<![CDATA[Magnetic Resonance Imaging (MRI) is one of the most widely used imaging modalities for diagnosing brain abnormalities due to its high spatial resolution and ability to visualize soft tissues in detail. However, manual interpretation of MRI images is time-consuming and subjective. This research aims to analyze the performance of the Random Forest algorithm in detecting brain tumors from MRI images. The dataset used consists of 253 brain MRI images obtained from the Kaggle Brain Tumor MRI Dataset, divided into two classes: tumor and non-tumor. The research stages include preprocessing, feature extraction using Gray Level Co-occurrence Matrix (GLCM), model training with Random Forest, and performance evaluation. Preprocessing steps such as grayscale conversion, noise reduction, contrast enhancement, and normalization were applied to improve image quality. The model achieved an accuracy of 86.27%, precision of 90%, recall of 87.1%, and F1-score of 88.52%, indicating strong classification capability. The results show that the Random Forest algorithm can effectively identify tumor patterns based on texture and intensity features, making it a reliable approach for supporting early brain tumor diagnosis and potentially applicable in developing automated computer-aided diagnostic systems in medical imaging.]]>
Copyrights © 2025
