Related Experiment Video
Updated: Aug 19, 2025
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
Comparative Analysis of a Locally Resampling MR Elastography Reconstruction Algorithm in Liver Fibrosis
Gwenaël Pagé1, Felicia Julea1, Valérie Paradis2
1Laboratory of Imaging Biomarkers, Université Paris Cité, Inserm, CRI, Paris, France.
Background:
In magnetic resonance elastography (MRE), the precision of the observed mechanical depends on the ratio between mechanical wavelength and spatial resolution. Since the mechanical wavelength may vary with actuation frequency, between patients and depending on position, a unique spatial resolution may not always generate an optimal ratio for multifrequency acquisitions, in patients with varying degrees of disease or in mechanically heterogeneous organs.
Purpose:
To describe an MRE reconstruction algorithm that adjusts the ratio between shear wavelength and pixel size, by locally resampling the matrix of shear displacement, and to assess its performance relative to existing reconstructions in different use cases.
Study Type:
Prospective.
Population:
Four phantoms, 20 healthy volunteers (5 men, median age 34, range 20-56) and 46 patients with nonalcoholic fatty liver disease (37 men, median age 63, range 33-83).
Field Strength/Sequence:
A 3 T; gradient-echo elastography sequence with 40 Hz, 60 Hz, and 80 Hz frequencies.
Assessment:
For each algorithm, phantoms stiffness were compared against their nominal values, repeatability was calculated in healthy volunteers, and diagnostic performance in detecting advanced liver fibrosis was assessed in 46 patients.
Statistical Tests:
Linear regression was used to evaluate the agreement between stiffness values and phantoms stiffnesses. Bland-Altman method was used to evaluate repeatability in volunteers. The ability to diagnose advanced fibrosis was assessed by receiver operating curve analysis (with Youden index thresholds). Significance was considered at P value of 0.05.
Results:
From the linear regression, the slope closest to 1 is provided by MARS (40 Hz) and k-MDEV (60H, 80 Hz). Repeatability index was best with MDEV (23%) and lowest with k-MDEV (53%). The best performance in detecting advanced fibrosis was provided by MARS at 40 Hz (area under the operating curve, AUC = 0.88), k-MDEV and MARS at 60 Hz (AUC = 0.91), and multimodel direct inversion (MMDI) and MARS at 80 Hz (AUC = 0.90).
Data Conclusion:
MARS shows the best diagnostic performance to detect advanced fibrosis and the second-best results in phantoms after k-MDEV.
Evidence Level:
1.
Technical Efficacy:
Stage 2.
