ABSTRACT
Deep learning has been increasingly popular in recent years for resolving issues in a variety of domains, including medical picture analysis. In recent years, clinical image assessment has changed medical services by enabling professionals to make earlier illness diagnoses and enhance patient recovery. Alzheimer's disease (AD) diagnosis has become heavily reliant on imaging. AD is a degenerative neurological condition that progressively impairs a person's ability to think and remember. To identify the causes of dementia in AD patients, computed tomography scans (CT) and magnetic resonance imaging (MRI) were first used. The purpose of this study is to use CNN and ResNet50 to categorize MRI images of individuals with Alzheimer's disease into many classifications. A convolutional neural network (CNN) architecture known as ResNet50 has demonstrated outstanding performance in a range of image categorization tasks. There are several phases of AD, including mild cognitive impairment, mild Alzheimer's disease, moderate Alzheimer's disease, and severe dysfunction. In general, categorizing MRI images of AD patients using CNN, ResNet50, and other deep learning methods can help advance research, patient care, and the creation of novel treatment approaches. For CNN, the accuracy of training and testing was 85.71%, whereas the accuracy for ResNet50 was 99.80%.
