Fat–water MRI separation using deep complex convolution network
- 3 July 2025
- journal article
- research article
- Published by Springer Nature in Magnetic Resonance Materials in Physics, Biology and Medicine
- Vol. 38 (6) , 959-977
Abstract
Objective Deep complex convolutional networks (DCCNs) utilize complex-valued convolutions and can process complex-valued MRI signals directly without splitting them into two real-valued magnitude and phase components. The performance of DCCN and real-valued U-Net is thoroughly investigated in the physics-informed subject-specific ad-hoc reconstruction method for fat–water separation and is compared against a widely used reference approach. Materials and methods A comprehensive test dataset (n = 33) was used for performance analysis. The 2012 ISMRM fat–water separation workshop dataset containing 28 batches of multi-echo MRIs with 3–15 echoes from the abdomen, thigh, knee, and phantoms, acquired with 1.5 T and 3 T scanners were used. Additionally, five MAFLD patients multi-echo MRIs acquired from our clinical radiology department were also used. Results The quantitative results demonstrated that DCCN produced fat–water maps with better normalized RMS error and structural similarity index with the reference approach, compared to real-valued U-Nets in the ad-hoc reconstruction method for fat–water separation. The DCCN achieved an overall average SSIM of 0.847 ± 0.069 and 0.861 ± 0.078 in generating fat and water maps, respectively, in contrast the U-Net achieved only 0.653 ± 0.166 and 0.729 ± 0.134. The average liver PDFF from DCCN achieved a correlation coefficient R of 0.847 with the reference approach.Keywords
This publication has 34 references indexed in Scilit:
- Water–fat separation and parameter mapping in cardiac MRI via deep learning with a convolutional neural networkJournal of Magnetic Resonance Imaging, 2019
- Chemical shift encoding‐based water–fat separation methodsJournal of Magnetic Resonance Imaging, 2014
- Quantitative assessment of liver fat with magnetic resonance imaging and spectroscopyJournal of Magnetic Resonance Imaging, 2011
- Combination of complex‐based and magnitude‐based multiecho water‐fat separation for accurate quantification of fat‐fractionMagnetic Resonance in Medicine, 2011
- Robust water/fat separation in the presence of large field inhomogeneities using a graph cut algorithmMagnetic Resonance in Medicine, 2009
- Multiecho water‐fat separation and simultaneous R estimation with multifrequency fat spectrum modelingMagnetic Resonance in Medicine, 2008
- Multiecho reconstruction for simultaneous water‐fat decomposition and T2* estimationJournal of Magnetic Resonance Imaging, 2007
- Field map estimation with a region growing scheme for iterative 3‐point water‐fat decompositionMagnetic Resonance in Medicine, 2005
- Multicoil Dixon chemical species separation with an iterative least‐squares estimation methodMagnetic Resonance in Medicine, 2003
- High‐resolution human in vivo spectroscopic imaging using echo‐ time encoding techniqueMagnetic Resonance in Medicine, 1986