<![CDATA[Alzheimer's disease (AD) is a progressive neurodegenerative disorder and one of the leading causes of dementia worldwide. Early detection is critical to slowing disease progression and improving patient outcomes. While Magnetic Resonance Imaging (MRI) is commonly used for AD diagnosis, analyzing the high-dimensional data remains challenging. This study explores the use of texture features from MRI images to improve the accuracy of AD classification using machine learning. This research utilized MRI brain images from publicly available datasets to classify early-stage Alzheimer's disease. The Random Forest algorithm handled large, complex datasets while minimizing overfitting. Texture features, including Histogram, Gray Level Co-Occurrence Matrix (GLCM), and Gray Level Run-Length Matrix (GLRLM), were extracted to highlight microstructural changes in the brain, particularly in the hippocampus and cortex—critical areas affected by AD. The model achieved an accuracy of 88%, precision of 85%, and Recall of 92% in the 10th fold using the WEKA platform, demonstrating its effectiveness in detecting early neurodegenerative changes. The Random Forest model, combined with texture feature extraction, provides a computationally efficient approach for the early detection of Alzheimer's disease. By identifying subtle changes in brain tissue, this method can potentially support clinicians in early diagnosis and intervention planning. Future research should focus on integrating additional imaging modalities and clinical data to enhance diagnostic accuracy and reliability.]]>
Copyrights © 2026
