An adaptive learning framework for Alzheimer’s disease diagnosis using structural Magnetic Resonance Imaging data analytics

Early and accurate diagnosis of Alzheimer’s disease (AD) is crucial for managing the disease and selecting therapies to slow its progression. Machine learning (ML) has demonstrated significant potential in improving its diagnostic accuracy with structural Magnetic Resonance Imaging (sMRI) data. However, developing robust ML models faces the challenge of domain shift in sMRI data caused by differences between datasets sources. These differences can lead to performance degradation when applying the ML models trained on one dataset to another. To address this issue, we propose a cross-domain learning framework tailored to classify AD, mild cognitive impairment (MCI), and cognitively normal (CN) subjects from sMRI data accounting for domain shift. Our approach begins by transfer-learning with pre-trained 3D ResNet50 using labeled images from the source domain. We then enhance the model through adversarial training using both source images and unlabeled target images and use the maximum mean discrepancy (MMD) to align the feature distributions across different domains at the same time. Building upon the adversarially trained model, we introduce a self-supervised learning stage with a teacher–student framework incorporated, which reduces class imbalance via dynamic class weights and reinforces domain alignment via MMD. Our proposed framework is validated to outperform existing domain adaptation approaches on 3T and 1.5T sMRI scans from Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Notably for MCI vs.CN classification, our model achieves a high enough accuracy of 86.86% to enable early detection of dementia. • Propose an adaptive learning framework for Alzheimer’s detection with structural imaging data. • Apply domain adaptation techniques to improve predictive model generalization. • Align feature distributions using maximum mean discrepancy in model training. • Reduce class imbalance with dynamic class weight adjustment during learning. • Achieve high accuracy for early dementia detection in mild cognitive impairment cases.