Normalized Multiple Features Fusion Based on PCA and Multiple Classifiers Voting in CT Liver Tumor Recognition

Liver cancer is a serious disease and is the third commonest cancer followed by stomach and lung cancer. The most effective way to reduce deaths due to liver cancer is to detect and diagnosis in the early stages. In this paper, a fast and accurate automatic Computer-Aided Diagnosis (CAD) system to diagnose liver tumors is proposed. First, texture features are extracted from liver tumors using multiple texture analysis methods and fused feature is applied to overcome the limitation of feature extraction in single scale and to increase the efficiency and stability of liver tumor diagnosis. Classification-based texture features is applied to discriminate between benign and malignant liver tumors using multiple classifier voting. We review different methods for liver tumors characterization. An attempt was made to combine the individual scores from different techniques in order to compensate their individual weaknesses and to preserve their strength. The experimental results show that the overall accuracy obtained is 100% of automatic agreement classification. The proposed system is robust and can help doctor for further treatment.

[1]  Dorota Duda,et al.  Computer-Aided Diagnosis of Liver Tumors Based on Multi-Image Texture Analysis of Contrast-Enhanced CT. Selection of the Most Appropriate Texture Features , 2013 .

[2]  K. Blekas,et al.  Fuzzy neural network-based texture analysis of ultrasonic images , 2000, IEEE Engineering in Medicine and Biology Magazine.

[3]  Konstantina S. Nikita,et al.  Characterization of CT liver lesions based on texture features and a multiple neural network classification scheme , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[4]  Hao Xu,et al.  Automatic thesaurus construction for spam filtering using revised back propagation neural network , 2010, Expert Syst. Appl..

[5]  Aboul Ella Hassanien,et al.  Automatic Mammographic Parenchyma Classification According to BIRADS Dictionary , 2014 .

[6]  Chein-I Chang,et al.  An automatic diagnostic system for CT liver image classification. , 1998, IEEE transactions on bio-medical engineering.

[7]  Gerald Schaefer,et al.  Automatic Segmentation and Classification of Liver Abnormalities Using Fractal Dimension , 2013, 2013 2nd IAPR Asian Conference on Pattern Recognition.

[8]  Agma J. M. Traina,et al.  An Efficient Algorithm for Fractal Analysis of Textures , 2012, 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images.

[9]  Ahmed M. Anter,et al.  Computational Intelligence Optimization Algorithm Based on Meta-heuristic Social-Spider: Case Study on CT Liver Tumor Diagnosis , 2016 .

[10]  R. S. Moni,et al.  Diagnosis of Liver Tumor from CT Images using Curvelet Transform , 2010 .

[11]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[12]  Aboul Ella Hassanien,et al.  Feature Selection Approach Based on Social Spider Algorithm: Case Study on Abdominal CT Liver Tumor , 2015, 2015 Seventh International Conference on Advanced Communication and Networking (ACN).

[13]  Oguz Gungor,et al.  Classification of multispectral images using Random Forest algorithm , 2012 .

[14]  Zhen Li,et al.  Classification of Hepatic Tissues from CT Images Based on Texture Features and Multiclass Support Vector Machines , 2009, ISNN.

[15]  Amr Ahmed,et al.  Computer-Aided Classification of Liver Lesions Using Contrasting Features Difference , 2015 .

[16]  Ahmed M. Anter,et al.  Computer Aided Diagnosis System for Mammogram Abnormality , 2016 .

[17]  R. K. Agrawal,et al.  First and Second Order Statistics Features for Classification of Magnetic Resonance Brain Images , 2012 .

[18]  Aboul Ella Hassanien,et al.  A Hybrid Approach to Diagnosis of Hepatic Tumors in Computed Tomography Images , 2014, Int. J. Rough Sets Data Anal..

[19]  Konstantina S. Nikita,et al.  A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier , 2003, IEEE Transactions on Information Technology in Biomedicine.

[20]  Shailendra Singh,et al.  Automatic Detection of Liver in CT images using Optimal Feature based Neural Network , 2013 .

[21]  Chien-Cheng Lee,et al.  Automatic Liver Diseases Diagnosis for CT Images Using Kernel-Based Classifiers , 2006, 2006 World Automation Congress.

[22]  S.Gunasundari,et al.  Comparison and Evaluation of Methods for Liver Tumor Classification from CT Datasets , 2012 .

[23]  A. Jemal,et al.  Global Cancer Statistics , 2011 .

[24]  G. S. Panayiotakis,et al.  Application of a neural network and four statistical classifiers in characterizing small focal liver lesions on CT , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  V. S. Bharathi,et al.  Classification of CT Liver Images Using Local Binary Pattern with Legendre Moments , 2016 .

[26]  Konstantina S. Nikita,et al.  Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers , 2007, Artif. Intell. Medicine.

[27]  Ashish Singh,et al.  Liver segmentation from registered multiphase CT data sets with EM clustering and GVF level set , 2010, Medical Imaging.

[28]  S. Janakiraman,et al.  A Study of Textural Analysis Methods for the Diagnosis of Liver Diseases from Abdominal Computed Tomography , 2013 .

[29]  V. Sadasivam,et al.  Wavelet based texture analysis of Liver tumor from Computed Tomography images for characterization using Linear Vector Quantization Neural Network , 2006, 2006 International Conference on Advanced Computing and Communications.