Jiawei Zhang ¹ , Xin Zhang ¹ and Xinyin Miao ² , ¹ PRA Group (Nasdaq: PRAA), USA, ² American Airlines Group Inc (Nasdaq: AAL), USA

This paper utilizes four cutting edge deep learning architectures, namely VGG19, Xception, InceptionV3, and ResNet50, with transfer learning, image augmentation and two layers of regularization to be able to accurately predict the Alzheimer's Disease classes under 33,982 MRI images with a 0.9563 accuracy, 0.9972 roc_auc, and 0.9559 F1 score in the testing scenario. By investigating the internal neural network structures and comparing the prediction performance, it provides the insight of how various deep learning architectures work differently with corresponding deep learning structure layouts. The main contribution of this article also includes the study of image augmentation and deep learning regularization methodologies to enhance architecture performance and reduce transfer learning over-fitting in the Alzheimer's disease image-based classification.

Deep learning, Transfer Learning, Image Classification, Neural Network Architecture, Regularization, Augmentation