Revolutionizing Alzheimer’s Diagnosis: High-Accuracy Detection Through MRI and Deep Learning

Alzheimer’s disease (AD) is a progressive neurological disorder, making early detection critical for effectivetreatment. This study presents an innovative approach using deep learning to analyze brain MRI scans for theearly diagnosis of AD. By employing the SPM toolbox to preprocess MRI images, gray matter segments areextracted and used as input for a convolutional neural network (CNN). The method, tested on the Alzheimer’sDisease Neuroimaging Initiative (ADNI) dataset, achieved over ۹۴.۷% accuracy in classifying three groups:normal control (NC), mild cognitive impairment (MCI), and Alzheimer’s disease (AD). The CNN modelautomatically identifies key features from MRI scans, particularly focusing on the hippocampus, a region knownfor its early involvement in AD. This approach not only enhances diagnostic accuracy but also streamlines theprocess by eliminating the need for manual feature extraction, outperforming traditional methods. The resultsindicate that deep learning combined with MRI data offers a powerful tool for the early detection of AD, pavingthe way for better patient outcomes and more timely interventions.

کلیدواژه ها:

Brain Magnetic Resonance Imaging (MRI) ، Convolutional Neural Network(CNN) ، Mild Cognitive Impairment (MCI) ، Alzheimer’s Disease ، Normal Control (NC)