OPTIMIZED U-NET SEGMENTATION MODEL AND DEEP MAXOUT CLASSIFIER FOR BRAIN TUMOR CLASSIFICATION

Abstract

The most serious nervous system ailment, a brain tumor impairs one’s health seriously and ultimately results in death. MRI, one of the most frequently used medical imaging modalities for brain tumors, has emerged as the main diagnostic system for the treatment and study of brain tumors. It was challenging to segment and classify the many kinds of brain tumors. The swarm intelligence approach has the potential to more efficiently and effectively tackle a number of issues. Therefore, this work develops a novel model for the classification of brain tumors that includes various phases. Primarily, the input image is preprocessed via the proposed median filtering that aids in removing noises. Subsequently, segmentation is done via optimal U-Net. For precise segmentation, the weights are tuned optimally by battle royale optimization with the Bernoulli randomization (BROBR) algorithm. Then, features like the proposed local Gabor XOR pattern (PLGXP), texton features, gray level co-occurrence matrix (GLCM), and correlation features are extracted. Finally, BTC is done using a deep maxout network (DMO) that provides the final output on the absence or presence of a brain tumor.