Ultrasound-Based Estimation of Hepatic Steatosis in Pediatric MASLD

Jae Won Choi50 enrolled

Overview

The purpose of this study is to validate an artificial intelligence (AI)-based algorithm that estimates hepatic steatosis using ultrasound (US) B-mode images in pediatric participants with metabolic dysfunction-associated steatotic liver disease (MASLD). The MRI proton density fat fraction (MRI-PDFF) serves as the reference standard for hepatic fat quantification.

Study Type

INTERVENTIONAL

Allocation

Purpose

DIAGNOSTIC

Masking

NONE

Enrollment

Conditions

MASLD Pediatric

Interventions

Ultrasound and MRIDIAGNOSTIC_TEST

Participants undergo same-day liver imaging including conventional B-mode ultrasound, quantitative ultrasound, and magnetic resonance imaging (MRI). Conventional Ultrasound: B-mode imaging performed on three ultrasound systems (Canon Aplio i800, Philips EPIQ, and Supersonic AIXPLORER) to acquire grayscale liver images for artificial intelligence (AI) analysis. Quantitative Ultrasound: Attenuation imaging (ATI) and shear wave elastography/dispersion measurements performed to assess hepatic fat and stiffness. MRI: Proton density fat fraction (PDFF) measurement used as the reference standard for hepatic steatosis quantification. All imaging is performed on the same day for each participant to ensure temporal consistency across modalities and vendors.

Eligibility

Sex: ALLMin age: 8 YearsMax age: 18 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: * participants aged 8 to 18 years clinically indicated for liver ultrasound examination to evaluate hepatic steatosis * participants with suspected or known metabolic dysfunction-associated steatotic liver disease (MASLD) * able to understand the study purpose and provide written informed consent (from both participant and legal guardian). * agree to undergo same-day liver MRI examination in addition to the ultrasound Exclusion Criteria: * unable to cooperate with imaging procedures * parent or legal guardian unable to understand the study explanation * contraindications to MRI * determined by the investigator to be otherwise unsuitable for participation after consultation

Locations (1)

Seoul National University Hospital

Seoul, South Korea

Outcomes

Primary Outcomes

Agreement Between AI-Predicted Ultrasound Fat Fraction (AI-USFF) and MRI Proton Density Fat Fraction (MRI-PDFF)

Reference standard: MRI-PDFF (percentage) \- intraclass correlation coefficient (ICC)

Time frame: At time of imaging (single visit)

Secondary Outcomes

Correlation Between AI-USFF and MRI-PDFF

Reference standard: MRI-PDFF (percentage) \- Pearson correlation coefficient (r)

Time frame: At time of imaging (single visit)

Diagnostic Performance of AI-USFF for MRI-Based Hepatic Steatosis Grades

The diagnostic performance of AI-USFF for detecting mild, moderate, and severe hepatic steatosis, as defined by MRI-PDFF thresholds, will be evaluated using area under the receiver operating characteristic curve (AUC).

Time frame: At time of imaging (single visit)

Inter-Vendor Reproducibility of AI-USFF

Reproducibility of AI-USFF across the three ultrasound systems are assessed using the intraclass correlation coefficient (ICC \[2,k\]).

Time frame: At time of imaging (single visit)

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.