Early detection of Alzheimer’s Disease using MRI images and deep learning techniques

Background Alzheimer’s is a neurodegenerative disease that diminishes the capability of individuals to perform their daily activities. It is an irreversible disease once it is started not able to stop it but early detection of the disease can help to slow down the progression of it by starting early treatment. In this experiment, we use MRI images and clinical study data available at the Alzheimer’s Disease Neuroimaging Initiative data set to detect the different stages of Alzheimer’s and forecast the duration required for the conversion from mild cognitive impairment to Alzheimer’s. The clinical signs of Alzheimer’s disease are portrayed by Age, patient education details, the progression rate of disease, and cognitive information. Done experiment by using Machine learning and Deep learning techniques like multi perceptron networks, Random forest, SVM, and decision tree classifiers to do binary and multi‐classification of Alzheimer’s Disease(AD), Late Mild cognitive impairment (MCI), Early cognitive impairment (EMCI), and Cognitive control(CN). Method Deep learning technique Result an average the model achieved 91.25% of precision indicates 91.25% total positive images are correctly classified, 91.25% of sensitivity indicates 91.25% of total images are detected remaining are not, and achieved 95.52% of accuracy Conclusion Alzheimer’s is a neuron degenerative disease. Currently no treatment is available to cure AD or to stop progress of disease. But detection of dementia at its early stage might help individual family to think about their future regarding financial issues. In this work we tried our best to categorize the different phases of AD. We used a deep neural network and achieved an accuracy of 95.52%.