Analysis of MR Images for Early and Accurate Detection of Brain Tumor using Resource Efficient Simulator Brain Analysis

Early detection of brain tumors is particularly important, as brain tumors are one of the leading causes of cancer-related mortality. However, identifying brain tumors can be challenging due to differences in tumor tissue variation among patients and, in some cases, the similarity of tumors to normal tissue. In this article, we propose a novel,
resource-efficient simulator called Brain Analysis for fast and accurate analysis and verification of brain tumors. The proposed simulator aims to improve the reliability and speed of this process in treatment. To evaluate its performance, accuracy, and other important factors, we compare the proposed algorithm with several other methods, including a genetic algorithm, a CNN-based multi-classification model, an ML scheme + SVM approach, and a CapsNets model based on collective intelligence. Our experimental results show that the proposed algorithm significantly reduces the time needed to accurately detect early brain tumors, compared to the other methods, by using a multi-core architecture and appropriate filters in the Brain Analysis Simulator. This research objective demonstrates the potential of the proposed simulator as a component of a strategy for the early and faster detection of brain tumors.