Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis

arXiv:2602.09781v2 Announce Type: replace-cross Abstract: 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.

Related

• CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder
• PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems
• MSG Score: Automated Video Verification for Reliable Multi-Scene Generation
• Surrogate modeling for interpreting black-box LLMs in medical predictions

Source: arXiv cs.AI | 2026-04-23