Deep learning radiomics of elastography for diagnosing compensated advanced chronic liver disease: an international multicenter study.
Authors
Affiliations (26)
Affiliations (26)
- 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.
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100190, China.
- Division of Hepatology, Department of Internal Medicine, School of Medicine, Iwate Medical University, Shiwa-Gun, Iwate, 028-3694, Japan.
- Medicina Interna E Gastroenterologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Università Cattolica del Sacro Cuore, Rome, 00168, Italy.
- Hepatology Unit, University Hospital, CHU Bordeaux, Pessac, & INSERM U1312, Bordeaux University, Bordeaux, 33000, France.
- Department of Gastroenterology, Hepatology and Clinical Nutrition, University Hospital Dubrava, Zagreb, 10000, Croatia.
- Ultrasound Department, Chinese PLA General Hospital, Beijing, 100853, China.
- Department of Ultrasound, Zhongshan Hospital Affiliated to Fudan University, Shanghai, 200032, China.
- Department of Ultrasound, Xiamen Hospital of Traditional Chinese Medicine, Xiamen, 361009, Fujian, China.
- Department of Ultrasound, Nanjing University Medical School Affiliated Nanjing Drum Tower Hospital, Nanjing, 210008, Jiangsu, China.
- Department of Ultrasound, National Clinical Research Center for Infectious Disease, Department of Ultrasound, Shenzhen Third People's Hospital, Second Hospital, Affiliated to Southern University of Science and Technology, Shenzhen, 518112, Guangdong, China.
- Department of Ultrasound, School of Medicine, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, 200025, China.
- Department of Ultrasound, Guangzhou Eighth People's Hospital, Guangzhou Medical University, Guangzhou, 510600, Guangdong, China.
- Department of Abdominal Ultrasound, the First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830054, Xinjiang Uygur Autonomous Region, China.
- Department of Ultrasound, Beijing You'an Hospital Affiliated to Capital Medical University, Beijing, 100069, China.
- Department of Ultrasound, Beijing Ditan Hospital, Capital Medical University, Beijing, 100015, China.
- Department of Ultrasound, Ningbo Yinzhou No. 2 Hospital, Ningbo, 315100, Zhejiang, China.
- Department of Ultrasound, the First Hospital of Lanzhou University, Lanzhou, 730000, Gansu, China.
- Department of Radiology, Medical School, Zhongda Hospital, Southeast University, Nanjing, 210009, Jiangsu, China.
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China. [email protected].
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100190, China. [email protected].
- Department of Ultrasound, Guangdong Key Laboratory of Liver Disease Research, Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, 510630, Guangdong, China. [email protected].
- Ultrasound Department, Chinese PLA General Hospital, Beijing, 100853, China. [email protected].
- CAS Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China. [email protected].
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100190, China. [email protected].
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.