MedLIME：面向医学显著性解释的分布对齐与证据支持框架
MedLIME: A Distribution-Aligned and Evidence-Supported Framework for Medical Saliency Explanations
在无法访问模型内部的白盒条件下，用生成式重建替代 LIME 的随机扰动、并用监督式测试时自适应校准掩码分布，可迁移到任意黑盒医学影像模型的病灶定位与显著性解释评估（AUPRC）。
原文依据 a novel, model-agnostic explanation framework designed to enhance the robustness and fidelity of saliency maps for medical imaging abnormality localization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于显著性的可解释性方法被广泛用于解释医学影像中的深度学习模型，然而现有许多方法依赖对模型的白盒访问，而由于隐私方面的顾虑，这种访问并不总是可行。本文提出 MedLIME，一种新颖的、模型无关的解释框架，旨在提升医学影像异常定位中显著性图的鲁棒性与保真度。MedLIME 在局部可解释模型无关解释（LIME）范式的基础上，集成了三个关键组件：(1) 生成式掩码（GM），(2) 监督式测试时自适应（STT），以及 (3) 基于证据的正则化（EBR），以提升 LIME 的显著性图生成精度。在多个医学数据集、三种模型架构上的大量实验表明，以 AUPRC 为度量，MedLIME 在异常定位上持续优于基于梯度和基于扰动的基线方法。研究结果表明，引入生成式重建、自适应扰动与数据驱动的正则化能够提升医学影像模型的可靠性与可解释性。
英文原文摘要 1160 字符
Saliency-based explainability methods are widely used to interpret deep learning models in medical imaging, yet many existing approaches rely on white box access of models, which is not always possible due to privacy concerns. In this work, we introduce **MedLIME**, a novel, model-agnostic explanation framework designed to enhance the robustness and fidelity of saliency maps for medical imaging abnormality localization. Building upon the Local Interpretable Model-agnostic Explanations (LIME) paradigm, MedLIME integrates three key components: (1) **Generative Masking** (GM), (2) **Supervised Test-Time Adaptation** (STT) and (3) a **Evidence-based Regularization** (EBR) to improve the saliency map generation accuracy of LIME. Extensive experiments on multiple medical datasets, across three model architectures demonstrate that MedLIME consistently outperforms gradient-based and perturbation-based baselines in abnormality localization as measured by AUPRC. Our results highlight that incorporating generative reconstruction, adaptive perturbation and data-driven regularization improves the reliability and interpretability of medical imaging models.