Alzheimer's disease (AD) is an irreversible neurological disorder that causes the gradual decline of one's cognitive abilities, and thus, early detection is significant to slow down its deterioration. Magnetic resonance imaging (MRI) images have been commonly used to diagnose AD. Furthermore, deep learning techniques such as the Convolutional Neural Network (CNN) are utilized to assist the diagnosis due to the complexity of MRI's analysis. However, CNN models require large datasets for training and have a challenging nature for model optimization. Thus, Transfer Learning, an emerging method that can improve the performance of the deep learning model by eliminating the need for training from scratch, is introduced. This paper will propose a Transfer Learning-based EfficientNet-B0 model to classify MRI brain images for AD diagnosis. The MRI images are obtained from Alzheimer's Disease Neuroimaging Initiative (ADNI) database; only axial-plane images are used in this study. As a result, the multi-class classification of MRI images into AD, MCI, and NC classes using a Transfer Learning-based model resulted in a training accuracy of 98.93% and a validation accuracy of 87.17%. These results evidenced the significance of Transfer Learning in improving model performance.

The classification of Alzheimer's disease (AD) using deep learning models is hindered by the limited availability of data. Medical image datasets are scarce due to stringent regulations on patient privacy, preventing their widespread use in research. Moreover, although open-access databases such as the Open Access Series of Imaging Studies (OASIS) are available publicly for providing medical image data for research, they often suffer from imbalanced classes. Thus, to address the issue of insufficient data, this study proposes the integration of a generative adversarial network (GAN) that can achieve comparable accuracy with a reduced data requirement. GANs are unsupervised deep learning networks commonly used for data augmentation that generate high-quality synthetic data to overcome data scarcity. Experimental data from the OASIS database are used in this research to train the GAN model in generating synthetic MRI data before being included in a pretrained convolutional neural network (CNN) model for multistage AD classification. As a result, this study has demonstrated that a multistage AD classification accuracy above 80% can be achieved even with a reduced dataset. The exceptional performance of GANs positions them as a solution for overcoming the challenge of insufficient data in AD classification.

Insufficient medical images have always been a challenge for deep learning-based Alzheimer's disease classification and detection tasks. The availability of Magnetic Resonance Imaging (MRI) data is limited due to patients' privacy issues. Access to individual medical records is strongly protected by the law, and appropriate consent is needed to utilize them for research purposes. Besides that, publicly available databases often experience imbalanced classes, further contributing to the issue of insufficient data. Thus, the performance of deep learning models used to diagnose Alzheimer's disease is often hindered by this issue. Basic data augmentation methods such as geometrical augmentation techniques also had limited applications to medical data. Hence, this study proposes a deep learning technique of Generative Adversarial Network (GAN) to expand the MRI dataset and improve the classification model performance. MRI images from the Open Access Series of Imaging Studies (OASIS) database are used in this study to perform experiments and validate hypotheses. After applying GAN to expand the dataset, a pre-trained Convolutional Neural Network (CNN) model is used to classify the data into multiple classes of Alzheimer's and the model's performance is measured. As a result, an improvement in accuracy for the classification task can be observed, indicating that the GAN is a solution for overcoming the challenge of insufficient data for Alzheimer's diagnosis.