Detection and diagnosis of brain tumors using deep learning convolutional neural networks

The detection of brain tumors in brain magnetic resonance imaging (MRI) image is an important process for preventing earlier death. This article proposes an automated computer aided method for detecting and locating the brain tumors in brain MRI images using deep learning algorithms. The proposed method has three sub modules as preprocessing, classifications and segmentation. In this article, data augmentation is used as preprocessing method. The preprocessed brain MRI images are classified into either tumor case or nontumor case using classification approach. In this brain tumor detection and segmentation process, convolutional neural networks (CNNs) classification architecture is used for classifying the brain images. The morphological based segmentation methodology is used in this article for segmenting the tumor regions in classified brain images. Further, the segmented tumor regions are diagnosed into "Mild" and "Severe" case using CNN architecture. The proposed methodology is applied on the brain images from open access dataset. The performance of the proposed system is analyzed in terms of sensitivity, specificity, and precision, F-score, Disc similarity index and tumor region segmentation accuracy on set of brain images. The simulation results of this proposed framework are verified by expert radiologist.