Comparative Survey of Deep Learning Techniques for Brain Tumor Detection

Abstract

Brain tumors are one of the most serious health problems today, and early detection is crucial for improving patient survival. Magnetic Resonance Imaging (MRI) is a commonly used, non-invasive technique that provides detailed images of brain tissues. A key step in diagnosing brain tumors is segmentation, which means separating abnormal tumor tissue from healthy brain areas. This step is important for accurate diagnosis, classification, and treatment planning.This paper reviews recent methods for brain tumor detection and segmentation using MRI. It focuses on image processing and deep learning techniques, especially Convolutional Neural Networks (CNNs), which are widely used in medical image analysis. The study also highlights common challenges in tumor detection, such as variations in size, shape, and unclear boundaries. This paper examines the strengths and weaknesses of different segmentation and classification techniques, as well as common preprocessing steps used to clean and prepare MRI images. The review also discusses how these techniques are improving and moving toward real-world clinical use.Overall, this paper provides a clear overview of the latest developments in brain tumor detection using MRI. It aims to support researchers and healthcare professionals in selecting more accurate and efficient tools for brain tumor diagnosis. Additionally, this survey focuses on enhancing tumor detection in the proposed research.