Prediction Alzheimer's disease from MRI images using deep learning

Alzheimer's is one of the diseases that are the most publicized type of dementia. Alzheimer's disease will be born every 3 second the world. Previous research shows that early prediction of AD in the medical field for reduced cost of treatment and time of it. To this end, construct an efficient prediction system for AD, which is the goal of this paper, often reduces time to treatment, medical errors, and overall healthcare cost. We used Deep Learning to predict and diagnose AD and for this reason using python code in Colaboratory as platform environments. In particular, we used 2D CNN and vgg16 to achieve the research goal, we used experiments conducted on MRI images from Kaggle dataset. Our experiment achieved accuracy of 67.5% for 2D CNN algorithm, while the vgg16 algorithm achieved accuracy of 70.3%. We conclude by showing that deep learning can improve the prediction AD and using algorithm vgg16 is better than 2D CNN.