Detection of Alzheimer's Risk Level using Inception V3 Transfer Learning Model

Alzheimer's disease is a degenerative brain disease that worsens with time. Alterations characterize it in the brain, leading to specific proteins' deposition. Alzheimer's disease produces a reduction in brain volume, which eventually leads to brain cell death. More than 70% are 75 years of age or older. Alzheimer's disease is estimated to impact 60–70 percent of the world's 55 million dementia patients. Researchers have uncovered many elements that may contribute to the development of Alzheimer's disease. Machine learning techniques have the potential to improve the diagnosis method for Alzheimer's disease dramatically. Deep learning algorithms have seen a lot of success in the field of medical image analysis in recent years. Yet, there has been little study into the use of deep learning algorithms for detecting and categorizing Alzheimer's disease. This paper presents a deep-learning model for identifying and classifying different types of Alzheimer's disease using brain MRI data. The data collection contains a total of 6400 photographs. There are 1279 photographs used for training and 5121 for testing purposes; in this case, data augmentation is also employed to diversify the dataset. A CNN-based transfer learning model named Inception V3 is used to create results in this work, and the outcomes are compared based on precision, recall, F1-Score, and accuracy. The model's total accuracy is 89%. The use of categorization in predicting Alzheimer's disease is precious to medical experts involved in the condition's treatment.