Alzheimer’s Disease Detection Using Convolution Neural Networks

Millions of people throughout the world are afflicted by the progressive neurological condition known as Alzheimer’s Disease (AD). Analyzing MRI brain pictures is one of the most promising methods for identifying AD. Deep learning methods have become effective tools for diagnosing AD from MRI scans in recent years. An overview of deep learning-based methods for AD identification using MRI scans is given in this research, along with an explanation of the various deep learning architectures, including convolutional neural networks (CNNs) and auto-encoders. We explore the difficulties in detecting AD using deep learning, such as the necessity for big and diverse datasets and the possibility of bias and overfitting. MRI images have been used in recent studies to identify AD using deep learning, including the utilization of adversarial training and transfer learning. The proposed work will give a good accuracy where training accuracy is 86.34% and validation accuracy is 86.45% on the test data with very small misclassifications on normal and very mild demented.