Implementation of Brain Tumor Detection with Deep Learning Classification Using Hybrid Feature Extraction

Abstract

Brain tumor is the most common kind of cancer, accounting for millions of fatalities worldwide. Early detection and treatment of new dangerous Brain tumor cases are critical to ensuring a low mortality rate as well as a high survival rate. The majority of relevant research has focused on machine learning-based algorithms, but they haven't been able to achieve the highest levels of accuracy and specificity. To address this issue, this work employs a deep learning based convolutional neural network (CNN) classification mechanism based on advanced deep learning. For effective identification of the location of Brain tumor, a k-means clustering based segmentation technique is first applied. Finally, CNN was constructed for Brain tumor classification with grey level co-occurrence matrix (GLCM) based Texture features, decimated wavelet Transform (DWT) based low level features, and Statistical Color features, respectively, to archive the system's maximum efficiency. As a result, the research findings can be utilized to classify benign and malignant based brain tumors. In comparison to state-of-the-art techniques, simulation study demonstrates that the suggested method provides better qualitative and quantitative analyses.