Review on Automated Brain Tumor Segmentation using Advanced Deep Learning Techniques: Enhancing Precision and Clinical Applicability

The incidence of brain tumors has emerged as a significant health concern in contemporary society, primarily due to the production of atypical cells within the brain that can lead to cancerous growths. Among the several types of BT, gliomas represent the most common form found in adults. Traditionally, the diagnosis of such tumors has relied on imaging techniques such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). However, early detection and accurate classification of tumors are vital for improving survival rates, as conventional methods can be time-consuming. In response to this challenge, researchers have been developing advanced segmentation and identification techniques for BT utilizing Machine Learning (ML) and Deep Learning (DL) methodologies, particularly through the application of Convolutional Neural network (CNN). These innovative approaches enhance diagnostic accuracy and facilitate earlier identification, thereby enabling patients to pursue appropriate treatment options, including chemotherapy, radiation, or surgical intervention, based on medical advice. Various algorithm and models were studied for BT classification and segmentation. We aim to design unused hybrid model for BT segmentation.