Enhancing Glioma Brain Tumor Detection from MRI using Deep Learning Techniques

Brain tumor classification from MRI image is one of the important areas in biomedical research. However, the interpretation of these images is subjective, and automated detection methods can improve diagnostic accuracy. This study proposes a hybrid model that combines deep learning, machine learning, and traditional image processing techniques to detect brain tumors from MRI images. The proposed model is based on a convolutional neural network (CNN) algorithm and a machine learning model. The first stage is employing the histogram equalisation approach to enhance the image. In the second stage, features of the grey level co-occurrence matrix are extracted from the improved image. Convolutional neural networks are utilised in the third stage to categorise as normal or abnormal. The abnormal brain tumor is segmented using a morphological segmentation algorithm. This study suggests a number of performance criteria, such as accuracy, sensitivity, and specificity, to evaluate the efficacy of the proposeed method. Our proposes algorithm demonstrates superior performance compared to existing methods regarding accuracy, sensitivity, and specificity.