对比CNN与Transformer在脑瘤检测中的可解释性表现
Explainability of Deep Neural Networks for Brain Tumor Detection
- 用LIME、SHAP等XAI技术分析模型决策依据
- VGG-16和ResNet-50在小数据上优于ViT和EfficientNet
- 浅层CNN更适合小样本医疗图像任务
医学图像分类对辅助临床决策和培训至关重要。尽管卷积神经网络（CNN）长期主导该领域，基于Transformer的模型正受到关注。本研究应用可解释人工智能（XAI）技术评估多种模型在真实医疗数据上的表现，并识别改进方向。比较了VGG-16、ResNet-50、EfficientNetV2L等CNN模型与ViT-Base-16 Transformer模型。结果表明，数据增强影响较小，但超参数调优和先进建模显著提升性能。在小样本条件下，CNN模型（尤其是VGG-16和ResNet-50）表现优于ViT-Base-16和EfficientNetV2L，可能源于数据不足导致的欠拟合。XAI方法如LIME和SHAP进一步显示，性能更优的模型能更准确可视化肿瘤区域。研究建议：在小数据集上，浅层CNN更具有效性，可更好支持医疗决策。
原文摘要 · Abstract (English)
Medical image classification is crucial for supporting healthcare professionals in decision-making and training. While Convolutional Neural Networks (CNNs) have traditionally dominated this field, Transformer-based models are gaining attention. In this study, we apply explainable AI (XAI) techniques to assess the performance of various models on real-world medical data and identify areas for improvement. We compare CNN models such as VGG-16, ResNet-50, and EfficientNetV2L with a Transformer model: ViT-Base-16. Our results show that data augmentation has little impact, but hyperparameter tuning and advanced modeling improve performance. CNNs, particularly VGG-16 and ResNet-50, outperform ViT-Base-16 and EfficientNetV2L, likely due to underfitting from limited data. XAI methods like LIME and SHAP further reveal that better-performing models visualize tumors more effectively. These findings suggest that CNNs with shallower architectures are more effective for small datasets and can support medical decision-making.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。