<![CDATA[A brain tumour develops when abnormal cell growth happens in or near the brain. These tumours can grow slowly and not be cancerous, or they can grow quickly and spread, which is known as malignancy. Brain tumours put pressure on the surrounding brain tissues, causing symptoms like memory loss, migraines, movement dysfunction, and vision impairment. Brain tumours are often divided into two groups: primary tumours, which start in the brain, and secondary tumours, which are caused by cancers that spread to other regions of the body. Although brain tumours provide a significant medical challenge, patient outcomes have improved thanks to recent advancements in diagnostic and treatment methods. Because of its better soft-tissue contrast and noninvasive nature, magnetic resonance imaging (MRI) is one of the most important medical imaging modalities for the early identification and precise localization of brain tumours. Clinical practice also makes use of other imaging methods such as PET-CT and functional MRI (fMRI). Artificial intelligence and deep learning techniques have demonstrated significant promise in automated brain cancer analysis in recent years. These methods enable precise cancer diagnosis, classification, and segmentation by identifying intricate patterns from MRI data that are challenging to recognize through manual examination. A thorough study of current deep learning and machine learning techniques for MRI-based brain tumour analysis is provided in this paper. The current thorough literature search includes papers released between 2019 and 2024. 67 pertinent articles are chosen for in-depth analysis after predetermined inclusion and exclusion criteria is used. Many of these studies make use of publicly accessible datasets like Figshare, TCIA, and BraTS. The results show that deep learning models frequently outperform traditional machine learning methods in terms of accuracy and robustness, especially convolutional neural network-based designs. However, there are still issues with clinical generalisation, model interpretability, and data heterogeneity.]]>
Copyrights © 2026
