Instabilities in Conventional Multi-Coil MRI Reconstruction with Small Adversarial Perturbations

Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akcakaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Although deep learning (DL) has recently received significant attention in accelerated MRI, recent studies suggest that small perturbations may lead to large instabilities in DL-based reconstructions. This has also highlighted concerns for their utility in clinical settings. However, these works focus on single-coil acquisitions, which are not practically relevant. In this work, we investigate how small adversarial perturbations affect multi-coil MRI reconstruction, particularly using conventional non-DL methods. Our results indicate that for multi-coil MRI reconstruction, conventional parallel imaging and multi-coil compressed sensing (CS) methods also exhibit considerable instabilities against small adversarial perturbations. Moreover, for physics-guided DL reconstructions that utilize the forward encoding operator explicitly, such small perturbations predominantly target the linear data-consistency units. These results suggest that at high acceleration rates, adversarial attacks exploit the ill-conditioning of the forward encoding operator.

Original languageEnglish (US)
Title of host publication55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages895-899
Number of pages5
ISBN (Electronic)9781665458283
DOIs
StatePublished - 2021
Event55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021 - Virtual, Pacific Grove, United States
Duration: Oct 31 2021Nov 3 2021

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2021-October
ISSN (Print)1058-6393

Conference

Conference55th Asilomar Conference on Signals, Systems and Computers, ACSSC 2021
Country/TerritoryUnited States
CityVirtual, Pacific Grove
Period10/31/2111/3/21

Bibliographical note

Funding Information:
This work was partially supported by NIH P41EB015894, NIH U01EB025144, NIH P41EB027061, NSF CAREER CCF-1651825.

Publisher Copyright:
© 2021 IEEE.

Center for Magnetic Resonance Research (CMRR) tags

  • IRP

Fingerprint

Dive into the research topics of 'Instabilities in Conventional Multi-Coil MRI Reconstruction with Small Adversarial Perturbations'. Together they form a unique fingerprint.

Cite this