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.

翻译：从脑部MRI扫描中对阿尔茨海默病进行早期准确分类，对于及时的临床干预和改善患者预后至关重要。本研究对五种CNN架构（EfficientNetB0、ResNet50、DenseNet201、MobileNetV3、VGG16）、五种基于Transformer的模型（ViT、ConvTransformer、PatchTransformer、MLP-Mixer、SimpleTransformer）以及一个名为Evan_V2的提出的混合模型进行了全面的比较分析。所有模型均在包含轻度痴呆、中度痴呆、非痴呆和极轻度痴呆类别的四分类AD任务上进行评估。实验结果表明，CNN架构始终表现出强大的性能，其中ResNet50达到了98.83%的准确率。Transformer模型展现了有竞争力的泛化能力，其中ViT以95.38%的准确率在其中表现最佳。然而，单个Transformer变体表现出更大的类别特异性不稳定性。所提出的Evan_V2混合模型通过特征级融合整合了十种CNN和Transformer架构的输出，取得了最佳的整体性能，准确率达到99.99%，F1分数为0.9989，ROC AUC为0.9968。混淆矩阵分析进一步证实，Evan_V2显著减少了所有痴呆阶段的误分类，其表现优于每个独立模型。这些发现凸显了混合集成策略在构建高度可靠且具有临床意义的阿尔茨海默病分类诊断工具方面的潜力。