TY  - JOUR
Y1  - 2024/05/23/
TI  - Training deep learning based dynamic MR image reconstruction using open-source natural videos
AV  - public
N2  - To develop and assess a deep learning (DL) pipeline to learn dynamic MR image reconstruction from publicly available natural videos (Inter4K). Learning was performed for a range of DL architectures (VarNet, 3D UNet, FastDVDNet) and corresponding sampling patterns (Cartesian, radial, spiral) either from true multi-coil cardiac MR data (N = 692) or from synthetic MR data simulated from Inter4K natural videos (N = 588). Real-time undersampled dynamic MR images were reconstructed using DL networks trained with cardiac data and natural videos, and compressed sensing (CS). Differences were assessed in simulations (N = 104 datasets) in terms of MSE, PSNR, and SSIM and prospectively for cardiac cine (short axis, four chambers, N = 20) and speech cine (N = 10) data in terms of subjective image quality ranking, SNR and Edge sharpness. Friedman Chi Square tests with post-hoc Nemenyi analysis were performed to assess statistical significance. In simulated data, DL networks trained with cardiac data outperformed DL networks trained with natural videos, both of which outperformed CS (p < 0.05). However, in prospective experiments DL reconstructions using both training datasets were ranked similarly (and higher than CS) and presented no statistical differences in SNR and Edge Sharpness for most conditions.The developed pipeline enabled learning dynamic MR reconstruction from natural videos preserving DL reconstruction advantages such as high quality fast and ultra-fast reconstructions while overcoming some limitations (data scarcity or sharing). The natural video dataset, code and pre-trained networks are made readily available on github.
IS  - 1
UR  - http://dx.doi.org/10.1038/s41598-024-62294-7
ID  - discovery10196662
EP  - 10
VL  - 14
N1  - © 2024 Springer Nature Limited. This article is licensed under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
A1  - Jaubert, Olivier
A1  - Pascale, Michele
A1  - Montalt-Tordera, Javier
A1  - Akesson, Julius
A1  - Virsinskaite, Ruta
A1  - Knight, Daniel
A1  - Arridge, Simon
A1  - Steeden, Jennifer
A1  - Muthurangu, Vivek
PB  - NATURE PORTFOLIO
JF  - Scientific Reports
KW  - Real-time
KW  -  Dynamic MRI
KW  -  Deep learning
KW  -  Image reconstruction
KW  -  Machine learning
ER  -