A deep learning framework for early diagnosis of Alzheimer’s disease on MRI images

• Published in: Multimedia tools and applications Vol. 83; no. 2; pp. 3767 - 3799
• Main Authors: Arafa, Doaa Ahmed, Moustafa, Hossam El-Din, Ali, Hesham A., Ali-Eldin, Amr M. T., Saraya, Sabry F.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2024; Springer Nature B.V
• Subjects: Accuracy; Alzheimer's disease; Artificial neural networks; Biomarkers; Classification; Computer Communication Networks; Computer Science; Data augmentation; Data Structures and Information Theory; Datasets; Deep learning; Diagnosis; Feature extraction; Image classification; Machine learning; Magnetic resonance imaging; Medical diagnosis; Medical imaging; Multimedia Information Systems; Performance measurement; Signs and symptoms; Software; Special Purpose and Application-Based Systems; Convolution Neural Network (CNN); Alzheimer’s Disease (AD); Imaging Pre-processing; Deep Learning (DL); Transfer Learning (TL)
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-15738-7

Numerous medical studies have shown that Alzheimer’s disease (AD) was present decades before the clinical diagnosis of dementia. As a result of the development of these studies with the discovery of many ideal biomarkers of symptoms of Alzheimer’s disease, it became clear that early diagnosis requires a high-performance computational tool to handle such large amounts of data, as early diagnosis of Alzheimer’s disease provides us with a healthy opportunity to benefit from treatment. The main objective of this paper is to establish a complete framework that is based on deep learning approaches and convolutional neural networks (CNN). Four stages of AD, such as (I) preprocessing and data preparation, (II) data augmentation, (III) cross-validation, and (IV) classification and feature extraction based on deep learning for medical image classification, are implemented. In these stages, two methods are implemented. The first method uses a simple CNN architecture. In the second method, the VGG16 model is the pre-trained model that is trained on the ImageNet dataset but applies the same model to the different datasets. We apply transfer learning, meaning, and fine-tuning to take advantage of the pre-trained models. Seven performance metrics are used to evaluate and compare the two methods. Compared to the most recent effort, the proposed method is proficient of analyzing AD, moreover, entails less labeled training samples and minimal domain prior knowledge. A significant performance gain on classification of all diagnosis groups was achieved in our experiments. The experimental findings demonstrate that the suggested designs are appropriate for basic structures with minimal computational complexity, overfitting, memory consumption, and temporal regulation. Besides, they achieve a promising accuracy, 99.95% and 99.99% for the proposed CNN model in the classification of the AD stage. The VGG16 pre-trained model is fine-tuned and achieved an accuracy of 97.44% for AD stage classifications.