Recurrent neural network improves 4D flow MRI spatial and temporal resolution
CURRENT: A Recurrent Neural Network for Concurrent Spatial and Temporal Super-Resolution of 4D Flow MRI
Computer Vision and Pattern Recognition
Summary
4D flow MRI is a way to see how blood moves through the aorta, but the images can be blurry or slow. The authors developed CURRENT, a deep learning model that sharpens these images both in space and time using just one system. They trained CURRENT on computer-simulated data mixed with real MRI backgrounds, then tested it against other methods and showed it gives clearer images and more accurate pressure estimates in the heart. Importantly, even though it was trained on synthetic data, it works well on real patient scans.
What this means in practice
- •For medical image analysts: Enhance the quality and accuracy of blood flow MRI scans to support better diagnosis of cardiovascular conditions.
- •For medical device manufacturers: Integrate a single network for spatial and temporal resolution improvement in 4D flow MRI hardware to provide faster and more detailed blood flow imaging tools.$Commercial implications: Enables improved MRI devices with advanced flow imaging capabilities valuable to hospitals and clinics.
Authors
Luuk Jacobs, Pietro Dirix, Sebastian Kozerke
Abstract
Objective: To improve the spatial and temporal resolution of aortic 4D flow MRI through a unified deep learning framework for post-acquisition super-resolution (SR) of reconstructed velocity vector fields. Methods: We propose CURRENT, a recurrent neural network that performs spatial and temporal SR with a single network architecture. Supervised training was conducted using paired low- and high-resolution datasets generated by embedding computational fluid dynamics simulations of aortic flow into in vivo thoracic MRI backgrounds, followed by controlled spatial and temporal downsampling. CURRENT was evaluated for two-fold spatial and temporal SR against 4DFlowNet and for two-fold spatiotemporal SR against sequential spatial and temporal SR pipelines based on 4DFlowNet. Image-based and k-space-based quantitative metrics were considered and conventional interpolation were used as baselines. In addition, the impact of CURRENT's spatiotemporal SR on physics-informed relative pressure estimation was assessed. Finally, the ability of CURRENT to generalize from synthetic training data to in vivo acquisitions was investigated. Results: CURRENT achieved superior spatial SR performance and comparable temporal SR performance to dedicated 4DFlowNet models while providing a unified solution for both tasks. Simultaneous spatiotemporal SR using CURRENT yielded more accurate relative pressure estimates than either spatial or temporal SR alone and outperformed sequential 4DFlowNet-based spatial and temporal SR approaches. Furthermore, the proposed model demonstrated promising generalization to in vivo 4D flow MRI data despite being trained exclusively on synthetic datasets. Conclusion: CURRENT provides a unified framework for spatial and temporal SR of 4D flow MRI. The proposed approach has the potential to enhance physics-based analysis and broaden the applicability of accelerated 4D flow MRI.