Chi Zhang1,2, Jinghan Jia3, Burhaneddin Yaman1,2, Steen Moeller2, Sijia Liu4, Mingyi Hong1, and Mehmet Akçakaya1,2
1Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States, 2Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States, 3University of Florida, Gainesville, FL, United States, 4MIT-IBM Watson AI Lab, IBM Research, Cambridge, MA, United States
1Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, United States, 2Center for Magnetic Resonance Research, University of Minnesota, Minneapolis, MN, United States, 3University of Florida, Gainesville, FL, United States, 4MIT-IBM Watson AI Lab, IBM Research, Cambridge, MA, United States
Conventional multi-coil
reconstructions are also susceptible to large instabilities from small
adversarial perturbations. It
is worthwhile to interpret the instabilities of DL methods within this broader
context for the practical multi-coil setting.
Figure
2. Reconstruction results for uniform undersampling without (top row) and with (bottom row)
attack. The small perturbation causes no visual difference in the fully-sampled
image or the zero-filled image. The reconstructions without attack show some
residual aliasing due to the R=4 acceleration. Both CG-SENSE and GRAPPA visibly
fail with the small perturbation attack.
Figure
3. Reconstruction results for
random undersampling without (top row) and with (bottom row) attack. The small
perturbation leads to no visual change in the fully-sampled or zero-filled
image. For the input without attack, CG-SENSE has visible and multi-coil CS has
subtle aliasing artifacts at R=4. For the attack input, both these
reconstructions fail although they are run with the exact same parameters as
the non-attack case.