Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alkhouri, Ismail, Liang, Shijun, Wang, Rongrong, Qu, Qing, Ravishankar, Saiprasad
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912744313192448
author Alkhouri, Ismail
Liang, Shijun
Wang, Rongrong
Qu, Qing
Ravishankar, Saiprasad
author_facet Alkhouri, Ismail
Liang, Shijun
Wang, Rongrong
Qu, Qing
Ravishankar, Saiprasad
contents Deep learning (DL) techniques have been extensively employed in magnetic resonance imaging (MRI) reconstruction, delivering notable performance enhancements over traditional non-DL methods. Nonetheless, recent studies have identified vulnerabilities in these models during testing, namely, their susceptibility to (\textit{i}) worst-case measurement perturbations and to (\textit{ii}) variations in training/testing settings like acceleration factors and k-space sampling locations. This paper addresses the robustness challenges by leveraging diffusion models. In particular, we present a robustification strategy that improves the resilience of DL-based MRI reconstruction methods by utilizing pretrained diffusion models as noise purifiers. In contrast to conventional robustification methods for DL-based MRI reconstruction, such as adversarial training (AT), our proposed approach eliminates the need to tackle a minimax optimization problem. It only necessitates fine-tuning on purified examples. Our experimental results highlight the efficacy of our approach in mitigating the aforementioned instabilities when compared to leading robustification approaches for deep MRI reconstruction, including AT and randomized smoothing.
format Preprint
id arxiv_https___arxiv_org_abs_2309_05794
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
Alkhouri, Ismail
Liang, Shijun
Wang, Rongrong
Qu, Qing
Ravishankar, Saiprasad
Image and Video Processing
Deep learning (DL) techniques have been extensively employed in magnetic resonance imaging (MRI) reconstruction, delivering notable performance enhancements over traditional non-DL methods. Nonetheless, recent studies have identified vulnerabilities in these models during testing, namely, their susceptibility to (\textit{i}) worst-case measurement perturbations and to (\textit{ii}) variations in training/testing settings like acceleration factors and k-space sampling locations. This paper addresses the robustness challenges by leveraging diffusion models. In particular, we present a robustification strategy that improves the resilience of DL-based MRI reconstruction methods by utilizing pretrained diffusion models as noise purifiers. In contrast to conventional robustification methods for DL-based MRI reconstruction, such as adversarial training (AT), our proposed approach eliminates the need to tackle a minimax optimization problem. It only necessitates fine-tuning on purified examples. Our experimental results highlight the efficacy of our approach in mitigating the aforementioned instabilities when compared to leading robustification approaches for deep MRI reconstruction, including AT and randomized smoothing.
title Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
topic Image and Video Processing
url https://arxiv.org/abs/2309.05794