Paper Title
ALZHEIMER’S DISEASE STAGES CLASSIFICATION USING MRI AND DEEP LEARNING

Abstract
Abstract - Alzheimer’s disease is a progressive and irreversible brain disorder that affects memory and cognitive abilities. Early and accu-rate diagnosis of the disease is crucial for effective treatment and man-agement. In this study, we evaluated the performance of three different deep learning models, namely, CNN, InceptionV3, and EfficientNet B0, for the classification of Alzheimer’s disease stages using MRI images. We trained and validated these models on a dataset of 5,121 images and evaluated their performance on a test set of 1,279 images. Our results showed that the CNN model achieved the highest accuracy of 98.75% with a low loss of 5.28%. In comparison, InceptionV3 achieved an ac-curacy of 62.39% and a loss of 128.90, while EfficientNet B0 achieved an accuracy of 97.03% with a loss of 7.68. These results suggest that transfer learning using deep learning models can be an effective tool for accurate and early diagnosis of Alzheimer’s disease. Our study provides insights into the potential of deep learning models for the development of non-invasive and accurate diagnostic tools for Alzheimer’s disease. Keywords - Alzheimer’s disease • MRI images • deep learning • transfer learning • convolutional neural network • InceptionV3 • EfficientNet.