Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI

TL;DR

This paper introduces a neural network-based method using SIRENs for enhancing 4D flow MRI data by providing super-resolution and denoising, leading to more accurate blood flow velocity measurements.

Contribution

The study demonstrates the effectiveness of SIRENs in improving 4D flow MRI data quality, outperforming existing methods in super-resolution and denoising tasks.

Findings

Outperformed state-of-the-art techniques in super-resolution and denoising.

Effective on both synthetic and real clinical data.

Quick and straightforward to implement.

Abstract

4D flow MRI is a non-invasive imaging method that can measure blood flow velocities over time. However, the velocity fields detected by this technique have limitations due to low resolution and measurement noise. Coordinate-based neural networks have been researched to improve accuracy, with SIRENs being suitable for super-resolution tasks. Our study investigates SIRENs for time-varying 3-directional velocity fields measured in the aorta by 4D flow MRI, achieving denoising and super-resolution. We trained our method on voxel coordinates and benchmarked our approach using synthetic measurements and a real 4D flow MRI scan. Our optimized SIREN architecture outperformed state-of-the-art techniques, producing denoised and super-resolved velocity fields from clinical data. Our approach is quick to execute and straightforward to implement for novel cases, achieving 4D super-resolution.