Detection and classification of Alzheimer's disease using deep learning methods

With the advancement of artificial intelligence, deep learning algorithms are frequently used in image-related studies. Deep learning algorithms provide high accuracy rates in image classification and object detection problems. Developing models with high speed and accuracy using deep learning algorithms is crucial for the detection of Alzheimer's disease. Alzheimer's disease is a progressive neurodegenerative disorder characterized by a decline in cognitive functions, the ability to perform daily activities, behavioral changes, and psychiatric symptoms. According to the World Health Organization,there are approximately 55 million dementia patients worldwide, and this number is expected to reach 78 million by 2030 and 139 million by 2050. In Turkey, it is estimated that there are more than 600,000 Alzheimer's patients. Currently, there is no cure for Alzheimer's disease. Accurate diagnosis of Alzheimer's disease, especially in the early stages, plays a significant role in patient care, as awareness of severity and progression risks allows patients to take preventive measures before irreversible brain damage occurs. In this thesis, the classification of Alzheimer's disease was performed using EfficientNetB0, ResNet50, DenseNet201, MobileNetV2, and InceptionV3 models, and a hybrid model was developed based on the used models. Experimental results showed that the developed hybrid model was the most successful one.