对比7种解释方法，揭示皮肤病变模型的决策盲区。
Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers
- 对比7种解释方法，分像素归因与高层概念两类
- 发现现有方法能暴露模型偏见但缺乏全面性
- 适合关注AI医疗可解释性的临床研究者
深度学习在计算机视觉任务中表现卓越，医疗领域也不例外。然而，深度学习模型的决策过程缺乏直观解释。仅靠高准确率不足以支撑皮肤癌预测。理解模型行为对临床应用和可靠结果至关重要。本文提出皮肤病变模型解释应满足的标准，分析了七种方法：四种基于像素归因（Grad-CAM、Score-CAM、LIME、SHAP），三种基于高层概念（ACE、ICE、CME），均针对在国际皮肤影像协作档案（ISIC Archive）上训练的深度神经网络。结果表明，尽管这些方法能揭示模型偏差，但解释的全面性仍有提升空间，以实现皮肤病变模型的真正透明。
原文摘要 · Abstract (English)
Deep Learning has shown outstanding results in computer vision tasks; healthcare is no exception. However, there is no straightforward way to expose the decision-making process of DL models. Good accuracy is not enough for skin cancer predictions. Understanding the model's behavior is crucial for clinical application and reliable outcomes. In this work, we identify desiderata for explanations in skin-lesion models. We analyzed seven methods, four based on pixel-attribution (Grad-CAM, Score-CAM, LIME, SHAP) and three on high-level concepts (ACE, ICE, CME), for a deep neural network trained on the International Skin Imaging Collaboration Archive. Our findings indicate that while these techniques reveal biases, there is room for improving the comprehensiveness of explanations to achieve transparency in skin-lesion models.
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。