Alzheimer's disease (AD), a complex, incurable, and terrible illness, has a positive worldwide influence on human survival. It had no vaccinations, making it the sixth most significant cause of mortality in the United States. The most challenging aspect of biological discovery. The identification of AD-related proteins and genes will aid in the understanding of the disease's aetiology and the identification of vaccine and treatment targets. They look into combining genes/proteins with Alzheimer's, necessitating using functional instruments and experience. It was used to build a machine-learning algorithm for predicting the connection of proteins with Alzheimer's disease using current data from all known AD proteins/genes. We proposed the EADD (Enhanced Alzheimer's Disease Detection) technique for MR scan of the brain is often used to diagnose Alzheimer's. The MRI dataset noises have been removed using Multilayer perception(MLP). The image enhancement has been done with Histogram equalization in this proposed work, the image segmentation has been done using Edge-based Robert operator, Training has been done using CNN with RESNet150, and classification has been done with CNN Algorithm. The experimental results indicate that the classification accuracy of the approach proposed in this research can reach 98%.