Related Experiment Video
Updated: Jun 7, 2025

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
High-precision MRI of liver and hepatic lesions on gadoxetic acid-enhanced hepatobiliary phase using a deep learning
Haruka Kiyoyama1, Masahiro Tanabe2, Keiko Hideura1
1Department of Radiology, Yamaguchi University Graduate School of Medicine, 1-1-1 Minami-Kogushi, Ube, Yamaguchi, 755-8505, Japan.
Purpose:
The purpose of this study was to investigate whether the high-precision magnetic resonance (MR) sequence using modified Fast 3D mode wheel and Precise IQ Engine (PIQE), that was collected in a wheel shape with sequential data filling in the k-space in the phase encode-slice encode plane, is feasible for breath-hold (BH) three-dimensional (3D) T1-weighted imaging of the hepatobiliary phase (HBP) of gadoxetic acid-enhanced MRI in comparison to the compressed sensing (CS) sequence using Advanced Intelligent Clear-IQ Engine (AiCE).
Methods:
This retrospective study included 54 patients with focal hepatic lesions who underwent dynamic contrast-enhanced MRI. Both standard HBP images using CS with AiCE and high-precision HBP images using modified Fast 3D mode wheel and PIQE were obtained. Image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were evaluated using the Wilcoxon signed-rank test. p values of < 0.05 were considered to be statistically significant.
Results:
Scores for image noise, conspicuity of liver contours and intrahepatic structures, and overall image quality in high-precision HBP imaging using modified Fast 3D mode wheel and PIQE were significantly higher than those in HBP imaging using CS and AiCE (all p < 0.001). There was no significant difference in the presence of artifact and motion-related blurring. There were no significant differences between the sequences in SNR (p = 0.341) or CNR (p = 0.077). The detection rate of focal hepatic lesions was 71.4-85.3% in CS with AiCE, and 82.2-95.8% in modified Fast 3D mode wheel and PIQE.
Conclusion:
A high-precision MR sequence using a modified Fast 3D mode wheel and PIQE is applicable for the HBP of BH 3D T1-weighted imaging.
More Related Videos
05:37Author Spotlight: A Non-Invasive Tool to Assess and Differentiate Fat Patterns in Liver Using 3D Dixon MRI
Published on: October 20, 2023
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018