Abstract: Background: Brain tumors are a significant global health concern impacting both adults and children. Tumors are characterized by abnormal or excessive growth resulting from uncontrolled cell division. Diagnosing brain tumors poses various challenges, including limited funding, a shortage of qualified professionals, and insufficient access to medical facilities in remote regions. Different learning techniques for detecting brain tumors have been developed due to their ease of use, cost-effectiveness, and non-invasive nature, in contrast to other invasive methods. Methods: This research conducts a systematic literature review to explore modern trends and concepts of machine learning in healthcare, aiming to identify effective techniques for brain tumor detection. It also compares and analyzes the most efficient machine learning methods currently in use, focusing on aspects such as machine learning algorithms, image augmentation, evaluation metrics, and the sizes of datasets employed. Results: The findings indicate that non-invasive methods, such as machine learning algorithms for brain tumor detection, are cost-effective and provide quick results. Conclusions: This systematic literature review offers a technical overview, demonstrating the efficiency and effectiveness of machine learning techniques in making brain tumor detection feasible. The study utilizes deep learning and machine learning methods to comprehensively analyse diagnosis, imaging, and clinical evaluations in medical fields related to brain tumor detection.
Read full abstract