's disease , 2008, Inf. Fusion.

[6]  J. Deasy,et al.  Combining multiple models to generate consensus: application to radiation-induced pneumonitis prediction. , 2008, Medical physics.

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[8]  Christos Davatzikos,et al.  EEG and MRI data fusion for early diagnosis of Alzheimer's disease , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Shoji Kido,et al.  Classification of patterns for diffuse lung diseases in thoracic CT images by AdaBoost algorithm , 2009, Medical Imaging.

[10]  Li Song,et al.  Recognizing Common CT Imaging Signs of Lung Diseases Through a New Feature Selection Method Based on Fisher Criterion and Genetic Optimization , 2015, IEEE Journal of Biomedical and Health Informatics.

[11]  Jingjing He,et al.  Neural network fusion strategies for identifying breast masses , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[12]  B. van Ginneken,et al.  Computer-aided diagnosis in high resolution CT of the lungs. , 2003, Medical physics.

[13]  S. Desai,et al.  Imaging in chest disease , 2012 .

[14]  Lena Costaridou,et al.  Texture-Based Identification and Characterization of Interstitial Pneumonia Patterns in Lung Multidetector CT , 2010, IEEE Transactions on Information Technology in Biomedicine.

[15]  Giulio Iannello,et al.  Aggregation of Classifiers for Staining Pattern Recognition in Antinuclear Autoantibodies Analysis , 2009, IEEE Transactions on Information Technology in Biomedicine.

[16]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Michael C. Lee,et al.  Computer-aided diagnosis of pulmonary nodules using a two-step approach for feature selection and classifier ensemble construction , 2010, Artif. Intell. Medicine.

[18]  Saurabh Prasad,et al.  A multi-classifier and decision fusion framework for robust classification of mammographic masses , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[19]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[20]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[21]  Mads Nielsen,et al.  Learning COPD Sensitive Filters in Pulmonary CT , 2009, MICCAI.

[22]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[23]  Michael F. McNitt-Gray,et al.  Automated classification of lung bronchovascular anatomy in CT using AdaBoost , 2007, Medical Image Anal..

[24]  Chong-Wah Ngo,et al.  Evaluating bag-of-visual-words representations in scene classification , 2007, MIR '07.

[25]  Xiabi Liu,et al.  Using HOG-LBP features and MMP learning to recognize imaging signs of lung lesions , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).

[26]  Robert P. W. Duin,et al.  The combining classifier: to train or not to train? , 2002, Object recognition supported by user interaction for service robots.

[27]  G. Beddoe,et al.  Efficient Computer-Aided Detection of Ground-Glass Opacity Nodules in Thoracic CT Images , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  A. Wang,et al.  The Application of Wavelet Transform to Multi-modality Medical Image Fusion , 2006, 2006 IEEE International Conference on Networking, Sensing and Control.

[29]  Bin Zheng,et al.  Computer-aided detection of early interstitial lung diseases using low-dose CT images , 2011, Physics in medicine and biology.

[30]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[31]  Hui Chen,et al.  Neural network ensemble-based computer-aided diagnosis for differentiation of lung nodules on CT images: clinical evaluation. , 2010, Academic radiology.

[32]  Li Song,et al.  A new classifier fusion method based on confusion matrix and classification confidence for recognizing common CT imaging signs of lung diseases , 2014, Medical Imaging.

[33]  Lihua Li,et al.  Classification of Breast Masses Based on Multi-View Information Fusion Using Multi-Agent Method , 2011, 2011 5th International Conference on Bioinformatics and Biomedical Engineering.

[34]  Tatjana Zrimec,et al.  Improving Computer Aided Disease Detection Using Knowledge of Disease Appearance , 2007, MedInfo.

[35]  Wei Liu,et al.  Multi-agent method for masses classification in mammogram , 2010, Medical Imaging.

[36]  J. del R. Millán,et al.  Multimodal Fusion of Muscle and Brain Signals for a Hybrid-BCI , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[37]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[38]  Bin Yu,et al.  Model Selection and the Principle of Minimum Description Length , 2001 .

[39]  Aydin Akan,et al.  Bagging support vector machine approaches for pulmonary nodule detection , 2013, 2013 International Conference on Control, Decision and Information Technologies (CoDIT).

[40]  Henning Müller,et al.  A classification framework for lung tissue categorization , 2008, SPIE Medical Imaging.

[41]  Berkman Sahiner,et al.  Computer-aided diagnosis of pulmonary nodules on CT scans: improvement of classification performance with nodule surface features. , 2009, Medical physics.

[42]  Jin Mo Goo,et al.  Computer-aided diagnosis of localized ground-glass opacity in the lung at CT: initial experience. , 2005, Radiology.

[43]  Dongkyoo Shin,et al.  A Comparative Study of Medical Data Classification Methods Based on Decision Tree and Bagging Algorithms , 2009, 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing.

[44]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.