This study presents a new method for brain tumor detection employing the Extreme Learning Machine (ELM) algorithm, focusing on medical imaging. The approach emphasizes image pre-processing to enhance significant features and minimize noise before inputting them into the ELM-based classifier which is known for its fast learning and efficient data handling. Because of its single hidden layer, the ELM algorithm outperforms previous methods, as evidenced by multiple trials on publicly available data. The system demonstrates high accuracy, sensitivity, and specificity, making it suitable for real-time applications in medical imaging. This advancement has the potential to improve computer-aided diagnosis systems by enabling early and reliable identification of brain tumors, thereby enhancing patient care.