Multimodal deep learning framework for Alzheimer’s stage classification using GAN-augmented MRI and clinical data
Preprint
- 27 October 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Alzheimer’s disease (AD) diagnosis remains challenging due to the scarcity of annotated medical imaging data, pronounced class imbalance, and the subtlety of early-stage structural brain changes. Traditional deep learning approaches often overfit to majority classes and lack interpretability, limiting their clinical adoption. We propose a multimodal deep learning framework that fuses MRI-derived spatial features with standardized clinical parameters to enhance Alzheimer’s stage classification. The pipeline incorporates a GAN-based augmentation module to synthetically expand minority class samples, validated using MS-SSIM and expert review, thereby mitigating class imbalance. MRI features are extracted using a fine-tuned ResNet50, where lower convolutional layers preserve general spatial feature detectors while higher layers adapt to AD-specific morphological patterns. Clinical features, normalized via z-score scaling, are concatenated with MRI-derived embeddings to form a unified multimodal representation. This joint vector is processed through fully connected layers for four-stage classification Non-Demented, Very Mild Demented, Mild Demented and Moderate Demented. Model interpretability is ensured via Grad-CAM for spatial saliency mapping and clinical feature attribution, offering transparent decision support for healthcare practitioners. Experimentally, the framework achieved 97.56% validation accuracy, 0.98 macro precision, 0.97 macro recall and 0.98 macro F1-score, outperforming a baseline CNN (85.00% accuracy) and a GAN-augmented CNN (95.00% accuracy). Minority class recognition, such as for Moderate Demented improved from near-zero representation to 99% precision and recall due to balanced augmentation. This approach offers a scalable, interpretable, and high-accuracy diagnostic solution with the potential to transform automated neurodegenerative disease detection in clinical and telemedicine settings.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Attentive deep learning with Randomized Vector Energy Least Square Twin Support Vector Machine for Alzheimer’s Disease diagnosisComputers and Electrical Engineering, 2025
- Advanced convolutional neural network with attention mechanism for Alzheimer's disease classification using MRIComputers in Biology and Medicine, 2025
- Towards Clinical Diagnoses: Classifying Alzheimer's Disease Using Single fMRI, Small Datasets, and Transfer LearningBrain and Behavior, 2025
- Weighted Hybrid Random Forest Model for Significant Feature prediction in Alzheimer’s Disease StagesInternational Journal of Computational Intelligence Systems, 2025
- Advancing Alzheimer’s detection: integrative approaches in MRI analysis with traditional and deep learning modelsNeural Computing and Applications, 2025
- Integrated Multi-Modal 3D-CNN and RNN Approach with Transfer Learning for Early Detection of Alzheimer’s DiseaseIranian Journal of Science and Technology, Transactions of Electrical Engineering, 2024
- A multilayered framework for diagnosis and classification of Alzheimer's disease using transfer learned Alexnet and LSTMNeural Computing and Applications, 2023
- A Deep Learning-Based Ensemble Method for Early Diagnosis of Alzheimer’s Disease using MRI ImagesNeuroinformatics, 2023
- Pyramid-attentive GAN for multimodal brain image complementation in Alzheimer’s disease classificationBiomedical Signal Processing and Control, 2023
- Deep learning-based approach for multi-stage diagnosis of Alzheimer’s diseaseMultimedia Tools and Applications, 2023