Brain Tumor Detection Using Deep Learning Techniques

Brain tumors can happen in the brain tissue. Nearby locations include nerves, the pituitary gland, the pineal gland, and the membranes that cover the surface of the brain. Although MRI images are a popular imaging method for evaluating these tumors, the volume of data it generates makes it difficult to manually segment the images in a reasonable amount of time, which restricts the use of precise quantitative assessments in clinical settings. The enormous spatial and structural heterogeneity among brain tumors makes automatic segmentation a difficult task, hence dependable and automatic segmentation methods are needed. This project focuses on developing deep learning models based on convolutional neural network and watershed algorithms to perform the automated semantic image segmentation of the MRI images of the brain. We explore the current state of the CNNs architecture and evaluate them on the BraTS dataset. Different regularization methods and hyperparameters are tested and optimized through a series of experiments. Finally, a web application is created so that the developed models can be used easily by medical practitioners. Key Words: CNN, Deep Learning, Histogram of Oriented Gradients (HOG), Fully Convolutional Networks (FCNs), Conditional Random Fields (CRFs), Support Vector Machine (SVM).