An Automated Computer-aided Diagnosis System for Abdominal CT Liver Images

Abstract In this paper, we present a computer-aided diagnosis (CAD) system for abdominal Computed Tomography liver images that comprises four main phases: liver segmentation, lesion candidate segmentation, feature extraction from each candidate lesion, and liver disease classification. A hybrid approach based on fuzzy clustering and grey wolf optimisation is employed for automatic liver segmentation. Fast fuzzy c-means clustering is used for lesion candidates extraction, and a variety of features are extracted from each candidate. Finally, these features are used in a classification stage using a support vector machine. Experimental results confirm the efficacy of the proposed CAD system, which is shown to yield an overall accuracy of almost 96% in terms of healthy liver extraction and 97% for liver disease classification.

[1]  Yee Leung,et al.  Clustering by Scale-Space Filtering , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Hichem Frigui,et al.  A Robust Competitive Clustering Algorithm With Applications in Computer Vision , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[4]  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.

[5]  Gerald Schaefer,et al.  Evaluating the effects of image filters in CT Liver CAD system , 2012, Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics.

[6]  Safaai Deris,et al.  RESEARCH REVIEW FOR DIGITAL IMAGE SEGMENTATION TECHNIQUES , 2011 .

[7]  N. Sakthivel,et al.  Mean – Median Filtering For Impulsive Noise Removal , 2014 .

[8]  Aboul Ella Hassanien,et al.  Level set-based CT liver image segmentation with watershed and artificial neural networks , 2012, HIS.

[9]  Jyotika Pruthi,et al.  Review of Image Processing Technique for Automatic Detection of Tumor in Human Liver , 2014 .

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

[11]  Mohamed Ali Mahjoub,et al.  Automatic liver segmentation method in CT images , 2012, ArXiv.

[12]  V. Sadasivam,et al.  Classification of Fatty and Cirrhosis Liver Using Wavelet-Based Statistical Texture Features andNeural Network Classifier , 2010, Int. J. Softw. Informatics.

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