Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM), have become indispensable for visualizing the reasoning process of deep neural networks in medical image analysis. Despite their popularity, the faithfulness and reliability of these heatmap-based explanations remain under scrutiny. This study critically investigates whether Grad-CAM truly represents the internal decision-making of deep models trained for lung cancer image classification. Using the publicly available IQ-OTH/NCCD dataset, we evaluate five representative architectures: ResNet-50, ResNet-101, DenseNet-161, EfficientNet-B0, and ViT-Base-Patch16-224, to explore model-dependent variations in Grad-CAM interpretability. We introduce a quantitative evaluation framework that combines localization accuracy, perturbation-based faithfulness, and explanation consistency to assess Grad-CAM reliability across architectures. Experimental findings reveal that while Grad-CAM effectively highlights salient tumor regions in most convolutional networks, its interpretive fidelity significantly degrades for Vision Transformer models due to non-local attention behavior. Furthermore, cross-model comparisons indicate substantial variability in saliency localization, implying that Grad-CAM explanations may not always correspond to the true diagnostic evidence used by the networks. This work exposes critical limitations of current saliency-based XAI approaches in medical imaging and emphasizes the need for model-aware interpretability methods that are both computationally sound and clinically meaningful. Our findings aim to inspire a more cautious and rigorous adoption of visual explanation tools in medical AI, urging the community to rethink what it truly means to "trust" a model's explanation.

翻译：可解释人工智能（XAI）技术，如梯度加权类激活映射（Grad-CAM），已成为医学影像分析中可视化深度神经网络推理过程不可或缺的工具。尽管这些基于热图的解释方法应用广泛，但其忠实性与可靠性仍备受审视。本研究批判性地探讨了Grad-CAM是否真实反映了用于肺癌图像分类的深度模型的内部决策机制。利用公开可用的IQ-OTH/NCCD数据集，我们评估了五种代表性架构：ResNet-50、ResNet-101、DenseNet-161、EfficientNet-B0和ViT-Base-Patch16-224，以探究Grad-CAM可解释性随模型变化的特性。我们提出了一个结合定位精度、基于扰动的忠实性以及解释一致性的量化评估框架，用以评估Grad-CAM在不同架构间的可靠性。实验结果表明，尽管Grad-CAM在大多数卷积网络中能有效突出显著的肿瘤区域，但由于Vision Transformer模型的非局部注意力机制，其解释保真度显著下降。此外，跨模型比较显示显著性定位存在显著差异，这意味着Grad-CAM的解释可能并不总是与网络实际使用的诊断证据相符。这项工作揭示了当前基于显著性的XAI方法在医学影像中的关键局限性，并强调需要开发兼具计算合理性与临床意义的、具有模型感知能力的可解释性方法。我们的研究旨在促使医学AI领域更谨慎、更严格地采用可视化解释工具，并推动学界重新思考“信任”模型解释的真正含义。