SRflow: Deep learning based super-resolution of 4D-flow MRI data
Authors:
Open Access
- 12 August 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 5, 928181
Abstract
Exploiting 4D-flow magnetic resonance imaging (MRI) data to quantify hemodynamics requires an adequate spatio-temporal vector field resolution at a low noise level. To address this challenge, we provide a learned solution to super-resolve in vivo 4D-flow MRI data at a post-processing level. We propose a deep convolutional neural network (CNN) that learns the inter-scale relationship of the velocity vector map and leverages an efficient residual learning scheme to make it computationally feasible. A novel, direction-sensitive, and robust loss function is crucial to learning vector-field data. We present a detailed comparative study between the proposed super-resolution and the conventional cubic B-spline based vector-field super-resolution. Our method improves the peak-velocity to noise ratio of the flow field by 10 and 30% for in vivo cardiovascular and cerebrovascular data, respectively, for 4 × super-resolution over the state-of-the-art cubic B-spline. Significantly, our method offers 10x faster inference over the cubic B-spline. The proposed approach for super-resolution of 4D-flow data would potentially improve the subsequent calculation of hemodynamic quantities.Keywords
Funding Information
- H2020 Marie Sklodowska-Curie Actions (76514)
This publication has 42 references indexed in Scilit:
- Pulse wave velocity with 4D flow MRI: Systematic differences and age-related regional vascular stiffnessMagnetic Resonance Imaging, 2014
- Robust 4D flow denoising using divergence‐free wavelet transformMagnetic Resonance in Medicine, 2014
- Quantifying the Large-Scale Hemodynamics of Intracranial AneurysmsAmerican Journal of Neuroradiology, 2013
- 4D flow MRIJournal of Magnetic Resonance Imaging, 2012
- Assessment of the accuracy of MRI wall shear stress estimation using numerical simulationsJournal of Magnetic Resonance Imaging, 2012
- Association of Hemodynamic Characteristics and Cerebral Aneurysm RuptureAmerican Journal of Neuroradiology, 2010
- Improved SNR in phase contrast velocimetry with five‐point balanced flow encodingMagnetic Resonance in Medicine, 2010
- Parallel MRI with extended and averaged GRAPPA kernels (PEAK‐GRAPPA): Optimized spatiotemporal dynamic imagingJournal of Magnetic Resonance Imaging, 2008
- Quantitative 2D and 3D phase contrast MRI: Optimized analysis of blood flow and vessel wall parametersMagnetic Resonance in Medicine, 2008
- Dynamic autocalibrated parallel imaging using temporal GRAPPA (TGRAPPA)Magnetic Resonance in Medicine, 2005