BRAIN TUMOR DETECTION AND CLASSIFICATION IN MEDICAL IMAGING: A SYSTEMATIC REVIEW OF APPROACHES, CHALLENGES AND RESEARCH TRENDS

Abstract

Recently, the world has observed emerging transformations in several domains due to the crucial developments in computer vision and Artificial Intelligence (AI) such as Machine Learning (ML) and Deep Learning (DL) techniques. This revolution has also inspired the medical sector as it generates a huge range of information. Among various medical domains, these techniques have shown excellence in identifying and categorizing brain tumors using different modality images. Thereby, this research study aims to review the use of AI techniques in brain tumor detection and classification studies by using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. This review covers the insights about the review of several AI techniques for brain tumor detection and classification approaches, concerning complicated tumor types and heterogeneous datasets. This review has also explored imaging modalities used for brain tumor analysis along with the conceptual overview on performance measures considered and experimental platforms considered for the experimentation. This analysis offered promising results to assist future researchers with a comprehensive perspective on recent research trends and analysis of several DL methodologies. Finally, it also discusses the challenges and future research directions on upcoming research challenges and opportunities for brain tumor detection techniques to assist medical professionals.