Deep learning radiomics of elastography for diagnosing compensated advanced chronic liver disease: an international multicenter study

Accurate, noninvasive diagnosis of compensated advanced chronic liver disease (cACLD) is essential for effective clinical management but remains challenging. This study aimed to develop a deep learning-based radiomics model using international multicenter data and to evaluate its performance by comparing it to the two-dimensional shear wave elastography (2D-SWE) cut-off method covering multiple countries or regions, etiologies, and ultrasound device manufacturers. This retrospective study included 1937 adult patients with chronic liver disease due to hepatitis B, hepatitis C, or metabolic dysfunction-associated steatotic liver disease. All patients underwent 2D-SWE imaging and liver biopsy at 17 centers across China, Japan, and Europe using devices from three manufacturers (SuperSonic Imagine, General Electric, and Mindray). The proposed generalized deep learning radiomics of elastography model integrated both elastographic images and liver stiffness measurements and was trained and tested on stratified internal and external datasets. A total of 1937 patients with 9472 2D-SWE images were included in the statistical analysis. Compared to 2D-SWE, the model achieved a higher area under the receiver operating characteristic curve (AUC) (0.89 vs 0.83, P = 0.025). It also achieved a highly consistent diagnosis across all subanalyses (P values: 0.21-0.91), whereas 2D-SWE exhibited different AUCs in the country or region (P < 0.001) and etiology (P = 0.005) subanalyses but not in the manufacturer subanalysis (P = 0.24). The model demonstrated more accurate and robust performance in noninvasive cACLD diagnosis than 2D-SWE across different countries or regions, etiologies, and manufacturers.

Authors

Institutions

Publication Details

Journal
Visual Computing for Industry Biomedicine and Art
Published
2025-08-15
DOI
https://doi.org/10.1186/s42492-025-00199-6
Citations
1
Primary Topic
Liver Disease Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
1.35

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep learning radiomics of elastography for diagnosing compensated advanced chronic liver disease: an international multicenter study

Ping Liang, Xiaolong Qi, Fankun Meng, Matteo Garcovich et al.
1 citations
Visual Computing for Industry Biomedicine and Art
Liver Disease Diagnosis and Treatment
1.35
article

Deep learning radiomics of elastography for diagnosing compensated advanced chronic liver disease: an international multicenter study

Ping Liang, Xiaolong Qi, Fankun Meng, Matteo Garcovich, Jinfen Wang, Changzhu Liu, Jie Ren, T. Z. Song, Ivica Grgurević, Jiandong Chang, Hidekatsu Kuroda, Runze Linghu, Xinping Ren, Haoyan Zhang, Hong Ding, Kun Wang, Jie Tian, Yao Zhang, Fang Ye, Xin Yang, Xue Lu, Cheng Feng, Min Wu, V. de Lédinghen, Sumei Ma
article en
1 citations

Abstract

Accurate, noninvasive diagnosis of compensated advanced chronic liver disease (cACLD) is essential for effective clinical management but remains challenging. This study aimed to develop a deep learning-based radiomics model using international multicenter data and to evaluate its performance by comparing it to the two-dimensional shear wave elastography (2D-SWE) cut-off method covering multiple countries or regions, etiologies, and ultrasound device manufacturers. This retrospective study included 1937 adult patients with chronic liver disease due to hepatitis B, hepatitis C, or metabolic dysfunction-associated steatotic liver disease. All patients underwent 2D-SWE imaging and liver biopsy at 17 centers across China, Japan, and Europe using devices from three manufacturers (SuperSonic Imagine, General Electric, and Mindray). The proposed generalized deep learning radiomics of elastography model integrated both elastographic images and liver stiffness measurements and was trained and tested on stratified internal and external datasets. A total of 1937 patients with 9472 2D-SWE images were included in the statistical analysis. Compared to 2D-SWE, the model achieved a higher area under the receiver operating characteristic curve (AUC) (0.89 vs 0.83, P = 0.025). It also achieved a highly consistent diagnosis across all subanalyses (P values: 0.21-0.91), whereas 2D-SWE exhibited different AUCs in the country or region (P < 0.001) and etiology (P = 0.005) subanalyses but not in the manufacturer subanalysis (P = 0.24). The model demonstrated more accurate and robust performance in noninvasive cACLD diagnosis than 2D-SWE across different countries or regions, etiologies, and manufacturers.

Visual Computing for Industry Biomedicine and ArtVol. 8(1)
Université de Bordeaux (FR), Xinjiang Medical University (CN), Inserm (FR), Sun Yat-sen University (CN), Iwate Medical University (JP), Chinese Academy of Sciences (CN), Fudan University (CN), University Hospital Dubrava (HR), Ruijin Hospital (CN), Agostino Gemelli University Polyclinic (IT), First Affiliated Hospital of Xinjiang Medical University (CN), Chinese PLA General Hospital (CN), Centre Hospitalier Universitaire de Bordeaux (FR), Shandong Institute of Automation (CN), Beijing Academy of Artificial Intelligence (CN), Ningbo No. 2 Hospital (CN), Zhongda Hospital Southeast University (CN), Bordeaux Population Health (FR), Nanjing Drum Tower Hospital (CN), Zhongshan Hospital (CN), Third Affiliated Hospital of Sun Yat-sen University (CN), Beijing YouAn Hospital (CN), Beijing Ditan Hospital (CN), Xiamen Chang Gung Hospital (CN), Guangzhou Eighth People's Hospital (CN), First Hospital of Lanzhou University (CN), University of Chinese Academy of Sciences (CN), Shenzhen Third People’s Hospital (CN), Lanzhou University (CN), Guangzhou Medical University (CN)
National Natural Science Foundation of China, Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences, Basic and Applied Basic Research Foundation of Guangdong Province
Partnerships for the goals
Openalex Percentile: Top 17%
Liver Disease Diagnosis and Treatment
1.35
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.