| Summary: | Alzheimer's disease (AD) is a neurodegenerative ailment that causes cognitive deterioration due to changes in brain structure. Individuals usually see diagnostic symptoms after irreversible brain damage has occurred. In order to slow the course of the illness and enhance the quality of life for AD patients, early diagnosis is crucial. Recent advances in machine learning and scanning have made the use of these methods to detect AD in its earliest stages possible. This article uses deep learning using CNN methods to extract picture characteristics from ADNI (Alzheimer's Disease Neuroimaging Initiative) datasets to improve Alzheimer's disease diagnosis techniques. This descriptor will be used in conjunction with the CNN to categorize the illness and add new characteristics that are more accurate, quicker, and stable than the current features. In this process, an Alzheimer's detection System will be implemented to mitigate the adverse effects of data imbalance on recognition performance, and an integrated multi-depth architectural technology will be introduced to boost recognition quality. Using the suggested model of the convolution neural network (CNN) technique, classification accuracy results were obtained above 97%.
|
|---|