Volume 45, Issue 7 e70148
ORIGINAL ARTICLE

A Deep Learning Model Based on High-Frequency Ultrasound Images for Classification of Different Stages of Liver Fibrosis

Linlin Zhang

Linlin Zhang

Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, China

Search for more papers by this author
Zhengbo Tan

Zhengbo Tan

MedAI Technology (Wuxi) Co. Ltd, Wuxi, China

Search for more papers by this author
Chunlei Li

Chunlei Li

MedAI Technology (Wuxi) Co. Ltd, Wuxi, China

Search for more papers by this author
Lichao Mou

Lichao Mou

MedAI Technology (Wuxi) Co. Ltd, Wuxi, China

Search for more papers by this author
Yi Lei Shi

Corresponding Author

Yi Lei Shi

MedAI Technology (Wuxi) Co. Ltd, Wuxi, China

Correspondence:

Yi Lei Shi ([email protected])

Xiao Xiang Zhu ([email protected])

Yan Luo ([email protected])

Search for more papers by this author
Xiao Xiang Zhu

Corresponding Author

Xiao Xiang Zhu

Chair of Data Science in Earth Observation, Technical University of Munich, Munich, Germany

Correspondence:

Yi Lei Shi ([email protected])

Xiao Xiang Zhu ([email protected])

Yan Luo ([email protected])

Search for more papers by this author
Yan Luo

Corresponding Author

Yan Luo

Department of Medical Ultrasound, West China Hospital, Sichuan University, Chengdu, China

Correspondence:

Yi Lei Shi ([email protected])

Xiao Xiang Zhu ([email protected])

Yan Luo ([email protected])

Search for more papers by this author
First published: 13 June 2025
Citations: 1

Funding: This study has received funding supports from Chinese Academy of Medical Sciences Research under Grants 2022-I2M-C&T-B-105.

Handling Editor: Dr. Alejandro Forner

ABSTRACT

Background and Aims

To develop a deep learning model based on high-frequency ultrasound images to classify different stages of liver fibrosis in chronic hepatitis B patients.

Methods

This retrospective multicentre study included chronic hepatitis B patients who underwent both high-frequency and low-frequency liver ultrasound examinations between January 2014 and August 2024 at six hospitals. Paired images were employed to train the HF-DL and the LF-DL models independently. Three binary tasks were conducted: (1) Significant Fibrosis (S0-1 vs. S2-4); (2) Advanced Fibrosis (S0-2 vs. S3-4); (3) Cirrhosis (S0-3 vs. S4). Hepatic pathological results constituted the ground truth for algorithm development and evaluation. The diagnostic value of high-frequency and low-frequency liver ultrasound images was compared across commonly used CNN networks. The HF-DL model performance was compared against the LF-DL model, FIB-4, APRI, and with SWE (external test set). The calibration of models was plotted. The clinical benefits were calculated. Subgroup analysis for patients with different characteristics (BMI, ALT, inflammation level, alcohol consumption level) was conducted.

Results

The HF-DL model demonstrated consistently superior diagnostic performance across all stages of liver fibrosis compared to the LF-DL model, FIB-4, APRI and SWE, particularly in classifying advanced fibrosis (0.93 [95% CI 0.90–0.95], 0.93 [95% CI 0.89–0.96], p < 0.01). The HF-DL model demonstrates significantly improved performance in both target patient detection and negative population exclusion.

Conclusions

The HF-DL model based on high-frequency ultrasound images outperforms other routinely used non-invasive modalities across different stages of liver fibrosis, particularly in advanced fibrosis, and may offer considerable clinical value.

Conflicts of Interest

The authors declare no conflicts of interest.

Data Availability Statement

The data supporting this study's findings are available from the corresponding author upon reasonable request.

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.