3. BİLSEL INTERNATIONAL WORLD SCIENCE AND RESEARCH CONGRESS
ALZHEIMER STAGE CLASSIFICATION WITH DEEP LEARNING ALGORITHMS
With the advancement of Artificial Intelligence today, successful AI models are being developed for the classification of images on large datasets. Deep Learning algorithms, among AI algorithms, have been developed with high accuracy rates for successful models. Deep Learning algorithms are frequently used in studies on images for classification and object detection problems. In this study, the classification of Alzheimer's disease has been conducted using Deep Learning algorithms. Alzheimer's disease is characterized by a decline in cognitive functions and daily living activities, behavioral changes, and psychiatric symptoms, representing a progressive neurodegenerative type of dementia. According to the World Health Organization, there are approximately 55 million people with dementia worldwide, with this number expected to rise to 78 million by 2030 and 139 million by 2050. It is estimated that there are more than 600,000 Alzheimer's patients in Turkey, and as of now, there is no cure. The accurate diagnosis of Alzheimer's disease plays a crucial role, especially in the early stages of patient care. In the study, the classification of Alzheimer's disease stages was performed using different brain MRI (Magnetic Resonance Imaging) image data. A new hybrid model was constructed by considering 1000 features through deep learning models such as EfficientNetB0, ResNet50, DenseNet201, MobileNetV2, and InceptionV3. Our hybrid model was compared with deep learning models through an SVM classifier and emerged as the most successful model.
Yayınevi Bilgileri
Alıntı Yap
Benzer Yayınlar
Kitap Bölümleri
Bu Sayfayı Yazdırın
Endnote
Mendeley