High Resolution HBA-MRI Using Deep Learning Reconstruction

Not Applicable

Active, not recruiting

• Conditions: Deep Learning; Liver Diseases; Magnetic Resonance Imaging
• Interventions: Diagnostic Test: Liver MRI

• Registration Number: NCT05182099
• Lead Sponsor: Seoul National University Hospital

Brief Summary

This study aims to compare image qualities between conventionally reconstructed MRI sequences and deep-learning reconstructed MRI sequences from the same data in patients who undergo Gd-EOB-DTPA enhanced liver MRI. The AIRTM deep learning sequence is applicable for various MRI sequences including T2-weighted image (T2WI), T1-weighted image and diffusion-weighted image (DWI). We plan to perform intra-individual comparisons of the image qualities between two reconstructed image datasets.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2021-12-16
• Study First Submitted QC: 2022-01-06
• Study Start: 2022-01-10
• Study First Posted: 2022-01-10
• Primary Completion: 2022-03-30
• Status Verified: 2023-05
• Last Update Submitted: 2023-05-15
• Last Update Posted: 2023-05-16
• Study Completion: 2023-09-30

Recruitment & Eligibility

• Status: ACTIVE_NOT_RECRUITING
• Sex: All
• Target Recruitment: 52

Inclusion Criteria

• older than 20 years old
• scheduled for Gd-EOB-DTPA enhanced liver MRI at a 3T scanner (Premier, GE Healthcare) in our institution
• signed informed consent

Exclusion Criteria

• younger than 20 years old
• any absolute/relative contrast indication of Gd-EOB-DTPA enhanced MRI
• history of transient dyspnea after Gd-EOB-DTPA administration

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Arm && Interventions

Group	Intervention	Description
Conventional image reconstruction	Liver MRI	Gd-EOB-DTPA enhanced liver MRI images are reconstructed using a conventional image reconstruction algorithm. It is automatically generated from a MRI console after the examination.
Deep learning image reconstruction	Liver MRI	Gd-EOB-DTPA enhanced liver MRI images are reconstructed using a deep learning based image reconstruction algorithm (AIRTM). It is additionally generated aside from the conventional images. For obtaining the images, we will use the same MRI raw data which is used for conventional image reconstruction.

Primary Outcome Measures

Name	Time	Method
Overall image quality of arterial phase	3 months after enrollment completion	qualitative assessment of arterial phase on a five point scale (highest score indicates better image quality)

Trial Locations

Locations (1)

Seoul National University Hospital; 🇰🇷 Seoul, Korea, Republic of