paper-with-me

Papers

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

2026-02-10 · Surjo Dey, Pallabi Saikia 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.

📄 PDF Abstract BibTeX arXiv:2602.09781

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Evaluating ChatGPT on Medical Information Extraction Tasks: Performance, Explainability and Beyond

2026-01-29 · Liz Li, Wei Zhu arxiv

Large Language Models (LLMs) like ChatGPT have demonstrated amazing capabilities in comprehending user intents and generate reasonable and useful responses. Beside their ability to chat, their capabilities in various nat…

Information Extraction

Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI

2025-07-25 · Niklas Bubeck, Yundi Zhang, Suprosanna Shit, Daniel Rueckert 외 arxiv

In medical imaging, generative models are increasingly relied upon for two distinct but equally critical tasks: reconstruction, where the goal is to restore medical imaging (usually inverse problems like inpainting or su…

Image InpaintingImage Generation

Cycle Diffusion Model for Counterfactual Image Generation

2025-09-29 · Fangrui Huang, Alan Wang, Binxu Li, Bailey Trang 외 arxiv

Deep generative models have demonstrated remarkable success in medical image synthesis. However, ensuring conditioning faithfulness and high-quality synthetic images for direct or counterfactual generation remains a chal…

Medical Image GenerationData Augmentation

LCE: A Framework for Explainability of DNNs for Ultrasound Image Based on Concept Discovery

2024-08-19 · Weiji Kong, Xun Gong, Juan Wang

Explaining the decisions of Deep Neural Networks (DNNs) for medical images has become increasingly important. Existing attribution methods have difficulty explaining the meaning of pixels while existing concept-based met…

Diagnostic

Towards Faithful Model Explanation in NLP: A Survey

2022-09-22 · Qing Lyu, Marianna Apidianaki, Chris Callison-Burch

End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model explainability in recent years. One desideratum of model explanati…

counterfactualmodelSurvey