ABSTRACT
In modern medical imaging the process of detecting tumors in brain is a very crucial and sensitive task, with the potential to have a significant impact on patient outcomes. This abstract provides an overview of the difficulties, most recent developments, and current research in brain tumor detection is given in this abstract. For the purpose of early diagnosis, medical professionals employ advanced imaging techniques such as MRI images and CT scans. These modalities are essential tools in detecting and evaluating various medical conditions at an early stage, allowing for timely and accurate treatment planning. In the past radiologist were evaluated manually but with advance techniques of deep learning particularly convolutional neural networks (CNNs), the field has experienced a revolution. These AI-based methods have shown encouraging results in automating the identification of brain tumors, increasing accuracy, and lessening the workload for medical personnel when combined with sizable and varied datasets. Yet, there are still issues, such as the requirement for more datasets, the interpretability of AI models, and CNN achieved a really impressive accuracy of 97.87% in our study. The paper's central idea revolves around the use of texture based and statistical criteria for distinguishing the normal and aberrant pixels.
