通过可信度分析，让扩散模型生成MRI的决策过程更透明。
Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis
- 用原型方法追踪生成图像与训练数据的关系。
- EPPNet可信度达0.1534，是表现最好的解释方法。
- 适合关注医疗AI可解释性与安全性的研究者。
本研究探讨生成式扩散模型在医学影像领域的可解释性，聚焦磁共振成像（MRI）合成任务。尽管扩散模型在生成逼真医学图像方面表现优异，但其内部决策机制仍不透明。本文提出一种基于可信度的可解释性框架，分析原型类方法如ProtoPNet（PPNet）、增强型ProtoPNet（EPPNet）和ProtoPool如何关联生成图像与训练特征。研究重点在于通过扩散模型去噪轨迹理解图像生成逻辑，并结合可信度分析进行原型可解释性评估。实验表明，EPPNet在可信度评分上达到最高值0.1534，提供更可靠的生成过程洞察。结果表明，通过可信度驱动的解释方法，可显著提升扩散模型的透明度与可信度，推动生成式AI在医疗应用中的安全与可解释性发展。
原文摘要 · Abstract (English)
This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance imaging (MRI) synthesis. Although diffusion models have shown strong performance in generating realistic medical images, their internal decision making process remains largely opaque. We present a faithfulness-based explainability framework that analyzes how prototype-based explainability methods like ProtoPNet (PPNet), Enhanced ProtoPNet (EPPNet), and ProtoPool can link the relationship between generated and training features. Our study focuses on understanding the reasoning behind image formation through denoising trajectory of diffusion model and subsequently prototype explainability with faithfulness analysis. Experimental analysis shows that EPPNet achieves the highest faithfulness (with score 0.1534), offering more reliable insights, and explainability into the generative process. The results highlight that diffusion models can be made more transparent and trustworthy through faithfulness-based explanations, contributing to safer and more interpretable applications of generative AI in healthcare.
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。