Lu Xue, Zhang Haoyan, Kuroda Hidekatsu, Garcovich Matteo, de Ledinghen Victor, Grgurević Ivica, Linghu Runze, Ding Hong, Chang Jiandong, Wu Min, Feng Cheng, Ren Xinping, Liu Changzhu, Song Tao, Meng Fankun, Zhang Yao, Fang Ye, Ma Sumei, Wang Jinfen, Qi Xiaolong, Tian Jie, Yang Xin, Ren Jie, Liang Ping, Wang Kun
Department of Ultrasound, Guangdong Key Laboratory of Liver Disease Research, Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510630, Guangdong, China.
CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
Vis Comput Ind Biomed Art. 2025 Aug 15;8(1):19. doi: 10.1186/s42492-025-00199-6.
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.
准确、无创地诊断代偿期晚期慢性肝病（cACLD）对于有效的临床管理至关重要，但仍具有挑战性。本研究旨在利用国际多中心数据开发一种基于深度学习的放射组学模型，并通过将其与覆盖多个国家或地区、病因及超声设备制造商的二维剪切波弹性成像（2D-SWE）截断值方法进行比较来评估其性能。这项回顾性研究纳入了1937例因乙型肝炎、丙型肝炎或代谢功能障碍相关脂肪性肝病导致的慢性肝病成年患者。所有患者在中国、日本和欧洲的17个中心使用三家制造商（SuperSonic Imagine、通用电气和迈瑞）生产 的设备接受了2D-SWE成像和肝活检。所提出的弹性成像广义深度学习放射组学模型整合了弹性成像图像和肝脏硬度测量值，并在分层的内部和外部数据集上进行训练和测试。统计分析共纳入了1937例患者的9472幅2D-SWE图像。与2D-SWE相比，该模型在受试者工作特征曲线下面积（AUC）更高（0.89对0.83，P = 0.025）。在所有亚分析中，该模型也实现了高度一致的诊断（P值：0.21 - 0.91），而2D-SWE在国家或地区（P < 0.001）和病因（P = 0.005）亚分析中表现出不同的AUC，但在制造商亚分析中没有差异（P = 0.24）。在不同国家或地区、病因及制造商中，该模型在无创cACLD诊断中表现出比2D-SWE更准确、更稳健的性能。
