Alzheimer's Disease Detection Based on Features Level Selection for CNN-SVM Combination

Neurodegenerative disease especially dementia are reported as disease that leads to death, Alzheimer's Disease (AD) is kind dementia that cause progressive and irreversible brain disorder loss which leads to death. AD shows no symptoms in its early stages which makes diagnosing it its beginning a challenge and helpful for doctors as they can slow down its progress in its early stages. Computer-aided approaches such as machine learning which come up with several techniques to detect AD by extracting features from the given image data and use them to build a classifier. Recently, a subcategory of machine learning called deep learning has widely been employed to enhance the medical diagnosis by attempting notable performance. In fact, these approaches avoid the tricky manual feature extraction using Convolutional Neural Network (CNN) considered as a reference in the field of computer vision. This paper proposes a combination of machine-deep learning technics for early diagnosis of AD from positron emission tomography (PET). We first train our CNN on PET images to extract the most relevant features, then we select the most appropriate CNN's level from where the features will be extracted, which will be feed in a second step as input to a Support Vector Machine based classifier (SVM). The proposed approach achieves notable results that exceeded the performance obtained by various existing approaches.