Artifact-free fat-water separation in Dixon MRI using deep learning

Abstract

Chemical-shift encoded MRI (CSE-MRI) is a widely used technique for the study of body composition and metabolic disorders, where derived fat and water signals enable the quantification of adipose tissue and muscle. The UK Biobank is acquiring whole-body Dixon MRI (a specific implementation of CSE-MRI) for over 100,000 participants. Current processing methods associated with large whole-body volumes are time intensive and prone to artifacts during fat-water separation performed by the scanner, making quantitative analysis challenging. The most common artifacts are fat-water swaps, where the labels are inverted at the voxel level. It is common for researchers to discard swapped data (generally around 10%), which is wasteful and may lead to unintended biases. Given the large number of whole-body Dixon MRI acquisitions in the UK Biobank, thousands of swaps are expected to be present in the fat and water volumes from image reconstruction performed on the scanner. If they go undetected, errors will propagate into processes such as organ segmentation, and dilute the results in population-based analyses. There is a clear need for a robust method to accurately separate fat and water volumes in big data collections like the UK Biobank. We formulate fat-water separation as a style transfer problem, where swap-free fat and water volumes are predicted from the acquired Dixon MRI data using a conditional generative adversarial network, and introduce a new loss function for the generator model. Our method is able to predict highly accurate fat and water volumes free from artifacts in the UK Biobank. We show that our model separates fat and water volumes using either single input (in-phase only) or dual input (in-phase and opposed-phase) data, with the latter producing superior results. Our proposed method enables faster and more accurate downstream analysis of body composition from Dixon MRI in population studies by eliminating the need for visual inspection or discarding data due to fat-water swaps.

Fast online spectral-spatial pulse design for subject-specific fat saturation in cervical spine and foot imaging at 1.5 T

“…Implementing Dixon in routine clinical practice requires individualized adaptations of sequences or protocols, e.g. by adding parallel imaging acceleration techniques [15][16][17]43]. In contrast, the proposed dynamic SPSP method offers a solution with no need for complex sequence adaptations.…”

“…Over the years, more advanced versions have addressed various issues, making fat-water separation appealing for diverse applications [11][12][13][14]. However, challenges such as increased scan time due to multiple echo acquisitions and the complexity of potential phase errors are still areas of ongoing research [15][16][17]. These challenges may currently lead to longer acquisition times or fat-water swaps.…”

Estimation of subvoxel fat infiltration in neurodegenerative muscle disorders using quantitative multi‐T2 analysis

“…It also eliminates B 1 + inhomogeneities as their effect is modeled in the fitting process 14 . Second, Dixon might misclassify water as fat, and vice versa, when their relative fractions are close to 50% 31,32 . This is because the water component decays very quickly relative to the fat, hence even for a relatively high fraction of the water component, its signal intensity would be low and only make a small contribution to the overall acquired signal, leading to water‐fat misclassifications.…”