A deep feature-based real-time system for Alzheimer disease stage detection

The origin of dementia can be largely attributed to Alzheimer's disease (AD). The progressive nature of AD causes the brain cell deterioration that eventfully leads to physical dependency and mental disability which hinders a person's normal life. A computer-aided diagnostic system is required that can aid physicians in diagnosing AD in real-time. The AD stages classification remains an important research area. To extract the deep-features, the traditional machine learning-based and deep learning-based methods often require large dataset and that leads to class imbalance and overfitting issues. To overcome this problem, the use an efficient transfer learning architecture to extract deep features which are further used for AD stage classification. In this study, an Alzheimer's stage detection system is proposed based on deep features using a pre-trained AlexNet model, by transferring the initial layers from pre-trained AlexNet model and extract the deep features from the Convolutional Neural Network (CNN). For the classification of extracted deep-features, we have used the widely used machine learning algorithms including support vector machine (SVM), k-nearest neighbor (KNN), and Random Forest (RF). The evaluation results of the proposed scheme show that a deep feature-based model outperformed handcrafted and deep learning method with 99.21% accuracy. The proposed model also outperforms existing state-of-the-art methods.