Texture based feature extraction method for classification of brain tumor MRI

In machine learning based disease diagnosis, extraction of relevant and informative features from medical image slices is vital aspect. Extracted features represent the descriptive nature of the imaging modality for machine learning. Texture description, is one such method which is used to extract the informative aspect of the object. In this paper a new texture based feature extraction algorithm is proposed for extracting relevant and informative features from brain MR Images having tumor. Suggested algorithm is based on finding the texture description using nine different variants of texture objects. Subsequently, the intermediate texture index matrix is formed using texture objects with high pass and low pass spiral filters. The resultant two index matrix are used to generate the Texture Co-occurrence Matrix (TOM). TOM helps to extract the spatial and spectral domain features that forms the hybrid feature set for brain MRI classification. Using TOM, an experimentation is performed with a dataset of 660 T1-weighted post contrast brain MR Images having 5 different types of malignant tumors. Experimental results suggest that proposed method gives significant results in abnormality classification when compared with state-of-art GLCM and Run length algorithms.