Technology Category
Computer Vision: Adversarial Attacks & RobustnessMachine Learning: Transfer, Domain Adaptation, Multi-Task LearningCognitive Modeling & Cognitive Systems: Adaptive Behavior
EffNetViTLoRA: An Efficient Hybrid Deep Learning Approach for Alzheimer's Disease Diagnosis
🤖 AI Summary
Early and accurate diagnosis of Alzheimer’s disease (AD) remains challenging due to difficulties in identifying mild cognitive impairment (MCI) and ambiguous class boundaries among AD, MCI, and cognitively normal (CN) individuals. To address these issues, we propose an end-to-end hybrid deep learning model that synergistically integrates convolutional neural networks (CNNs) and Vision Transformers (ViTs), augmented with Low-Rank Adaptation (LoRA) for efficient fine-tuning of pre-trained weights—thereby enhancing cross-domain generalizability and clinical robustness. The model is trained and evaluated on the complete ADNI cohort using T1-weighted MRI scans, performing a three-class classification task (AD, MCI, CN). Experimental results demonstrate state-of-the-art performance: 92.52% accuracy and 92.76% macro-F1 score on the full ADNI dataset—surpassing existing methods. This work delivers an interpretable, transferable AI solution for early MCI detection and stratified AD diagnosis.
Technology Category
Application Category
📝 Abstract
Alzheimer's disease (AD) is one of the most prevalent neurodegenerative disorders worldwide. As it progresses, it leads to the deterioration of cognitive functions. Since AD is irreversible, early diagnosis is crucial for managing its progression. Mild Cognitive Impairment (MCI) represents an intermediate stage between Cognitively Normal (CN) individuals and those with AD, and is considered a transitional phase from normal cognition to Alzheimer's disease. Diagnosing MCI is particularly challenging due to the subtle differences between adjacent diagnostic categories. In this study, we propose EffNetViTLoRA, a generalized end-to-end model for AD diagnosis using the whole Alzheimer's Disease Neuroimaging Initiative (ADNI) Magnetic Resonance Imaging (MRI) dataset. Our model integrates a Convolutional Neural Network (CNN) with a Vision Transformer (ViT) to capture both local and global features from MRI images. Unlike previous studies that rely on limited subsets of data, our approach is trained on the full T1-weighted MRI dataset from ADNI, resulting in a more robust and unbiased model. This comprehensive methodology enhances the model's clinical reliability. Furthermore, fine-tuning large pretrained models often yields suboptimal results when source and target dataset domains differ. To address this, we incorporate Low-Rank Adaptation (LoRA) to effectively adapt the pretrained ViT model to our target domain. This method enables efficient knowledge transfer and reduces the risk of overfitting. Our model achieves a classification accuracy of 92.52% and an F1-score of 92.76% across three diagnostic categories: AD, MCI, and CN for full ADNI dataset.
Problem
Research questions and friction points this paper is trying to address.
Diagnosing Alzheimer's disease and Mild Cognitive Impairment from MRI scans
Distinguishing subtle differences between adjacent diagnostic categories in neuroimaging
Adapting pretrained vision models effectively for medical domain transfer
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hybrid CNN-ViT model for feature extraction
Full ADNI MRI dataset training for robustness
LoRA fine-tuning for efficient domain adaptation
🔎 Similar Papers
No similar papers found.
