CaltechAUTHORS
  A Caltech Library Service

VORTEX: Physics-Driven Data Augmentations for Consistency Training for Robust Accelerated MRI Reconstruction

Desai, Arjun D. and Gunel, Beliz and Ozturkler, Batu M. and Beg, Harris and Vasanawala, Shreyas and Hargreaves, Brian and Ré, Christopher and Pauly, John M. and Chaudhari, Akshay S. (2021) VORTEX: Physics-Driven Data Augmentations for Consistency Training for Robust Accelerated MRI Reconstruction. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20211108-011022956

[img] PDF - Submitted Version
See Usage Policy.

7MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20211108-011022956

Abstract

Deep neural networks have enabled improved image quality and fast inference times for various inverse problems, including accelerated magnetic resonance imaging (MRI) reconstruction. However, such models require large amounts of fully-sampled ground truth data, which are difficult to curate and are sensitive to distribution drifts. In this work, we propose applying physics-driven data augmentations for consistency training that leverage our domain knowledge of the forward MRI data acquisition process and MRI physics for improved data efficiency and robustness to clinically-relevant distribution drifts. Our approach, termed VORTEX (1) demonstrates strong improvements over supervised baselines with and without augmentation in robustness to signal-to-noise ratio change and motion corruption in data-limited regimes; (2) considerably outperforms state-of-the-art data augmentation techniques that are purely image-based on both in-distribution and out-of-distribution data; and (3) enables composing heterogeneous image-based and physics-driven augmentations.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/2111.02549arXivDiscussion Paper
Additional Information:This work was supported by R01 AR063643, R01 EB002524, R01 EB009690, R01 EB026136, K24 AR062068, and P41 EB015891 from the NIH; the Precision Health and Integrated Diagnostics Seed Grant from Stanford University; DOD – National Science and Engineering Graduate Fellowship (ARO); National Science Foundation (GRFP-DGE 1656518, CCF1763315, CCF1563078); Stanford Artificial Intelligence in Medicine and Imaging GCP grant; Stanford Human-Centered Artificial Intelligence GCP grant; GE Healthcare and Philips.
Funders:
Funding AgencyGrant Number
NIHR01 AR063643
NIHR01 EB002524
NIHR01 EB009690
NIHR01 EB026136
NIHK24 AR062068
NIHP41 EB015891
Stanford UniversityUNSPECIFIED
National Defense Science and Engineering Graduate (NDSEG) FellowshipUNSPECIFIED
NSF Graduate Research FellowshipDGE-1656518
NSFCCF-1763315
NSFCCF-1563078
GE HealthcareUNSPECIFIED
PhilipsUNSPECIFIED
Record Number:CaltechAUTHORS:20211108-011022956
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20211108-011022956
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:111784
Collection:CaltechAUTHORS
Deposited By: Harris Beg
Deposited On:09 Nov 2021 21:17
Last Modified:09 Nov 2021 21:17

Repository Staff Only: item control page