用梯度注意力图检测医学影像模型可靠性，防止误判。
Gradient Attention Map Based Verification of Deep Convolutional Neural Networks with Application to X-ray Image Datasets
- 通过梯度注意力图分析模型关注区域，对比相似性指标
- 在多个数据集上识别出不适用的模型与异常输入
- 适合医疗影像领域需高可靠性的深度学习应用
深度学习在医学影像（如正畸和骨骼成熟度评估）中潜力巨大。但将模型应用于训练数据以外的数据可能导致不可靠预测，影响患者安全。为此，我们提出一个综合验证框架，通过多种互补策略评估模型适用性。首先，引入基于梯度注意力图（GAM）的方法，利用Grad-CAM分析注意力模式，并通过交并比（IoU）、Dice相似性、SSIM、余弦相似性、皮尔逊相关系数、KL散度和Wasserstein距离等指标进行比较。其次，将验证扩展至早期卷积特征图，捕捉仅靠注意力无法发现的结构错位。最后，在分类模型中引入额外的“垃圾类”以显式拒绝分布外输入。实验表明，这些方法能有效识别不合适的模型和输入，提升医学影像中深度学习部署的安全性与可靠性。
原文摘要 · Abstract (English)
Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact patient care. To address this, we propose a comprehensive verification framework that evaluates model suitability through multiple complementary strategies. First, we introduce a Gradient Attention Map (GAM)-based approach that analyzes attention patterns using Grad-CAM and compares them via similarity metrics such as IoU, Dice Similarity, SSIM, Cosine Similarity, Pearson Correlation, KL Divergence, and Wasserstein Distance. Second, we extend verification to early convolutional feature maps, capturing structural mis-alignments missed by attention alone. Finally, we incorporate an additional garbage class into the classification model to explicitly reject out-of-distribution inputs. Experimental results demonstrate that these combined methods effectively identify unsuitable models and inputs, promoting safer and more reliable deployment of deep learning in medical imaging.
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。