High-performance compression-based brain tumor detection using lightweight optimal deep neural network

Abstract

Medical image-processing plays a vital role in the brain tumor detection and diagnosis process for supporting the automation of computerized based analysis. Magnetic Resonance Image (MRI) is widely considered an imaging modality used for the diagnosis of brain tumors. The primary concern of this research is to detect and reduce the affected tumor region from MRI images and segmentation. But it is a tedious and more challenging task. Most brain tumors are diagnosed after symptoms appear. Brain tumor is a life-threatening problem and hampers the normal functioning of the human body. The noise interference is the major problem in image compression. To overcome these kinds of issues computerized technology is proposed. In this research, to reduce the complexity and improve the performance of detecting the brain tumor in the medical image segmentation process, an optimal threshold segmentation approach is introduced. In this proposed approach, a Lightweight optimal Deep Learning Technique and an effectual compression standard technique are proposed to improve the quality of an image and accuracy level. Using this proposed approach accurate classification is done by minimizing the error. This paper combines the Whale optimization algorithm (WOA) and the Black Widow Optimization algorithm (BWO) to detect the tumor. This hybrid technique is used to detect the severity of the brain tumor. The analytical results of the suggested method have been calculated and verified for quality and performance analysis on MRI images, relying on dice coefficient, specificity, accuracy, structural similarity index, and sensitivity. This research showed that our approach is better than the previous research according to the quality standards and accuracy. The accuracy of our proposed work is greater than the other techniques.