Early diagnosis of Alzheimer's disease from MRI images with deep learning model

Alzheimer’s disease (AD) is a chronic, irreversible brain illness for which there is now no known effective treatment. AD is a condition that significantly impairs the ability to carry out daily activities, ranging from mild to severe. Early diagnosis plays a critical role in patient care and clinical trials. Convolutional neural networks (CNN) are used to create a framework for identifying specific disease features from magnetic resonance imaging (MRI) scans. However, the image dataset obtained from Kaggle faces a significant issue of class imbalance, which requires equal distribution of samples from each class to address. In this article, to address this imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is utilized. A Inceptionv3 was utilized in conjunction with the DEMNET dementia network to extract essential features from AD images. The model achieved an accuracy of 98.67%.