# On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction

arXiv: https://arxiv.org/abs/2406.16983 · HTML: https://mlsanity.com/paper/2406.16983/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 23 Jun 2024.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [ResUNet++: An Advanced Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1911.07067/) (2019)
- [Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1712.01751/) (2017)
- [Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge](https://mlsanity.com/paper/2001.02518/) (2020)
- [Measuring Robustness in Deep Learning Based Compressive Sensing](https://mlsanity.com/paper/2102.06103/) (2021)
- [Invert to Learn to Invert](https://mlsanity.com/paper/1911.10914/) (2019)
- [i-RIM applied to the fastMRI challenge](https://mlsanity.com/paper/1910.08952/) (2019)
- [Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization](https://mlsanity.com/paper/2011.13011/) (2020)

## Built on by (most cited first, 1 of 1)

- [Training-Free Adversarial Robustness in Computational MRI](https://mlsanity.com/paper/2501.01908/) (2025)

## Abstract (arXiv)

Denoising diffusion models offer a promising approach to accelerating magnetic resonance imaging (MRI) and producing diagnostic-level images in an unsupervised manner. However, our study demonstrates that even tiny worst-case potential perturbations transferred from a surrogate model can cause these models to generate fake tissue structures that may mislead clinicians. The transferability of such worst-case perturbations indicates that the robustness of image reconstruction may be compromised due to MR system imperfections or other sources of noise. Moreover, at larger perturbation strengths, diffusion models exhibit Gaussian noise-like artifacts that are distinct from those observed in supervised models and are more challenging to detect. Our results highlight the vulnerability of current state-of-the-art diffusion-based reconstruction models to possible worst-case perturbations and underscore the need for further research to improve their robustness and reliability in clinical settings.