Convolutional Neural Network for Alzheimer's Disease Prediction Using MRI and Incomplete Clinical Scores

Alzheimer's Disease (AD) is one among the death-causing problem in the developed countries such as United States. So, a critical focus on the disease prognosis is in greater need. Since Magnetic Resonance Imaging (MRI) scans their own benefits in obtaining high-resolution data and the use of computer-based techniques such as Deep Learning (DL) has been one of the hottest topics in the domain of medical image analysis. The paper focuses on the application of the DL technique such as Convolutional Neural Network (CNN) model with modification in a number of layers for the purpose of disease prognosis using incomplete clinical scores. The experiment performed here is just a trial of using deep layers in making more features in the process of predicting the disease. To check the robustness of the model, it is trained and tested with two sets separately. The accuracy obtained from each trial lies at approximately 96% which is found higher than other comparing models. This experiment obtained an inspiration from the works that made use of incomplete clinical scores for disease prognosis.