A Computer Vision Hybrid Approach: CNN and Transformer Models for Accurate Alzheimer's Detection from Brain MRI Scans

TL;DR

This paper introduces a hybrid CNN-Transformer model called Evan_V2 that significantly improves accuracy in Alzheimer's disease classification from brain MRI scans by combining multiple architectures.

Contribution

The study proposes a novel hybrid ensemble model, Evan_V2, integrating CNN and Transformer outputs, achieving superior performance over individual models in Alzheimer's detection.

Findings

Evan_V2 achieved 99.99% accuracy in four-class AD classification.

ResNet50 attained 98.83% accuracy among CNNs.

ViT reached 95.38% accuracy among Transformer models.

Abstract

Early and accurate classification of Alzheimers disease (AD) from brain MRI scans is essential for timely clinical intervention and improved patient outcomes. This study presents a comprehensive comparative analysis of five CNN architectures (EfficientNetB0, ResNet50, DenseNet201, MobileNetV3, VGG16), five Transformer-based models (ViT, ConvTransformer, PatchTransformer, MLP-Mixer, SimpleTransformer), and a proposed hybrid model named Evan_V2. All models were evaluated on a four-class AD classification task comprising Mild Dementia, Moderate Dementia, Non-Demented, and Very Mild Dementia categories. Experimental findings show that CNN architectures consistently achieved strong performance, with ResNet50 attaining 98.83% accuracy. Transformer models demonstrated competitive generalization capabilities, with ViT achieving the highest accuracy among them at 95.38%. However, individual Transformer variants exhibited greater class-specific instability. The proposed Evan_V2 hybrid model, which integrates outputs from ten CNN and Transformer architectures through feature-level fusion, achieved the best overall performance with 99.99% accuracy, 0.9989 F1-score, and 0.9968 ROC AUC. Confusion matrix analysis further confirmed that Evan_V2 substantially reduced misclassification across all dementia stages, outperforming every standalone model. These findings highlight the potential of hybrid ensemble strategies in producing highly reliable and clinically meaningful diagnostic tools for Alzheimers disease classification.