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

作者：Xue Lu, Haoyan Zhang, Hidekatsu Kuroda, Matteo Garcovich, V. de Lédinghen, Ivica Grgurević, Runze Linghu, Hong Ding, Jiandong Chang, Min Wu, Cheng Feng, Xinping Ren, Changzhu Liu, Tao Song, Fankun Meng, Yao Zhang, Fang Ye, Sumei Ma, Jinfen Wang, Xiaolong Qi, Jie Tian, Xin Yang, Jie Ren, Ping Liang, Kun Wang · 发表于：Visual Computing for Industry Biomedicine and Art · 年份：2025 · DOI：10.1186/s42492-025-00199-6 · 被引用次数：3 · 研究领域：Liver Disease Diagnosis and Treatment、Radiomics and Machine Learning in Medical Imaging、Hepatocellular Carcinoma Treatment and Prognosis

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...