Automatic classification of computed tomography brain images using ANN, k-NN and SVM

Computed tomography images are widely used in the diagnosis of intracranial hematoma and hemorrhage. This paper presents a new approach for automated diagnosis based on classification of the normal and abnormal images of computed tomography. The computed tomography images used in the classification consists of non-enhanced computed tomography images. The proposed method consists of four stages namely pre-processing, feature extraction, feature reduction and classification. The discrete wavelet transform coefficients are the features extracted in this method. The essential coefficients are selected by the principal component analysis. The features derived are used to train the binary classifier, which infer automatically whether the image is that of a normal brain or a pathological brain, suffering from brain lesion. The proposed method has been evaluated on a dataset of 80 images. A classification with a success of 92, 97 and 98 % has been obtained by artificial neural network, k-nearest neighbor and support vector machine, respectively. This result shows that the proposed technique is robust and effective.

[1]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[2]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[3]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[4]  Qi Tian,et al.  Automatic labeling and classification of brain CT images , 2011, 2011 18th IEEE International Conference on Image Processing.

[5]  Max Wintermark,et al.  The Role of CT and MRI in the Emergency Evaluation of Persons with Suspected Stroke , 2010, Current neurology and neuroscience reports.

[6]  R. Sukanesh A Padma,et al.  Automatic Classification and Segmentation of Brain Tumor in CT Images using Optimal Dominant Gray level Run length Texture Features , 2011 .

[7]  Xiaomei Li,et al.  Automatic segmentation of intracranial hematoma and volume measurement , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  Augusto Silva,et al.  Spontaneous Intracerebral Hemorrhage Image Analysis Methods: A Survey , 2009 .

[9]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  K. Doi,et al.  Current status and future potential of computer-aided diagnosis in medical imaging. , 2005, The British journal of radiology.

[11]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[12]  J. Sivaswamy,et al.  A method for automatic detection and classification of stroke from brain CT images , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Mohammad Pooyan,et al.  A new approach for classification of human brain CT images based on morphological operations , 2010 .

[14]  Wufan Chen,et al.  Region Feature Extraction of Brain CT Image for Classification , 2008, 2008 2nd International Conference on Bioinformatics and Biomedical Engineering.

[15]  Xi-Zhao Wang,et al.  Feature Extraction and Classification for Human Brain CT Images , 2007, 2007 International Conference on Machine Learning and Cybernetics.