Application of Contourlet Transform in Brain Tumor Classification

In this paper, contourlet transformation has been used for Brain Tumor classification along with Probabilistic neural network. The other methods like wavelet and support vector machine based classification resulted in a limited precision, since it cannot work accurately for a large data due to training complexity. Computerized Tomography and Magnetic Resonance Images are based on human inspection for tumor classification and detection. These methods are not effective and are also non reproducible if amount of data is large. Also, the directional features of wavelet and other transforms are not taken from all directions except horizontal,vertical and diagonal. Neural Networks based classificatioin shows good results in medical fields which are combined here with contourlet transform. Decision is based on two steps (i) Image reduction and Feature extraction using contourlet transform (ii) Classification using probabilistic Neural Network(PNN). Various Features extracted from different brain images are tabulated which shows 100%  recognition rate and also fast results, when compared to other classifiers.

Index Terms— Brain tumor image classification, Probabilistic, Neural Networks, Contourlet Transform, Dimensionality Reduction, Feature Extraction.