<![CDATA[Brain stroke is a critical medical condition caused by a disruption in blood supply to the brain, classified into ischemic and hemorrhagic strokes. Accurate classification of strokes into normal, ischemic, and hemorrhagic categories is essential for effective treatment planning and improved patient outcomes. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the primary imaging modalities used for stroke diagnosis, offering complementary advantages in capturing crucial brain information. This paper reviews state-of-the-art computer-aided techniques, including Machine Learning (ML), Deep Learning (DL), Transfer Learning (TL), and Hybrid models for stroke classification using MRI and CT images. A systematic analysis of methodologies is conducted based on their characteristics and similarities. From 2020 to 2025, studies were identified from scientific databases such as Google Scholar, Springer, and ScienceDirect, focusing on these advanced techniques for brain stroke classification. This review highlights the contributions of each approach and the integration of MRI and CT imaging in developing accurate and efficient automated diagnostic systems.]]>
Copyrights © 2025
