On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929398809100288 |
|---|---|
| author | Han, Tianyu Nebelung, Sven Khader, Firas Kather, Jakob Nikolas Truhn, Daniel |
| author_facet | Han, Tianyu Nebelung, Sven Khader, Firas Kather, Jakob Nikolas Truhn, Daniel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16983 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction Han, Tianyu Nebelung, Sven Khader, Firas Kather, Jakob Nikolas Truhn, Daniel Image and Video Processing Artificial Intelligence Machine Learning 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. |
| title | On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction |
| topic | Image and Video Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.16983 |