Automatic hepatic steatosis quantification using low-dose CT with deep learning-based noise reduction and CT fat fraction analysis software.

Sung Joon Youn¹, Sun Kyung Jeon², Jeong Hee Yoon^2,3,4, Chulkyun Ahn^5,6, Jeong Min Lee^2,3,4

¹Seoul National University College of Medicine, Seoul 03080, Korea.

²Department of Radiology, Seoul National University Hospital, Seoul 03080, Korea.

³Department of Radiology, Seoul National University College of Medicine, Seoul 03080, Korea.

⁴Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul 03080, Korea.

⁵Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul 08826, Korea.

⁶ClariPi Research, ClariPi, Seoul 03088, Korea.

PubMed DOI

Abstract

OBJECTIVES: To evaluate the accuracy of CT-derived fat fraction (CDFF) software for quantifying hepatic steatosis at various radiation doses, using MRI-derived proton density fat fraction (MRI-PDFF) as the reference standard, and examines the impact of deep learning (DL)-based noise reduction on CDFF accuracy in low-dose CT (LDCT) scans. METHODS: We conducted a retrospective analysis of 125 livin…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Mentioned Companies

ClariPI
affiliation

Other Funding

SNUH(0620221870)
ClariPi., Ltd.

MeSH Terms

Fatty Liver*Tomography, X-Ray Computed*Deep Learning*Software0Magnetic Resonance Imaging0Reference Standards0Retrospective Studies0Radiation Dosage*Liver*Living Donors0ROC Curve0Image Processing, Computer-Assisted*Humans0Male0Female0Young Adult0Adult0Middle Aged0Aged0

Keywords

CT-derived fat fractionautomated fat quantificationdeep learning denoising reconstructionhepatic steatosislow-dose CT

Article Info

PMID: 41787978
DOI: 10.1093/bjr/tqag054
Received: December 10, 2024
Accepted: February 26, 2026

How to Cite

Youn SJ et al. Automatic hepatic steatosis quantification using low-dose CT with deep learning-based noise reduction and CT fat fraction analysis software. Br J Radiol2026;99(1182):1114-1124. doi:10.1093/bjr/tqag054

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.