Full-Range Liver Fat Fraction Estimation in Magnitude MRI Using a Signal Shape Descriptor

Current methods for estimation of proton density fat fraction (PDFF) of the liver using magnitude magnetic resonance (MR) imaging face the challenge of correctly estimating it when fat is the dominant molecule; i.e., PDFF is more than 50%. Therefore, the accuracy of the methods is limited to half-range operation. We introduce a method based on neural networks for regression capable of estimating over the full range of fat fractions. We built a neural network based on the angles and distances between the data in the discrete MR signal (ADALIFE), using these as features associated with different PDFFs and as input for the network. Tests were performed using ADALIFE and Multi-interference, a state-of-the-art method to estimate PDFFs, with simulated signals at various signal-to-noise (SNR) values. Results were compared in order to verify repeatability and agreement using Bland-Altman and REC curves. Results for Multi-interference were similar to its in vivo literature, showing the relevance of a simulation. ADALIFE was able to correctly estimate fat fractions up to 100%, breaking the current paradigm for full-range estimation using only offline postprocessing. Within half range, our method outperformed Multi-interference in repeatability and agreement, with narrower limits of agreement and lower expected error at any SNR.

[1]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[2]  W. T. Dixon.  Simple proton spectroscopic imaging. , 1984, Radiology.

[3]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[4]  L. Lin,et al.  A concordance correlation coefficient to evaluate reproducibility. , 1989, Biometrics.

[5]  H. Gudbjartsson,et al.  The rician distribution of noisy mri data , 1995, Magnetic resonance in medicine.

[6]  C. Tiribelli,et al.  Proton MR spectroscopy in quantitative in vivo determination of fat content in human liver steatosis , 1995, Journal of magnetic resonance imaging : JMRI.

[7]  Jinbo Bi,et al.  Regression Error Characteristic Curves , 2003, ICML.

[8]  A. ADoefaa,et al.  ? ? ? ? f ? ? ? ? ? , 2003 .

[9]  S. Grundy,et al.  Magnetic resonance spectroscopy to measure hepatic triglyceride content: prevalence of hepatic steatosis in the general population. , 2005, American journal of physiology. Endocrinology and metabolism.

[10]  Ahmet Alkan,et al.  Automatic seizure detection in EEG using logistic regression and artificial neural network , 2005, Journal of Neuroscience Methods.

[11]  H. Hussain,et al.  Hepatic fat fraction: MR imaging for quantitative measurement and display--early experience. , 2005, Radiology.

[12]  S. Reeder,et al.  Fat quantification with IDEAL gradient echo imaging: Correction of bias from T1 and noise , 2007, Magnetic resonance in medicine.

[13]  S. Reeder,et al.  Noise considerations of three-point water-fat separation imaging methods. , 2008, Medical physics.

[14]  C. Sirlin,et al.  Relaxation effects in the quantification of fat using gradient echo imaging. , 2008, Magnetic resonance imaging.

[15]  J. Krouwer.  Why Bland–Altman plots should use X, not (Y+X)/2 when X is a reference method , 2008, Statistics in medicine.

[16]  A. Gamst,et al.  Nonalcoholic fatty liver disease: diagnostic and fat-grading accuracy of low-flip-angle multiecho gradient-recalled-echo MR imaging at 1.5 T. , 2009, Radiology.

[17]  J. Cercueil,et al.  Mapping of liver fat with triple-echo gradient echo imaging: validation against 3.0-T proton MR spectroscopy , 2009, European Radiology.

[18]  J. Cercueil,et al.  Quantification of liver fat content: comparison of triple-echo chemical shift gradient-echo imaging and in vivo proton MR spectroscopy. , 2009, Radiology.

[19]  P. Kellman,et al.  Chemical shift–based water/fat separation: A comparison of signal models , 2010, Magnetic resonance in medicine.

[20]  C. Sirlin,et al.  In vivo characterization of the liver fat 1H MR spectrum , 2011, NMR in biomedicine.

[21]  S. Horgan,et al.  Estimation of hepatic proton-density fat fraction by using MR imaging at 3.0 T. , 2011, Radiology.

[22]  S. Reeder,et al.  Addressing phase errors in fat‐water imaging using a mixed magnitude/complex fitting method , 2012, Magnetic resonance in medicine.

[23]  F. F. Paiva,et al.  Is MR Spectroscopy Really the Best MR-Based Method for the Evaluation of Fatty Liver in Diabetic Patients in Clinical Practice? , 2014, PloS one.

[24]  S. Reeder,et al.  Quantitative chemical shift‐encoded MRI is an accurate method to quantify hepatic steatosis , 2014, Journal of magnetic resonance imaging : JMRI.

[25]  I. Pedrosa,et al.  Quantitative R2* MRI of the liver with rician noise models for evaluation of hepatic iron overload: Simulation, phantom, and early clinical experience , 2015, Journal of magnetic resonance imaging : JMRI.

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  L. Henry,et al.  Global epidemiology of nonalcoholic fatty liver disease—Meta‐analytic assessment of prevalence, incidence, and outcomes , 2016, Hepatology.

[28]  S. Reeder,et al.  Multisite, multivendor validation of the accuracy and reproducibility of proton‐density fat‐fraction quantification at 1.5T and 3T using a fat–water phantom , 2017, Magnetic resonance in medicine.

[29]  H. Te,et al.  Prevalence of non-alcoholic fatty liver disease and risk factors for advanced fibrosis and mortality in the United States , 2017, PloS one.

[30]  Mimi Kim,et al.  Feasibility of modified Dixon MRI techniques for hepatic fat quantification in hepatic disorders: validation with MRS and histology. , 2017, The British journal of radiology.

[31]  T. Miyati,et al.  Multicenter, multivendor phantom study to validate proton density fat fraction and T2* values calculated using vendor-provided 6-point DIXON methods. , 2018, Clinical imaging.

[32]  M. Brady,et al.  Magnitude‐intrinsic water–fat ambiguity can be resolved with multipeak fat modeling and a multipoint search method , 2019, Magnetic resonance in medicine.

[33]  HyunWook Park,et al.  Robust water–fat separation for multi‐echo gradient‐recalled echo sequence using convolutional neural network , 2019, Magnetic resonance in medicine.

[34]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[35]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.