Brain tumors are now the 10th most prevalent type of tumor, affecting both children and adults, thanks to a considerable rise in incidence in recent years. If caught early enough, It is also one of the tumor forms that is most easily treated. In order to detect the kind and stage of tumor, scientists and researchers have been attempting to create advanced procedures and approaches. For re-sectioning and assessing irregularities in the shape, size, or location of brain tissues that in turn aid in the detection of tumors, two techniques that are extensively utilized are Magnetic Resonance Imaging (MRI) and Computer Tomography (CT). Doctors favor MRI over CT scan because of its benefits, which are addressed later in the text. As MRI provides non-invasive imaging, the cerebrum is one of the most profoundly involved locations in the medical science network. This paper offers a thorough review of the literature on approaches for detecting brain tumors and classifying abnormalities and normalcy in MRI images based on many methodologies such as deep learning techniques, meta-heuristic techniques, and their hybridization. It consists of the presentation and quantitative investigation of best-in-class strategies using conventional detection and classification techniques.

No abstract