Tumor detection and classification of MRI brain image using wavelet transform and SVM

Brain tumor is a life threatening disease and its early detection is very important to save life. The tumor region can be detected by segmentation of brain Magnetic Resonance Image (MRI). In the case of suspected brain tumor, the location and size of tumor can be determined with the help of radiologic evaluations. The report of this evaluation is very important for futher diagnosis and treatment planning. The detection of tumor must be fast and accurate for the diagnosis purpose. The segmentation or extraction of brain tumor from MRI is possible manually. But it is time consuming and tedious. Also the accuracy depends upon the experience of expert. Hence, the computer aided automatic segmentation has become important. MRI scanned images offer valuable information regarding brain tissues. MRI scans provide very detailed diagnostic pictures of most of the important organs and tissues in our body. It is generally painless and noninvasive. It does not produce ionizing radiation. So MRI is one of the best clinical imaging modalities. Several automated segmentation algorithms have been proposed. But still segmentation of MRI brain image remains as a challenging problem due to its complexity and there is no standard algorithm that can produce satisfactory results. The aim of this research work is to propose and implement an efficient system for tumor detection and classification. The different steps involved in this work are image preprocessing for noise removal, feature extraction, segmentation and classification. Proposed work preprocessed the MRI brain image using anisotropic diffusion filters. In the feature extraction step, discrete wavelet transforms(DWT) based features are extracted. The extracted features was given as input to the segmentation stage. Here Support Vector Machine (SVM) was used for tumor segmentation and classification.