Brain Tumor Analysis plays a vital role in detecting the tumored cells of the brain. A brain tumor can become very lethal at its advance stages. It can easily spread to other parts of the brain and affect the healthy cells of the brain as well. They reproduce uncontrollably. Hence, detection at early stages is very essential in treatment for improvement of the life expectancy of the patients. However, the detection of the tumor is a difficult and challenging task since the tumor possesses complex characteristics in appearance and boundaries. Magnetic resonance imaging (MRI) is being used extensively for the detection of brain tumors that requires segmenting huge volumes of 3D MRI images which is very challenging if done manually. It is the most commonly used medical image for brain tumor analysis. So, we are using MRI images for detecting the brain tumor. In this system, we are going to use Keras and Convolutional neural network(CNN) for the automatic segmentation and detection of a brain tumor using MRI images. It is considered as one of the efficient methods for detection of brain tumors. It has one or more convolutional layers and is used mainly for image classification and segmentation techniques. It helps in achieving high accuracy and is optimal as well.