VORTEX: Physics-Driven Data Augmentations Using Consistency Training for Robust Accelerated MRI Reconstruction
Arjun D Desai, Beliz Gunel, Batu Ozturkler, Harris Beg, Shreyas Vasanawala, Brian Hargreaves, Christopher Re, John M. Pauly, Akshay Chaudhari
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 extensive fully-sampled ground truth datasets, 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 to achieve improved data efficiency and robustness to clinically-relevant distribution drifts. Our approach, termed VORTEX, (1) demonstrates strong improvements over supervised baselines with and without data augmentation in robustness to signal-to-noise ratio change and motion corruption in data-limited regimes; (2) considerably outperforms state-of-the-art purely image-based data augmentation techniques and self-supervised reconstruction methods on both in-distribution and out-of-distribution data; and (3) enables composing heterogeneous image-based and physics-driven data augmentations.
Wednesday 6th July
Poster Session 1.2 - onsite 11:00 - 12:00, virtual 15:20 - 16:20 (UTC+2)