A Web-Based Interface for Comprehensive Staging Classification of Alzheimer's Disease Diagnosis Through Convolutional Neural Networks

Alzheimer's Disease (AD) is a chronic neurodegenerative condition that results in behavioral changes, memory loss, and cognitive decline. Though there has been a lot of ongoing research, there is still no effective treatment for its diagnosis. Therefore, early detection of AD is necessary for managing symptoms and slowing its progression. The proposed approach enables the Convolutional Neural Networks (CNN) to learn all the relevant features from the input processed Magnetic Resonance Images, followed by effective classification of the disease. The trained CNN model possesses the capability to categorize Alzheimer's into distinct ages like early, mild, and moderate. In addition, a web- based Graphical User Interface has been developed using Python library, to enhance user-friendliness and informational value. Through this intuitive interface, users can access comprehensive information regarding the symptoms linked with each stage and precautions to be taken for it.