Observational Study
Copyright ©The Author(s) 2022. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Jun 14, 2022; 28(22): 2494-2508
Published online Jun 14, 2022. doi: 10.3748/wjg.v28.i22.2494
Accurate and generalizable quantitative scoring of liver steatosis from ultrasound images via scalable deep learning
Bowen Li, Dar-In Tai, Ke Yan, Yi-Cheng Chen, Cheng-Jen Chen, Shiu-Feng Huang, Tse-Hwa Hsu, Wan-Ting Yu, Jing Xiao, Lu Le, Adam P Harrison
Bowen Li, Ke Yan, Lu Le, Adam P Harrison, Research and Development, PAII Inc., Bethesda, MD 20817, United States
Dar-In Tai, Yi-Cheng Chen, Cheng-Jen Chen, Tse-Hwa Hsu, Wan-Ting Yu, Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Linkou Medical Center, Taoyuan 33305, Taiwan
Shiu-Feng Huang, Division of Molecular and Genomic Medicine, National Health Research Institute, Taoyuan 33305, Taiwan
Jing Xiao, Research and Development, Ping An Insurance Group, Shenzhen 518001, Guangdong, China
Author contributions: Li B contributed to software, visualization, and writing original draft and investigation; Yan K contributed to formal analysis, visualization and writing review and editing; Chen YC, Chen CJ, Huang SF, Hsu TH, and Yu WT contributed to data curation; Huang SF contributed to resources; Xiao J contributed to project administration and funding acquisition, and writing review and editing; Lu L contributed to project administration, supervision, writing review and editing, and resources; Harrison AP contributed to formal analysis, supervision, software, writing review and editing, investigation, and methodology; Tai DI contributed to supervision, data curation, conceptualization, writing review and editing, validation, project administration, investigation, resources, and methodology.
Supported by the Maintenance Project of the Center for Artificial Intelligence, No. CLRPG3H0012 and No. SMRPG3I0011.
Institutional review board statement: The study was reviewed and approved by the Institutional Review Board of the Chang Gung Medical Foundation (CGMH IRB No. 201801283B0).
Informed consent statement: Patients were not required to give informed consent to the study.
Conflict-of-interest statement: All authors declare no conflict of interest.
Data sharing statement: No additional data are available.
STROBE statement: The authors have read the STROBE Statement—checklist of items, and the manuscript was prepared and revised according to the STROBE Statement—checklist of items.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Dar-In Tai, MD, PhD, Professor, Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Linkou Medical Center, No. 5 Fuxing Street, Guishan Dist, Taoyuan 33305, Taiwan. tai48978@cgmh.org.tw
Received: December 18, 2021
Peer-review started: December 18, 2021
First decision: January 23, 2022
Revised: February 3, 2022
Accepted: April 22, 2022
Article in press: April 22, 2022
Published online: June 14, 2022
Abstract
BACKGROUND

Hepatic steatosis is a major cause of chronic liver disease. Two-dimensional (2D) ultrasound is the most widely used non-invasive tool for screening and monitoring, but associated diagnoses are highly subjective.

AIM

To develop a scalable deep learning (DL) algorithm for quantitative scoring of liver steatosis from 2D ultrasound images.

METHODS

Using multi-view ultrasound data from 3310 patients, 19513 studies, and 228075 images from a retrospective cohort of patients received elastography, we trained a DL algorithm to diagnose steatosis stages (healthy, mild, moderate, or severe) from clinical ultrasound diagnoses. Performance was validated on two multi-scanner unblinded and blinded (initially to DL developer) histology-proven cohorts (147 and 112 patients) with histopathology fatty cell percentage diagnoses and a subset with FibroScan diagnoses. We also quantified reliability across scanners and viewpoints. Results were evaluated using Bland-Altman and receiver operating characteristic (ROC) analysis.

RESULTS

The DL algorithm demonstrated repeatable measurements with a moderate number of images (three for each viewpoint) and high agreement across three premium ultrasound scanners. High diagnostic performance was observed across all viewpoints: Areas under the curve of the ROC to classify mild, moderate, and severe steatosis grades were 0.85, 0.91, and 0.93, respectively. The DL algorithm outperformed or performed at least comparably to FibroScan control attenuation parameter (CAP) with statistically significant improvements for all levels on the unblinded histology-proven cohort and for “= severe” steatosis on the blinded histology-proven cohort.

CONCLUSION

The DL algorithm provides a reliable quantitative steatosis assessment across view and scanners on two multi-scanner cohorts. Diagnostic performance was high with comparable or better performance than the CAP.

Keywords: Ultrasound, Liver steatosis, Deep learning, Screening, Computer-aided diagnosis

Core Tip: Ultrasound is widely used to evaluate liver steatosis, but it is subjective. We developed a deep learning algorithm for quantitative steatosis scoring from ultrasound. The algorithm was trained on > 200000 images and composed of different scanners and viewpoints from both hepatic lobes. High diagnostic performance was measured across all viewpoints in separate histology proven groups, which was comparable to or better than the control attenuation parameter. We demonstrated high agreement across scanners and viewpoints. Thus, our deep learning algorithm provides a quantitative assessment with high performance and reliability.