Detection of Alzheimer’s Disease with Deep Learning Method

Alzheimer's disease is a common type of dementia that is a progressive neurodegenerative disease with no cure. Many imaging techniques are used to diagnose the disease. One of these techniques is Magnetic Resonance Imaging (MRI). Early diagnosis is of great importance for the patient and his family in slowing the progression of the disease and taking the necessary precautions. Supportive studies have been carried out on this subject with deep learning methods for early and accurate diagnosis. At the same time, deep learning methods are used to follow the course of the disease. This study was carried out using AlexNet and MobileNetV2 architectures and CNN (Convolutional Neural Network) model. These features were combined by extracting features from both architectures using a total of 6400 MR images. Feature selection was made using the NCA (Neighbourhood Components Analysis) algorithm and classification were performed with SVM (Support Vector Machine). 100% accuracy value was calculated in the studied model.