article · Multimedia Tools and Applications
Alzheimer's disease can manifest decades prior to clinical dementia, making early diagnosis critical for timely therapeutic intervention. Analysing the vast quantities of medical imaging data associated with early biomarkers demands high-performance computational solutions. A deep learning framework has been developed to classify stages of Alzheimer's disease using magnetic resonance imaging data. The workflow incorporates preprocessing and data preparation, data augmentation, cross-validation, and feature extraction alongside classification. Two distinct approaches were evaluated: a custom convolutional neural network and a fine-tuned, pre-trained VGG16 model using transfer learning. The framework operates effectively with fewer labelled training samples and minimal prior domain knowledge, while reducing computational complexity, overfitting, and memory demands. Both methods demonstrated strong classification capabilities across all diagnostic categories, with the custom architecture reaching accuracies of up to 99.99 percent and the fine-tuned VGG16 model achieving 97.44 percent accuracy.
Early diagnosis of Alzheimer's disease offers patients the best opportunity to benefit from medical treatment before severe symptoms appear. Automated, reliable classification of magnetic resonance images can help process large amounts of diagnostic data efficiently. By requiring minimal training samples and lower computational resources, such approaches make advanced machine learning tools more feasible for integration into clinical diagnostic workflows.
This framework could enable automated diagnostic software tools for healthcare providers and radiologists assessing brain scans for early signs of Alzheimer's disease. Because it achieves high accuracy with low computational and memory demands, the system is suitable for deployment on standard computer hardware. However, the work represents early-stage technical research tested on benchmark datasets, requiring clinical validation and regulatory clearance before reaching commercial medical use.
AI-generated from the published abstract. Always read the original work before citing.
Abstract 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.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s11042-023-15738-7
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
