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

arXiv: https://arxiv.org/abs/2602.09781 · HTML: https://mlsanity.com/paper/2602.09781/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 11 of 11)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis](https://mlsanity.com/paper/2305.18453/) (2023)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [VALD-MD: Visual Attribution via Latent Diffusion for Medical Diagnostics](https://mlsanity.com/paper/2401.01414/) (2024)
- [Enhanced Prototypical Part Network (EPPNet) For Explainable Image Classification Via Prototypes](https://mlsanity.com/paper/2408.04606/) (2024)
- [Mediffusion: Joint Diffusion for Self-Explainable Semi-Supervised Classification and Medical Image Generation](https://mlsanity.com/paper/2411.09434/) (2024)

## Abstract (arXiv)

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.