Abstract
4D-flow magnetic resonance imaging (MRI) is an emerging imaging technique where spatiotemporal 3D blood velocity can be captured with full volumetric coverage in a single non-invasive examination. This enables qualitative and quantitative analysis of hemodynamic flow parameters of the heart and great vessels. An increase in the image resolution would provide more accuracy and allow better assessment of the blood flow, especially for patients with abnormal flows. However, this must be balanced with increasing imaging time. The recent success of deep learning in generating super resolution images shows promise for implementation in medical images. We utilized computational fluid dynamics simulations to generate fluid flow simulations and represent them as synthetic 4D flow MRI data. We built our training dataset to mimic actual 4D flow MRI data with its corresponding noise distribution. Our novel 4DFlowNet network was trained on this synthetic 4D flow data and was capable in producing noise-free super resolution 4D flow phase images with upsample factor of 2. We also tested the 4DFlowNet in actual 4D flow MR images of a phantom and normal volunteer data, and demonstrated comparable results with the actual flow rate measurements giving an absolute relative error of 0.6 to 5.8% and 1.1 to 3.8% in the phantom data and normal volunteer data, respectively.
Highlights
Cardiovascular magnetic resonance imaging (MRI) is a rapidly advancing non-invasive quantitative imaging method which enables precise evaluation of heart function
To validate the method and test whether this mapping is applicable to actual 4D flow Magnetic Resonance (MR) images, we evaluated our method with both synthetic and in vitro 4D flow MRI data in a flow phantom imaged at two resolutions, as well as an in-vivo scan of a normal volunteer
We have developed 4DFlowNet, a deep super resolution (SR) residual network to increase the resolution of 4D flow MRI by using computational fluid dynamics as a proxy to generate training data
Summary
Cardiovascular magnetic resonance imaging (MRI) is a rapidly advancing non-invasive quantitative imaging method which enables precise evaluation of heart function. While being able to image the time-varying cardiac anatomy with high contrast, it can acquire images of intravascular hemodynamics with blood velocity encoded in the phase of the MRI signal. 4D Flow provides a promising clinical utility to assess the hemodynamics of the blood inside the heart chambers and the great vessels for patients with cardiovascular disease [1,2,3,4,5]. 4D flow MRI provides complete coverage of blood flow inside the cardiovascular system, it still has limitations associated with signal-to-noise ratio (SNR), velocity encoding (VENC), and spatiotemporal resolution [6]. As the current resolution for 4D flow MRI is limited, some of the hemodynamic parameters, such as wall shear stress, cannot yet be calculated accurately. In keeping with the ability of CFD to accurately model blood flow with (theoretically) unlimited spatiotemporal resolution, we took advantage of this to generate high resolution (HR) flow images, and model it as an image super resolution (SR) problem
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
