Automatic Multimodality Brain Tumor Detection

Automatic detection of brain tumor is a difficult task due to variations in type, size, location and shape of tumor. A multi-modality framework for automatic tumor detection by fusing different Magnetic Resonance Imaging modalities including T1-weighted, T2-weighted, and T1 with gadolinium contrast agent. The intensity, shape deformation were extracted from each image. The Multimodal MR images with simulated tumor have been used as the ground truth for training using neural networks and validation of the detection method. Preprocessing is done to coordinate the number of axis. The features are extracted and it is compared and used for further processing. Segmentation describes separation of suspicious region from background MRI image. The neural network is used for training the network for classification of tumor cells. The neural network is trained with the selected feature and tumor affected regions can be detected. KeywordsMRI, T1-WEIGHTED, T2-WEIGHTED, GADOLINIUM, MULTIMODAL