Yanna Liu1, Zhenyuan Ning2, Necati Örmeci3, Weimin An4, Qian Yu5, Kangfu Han2, Yifei Huang6, Dengxiang Liu7, Fuquan Liu8, Zhiwei Li9, Huiguo Ding10, Hongwu Luo11, Changzeng Zuo7, Changchun Liu4, Jitao Wang7, Chunqing Zhang12, Jiansong Ji13, Wenhui Wang6, Zhiwei Wang14, Weidong Wang15, Min Yuan16, Lei Li6, Zhongwei Zhao13, Guangchuan Wang12, Mingxing Li14, Qingbo Liu15, Junqiang Lei6, Chuan Liu6, Tianyu Tang5, Seray Akçalar17, Emrecan Çelebioğlu17, Evren Üstüner17, Sadık Bilgiç17, Zeynep Ellik3, Özgün Ömer Asiller3, Zaiyi Liu18, Gaojun Teng19, Yaolong Chen20, Jinlin Hou21, Xun Li6, Xiaoshun He22, Jiahong Dong23, Jie Tian24, Ping Liang25, Shenghong Ju26, Yu Zhang27, Xiaolong Qi28. 1. Chinese Portal Hypertension Diagnosis and Monitoring Study Group (CHESS) Center, Institute of Portal Hypertension, The First Hospital of Lanzhou University, Lanzhou, China; Department of Hepatology Unit and Infectious Diseases, Nanfang Hospital, Southern Medical University, Guangzhou, China. 2. School of Biomedical Engineering, Southern Medical University, Guangzhou, China. 3. Department of Gastroenterology. 4. Department of Radiology, Fifth Medical Center of Chinese People's Liberation Army General Hospital, Beijing, China. 5. Department of Radiology. 6. Chinese Portal Hypertension Diagnosis and Monitoring Study Group (CHESS) Center, Institute of Portal Hypertension, The First Hospital of Lanzhou University, Lanzhou, China. 7. Chinese Portal Hypertension Diagnosis and Monitoring Study Group (CHESS) Working Party, Xingtai People's Hospital, Xingtai, China. 8. Department of Interventional Therapy, Beijing Shijitan Hospital. 9. Department of Hepatobiliary Surgery, The Third People's Hospital of Shenzhen, Shenzhen, China. 10. Department of Gastroenterology and Hepatology, Beijing You'an Hospital, Capital Medical University, Beijing, China. 11. Department of General Surgery, The Third Xiangya Hospital of Central South University, Changsha, China. 12. Department of Gastroenterology, Shandong Provincial Hospital Affiliated to Shandong University, Jinan, China. 13. Key Laboratory of Imaging Diagnosis and Minimally Invasive Intervention Research, Lishui Hospital of Zhejiang University, Lishui, China. 14. Department of Vascular and Endovascular Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China. 15. Department of Hepatobiliary Surgery, Shunde Hospital, Southern Medical University, Foshan, China. 16. Department of Interventional Radiology, Shanghai Public Health Clinical Center, Shanghai, China. 17. Department of Radiology, Ankara University School of Medicine, Ankara, Turkey. 18. Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China. 19. Department of Interventional Radiology, Zhongda Hospital, Medical School of Southeast University, Nanjing, China. 20. Evidence-Based Medicine Center, School of Basic Medical Sciences, Lanzhou University, Lanzhou, China. 21. Department of Hepatology Unit and Infectious Diseases, Nanfang Hospital, Southern Medical University, Guangzhou, China. 22. Organ Transplant Center, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China. 23. Department of Hepatopancreatobiliary Surgery, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China. 24. Key Laboratory of Molecular Imaging of Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences, Beijing, China. 25. Department of Interventional Ultrasound, Chinese People's Liberation Army General Hospital, Beijing, China. 26. Department of Radiology. Electronic address: jsh0836@126.com. 27. School of Biomedical Engineering, Southern Medical University, Guangzhou, China. Electronic address: yuzhang@smu.edu.cn. 28. Chinese Portal Hypertension Diagnosis and Monitoring Study Group (CHESS) Center, Institute of Portal Hypertension, The First Hospital of Lanzhou University, Lanzhou, China. Electronic address: qixiaolong@vip.163.com.
Abstract
BACKGROUND & AIMS: Noninvasive and accurate methods are needed to identify patients with clinically significant portal hypertension (CSPH). We investigated the ability of deep convolutional neural network (CNN) analysis of computed tomography (CT) or magnetic resonance (MR) to identify patients with CSPH. METHODS: We collected liver and spleen images from patients who underwent contrast-enhanced CT or MR analysis within 14 days of transjugular catheterization for hepatic venous pressure gradient measurement. The CT cohort comprised participants with cirrhosis in the CHESS1701 study, performed at 4 university hospitals in China from August 2016 through September 2017. The MR cohort comprised participants with cirrhosis in the CHESS1802 study, performed at 8 university hospitals in China and 1 in Turkey from December 2018 through April 2019. Patients with CSPH were identified as those with a hepatic venous pressure gradient of 10 mm Hg or higher. In total, we analyzed 10,014 liver images and 899 spleen images collected from 679 participants who underwent CT analysis, and 45,554 liver and spleen images from 271 participants who underwent MR analysis. For each cohort, participants were shuffled and then sampled randomly and equiprobably for 6 times into training, validation, and test data sets (ratio, 3:1:1). Therefore, a total of 6 deep CNN models for each cohort were developed for identification of CSPH. RESULTS: The CT-based CNN analysis identified patients with CSPH with an area under the receiver operating characteristic curve (AUC) value of 0.998 in the training set (95% CI, 0.996-1.000), an AUC of 0.912 in the validation set (95% CI, 0.854-0.971), and an AUC of 0.933 (95% CI, 0.883-0.984) in the test data sets. The MR-based CNN analysis identified patients with CSPH with an AUC of 1.000 in the training set (95% CI, 0.999-1.000), an AUC of 0.924 in the validation set (95% CI, 0.833-1.000), and an AUC of 0.940 in the test data set (95% CI, 0.880-0.999). When the model development procedures were repeated 6 times, AUC values for all CNN analyses were 0.888 or greater, with no significant differences between rounds (P > .05). CONCLUSIONS: We developed a deep CNN to analyze CT or MR images of liver and spleen from patients with cirrhosis that identifies patients with CSPH with an AUC value of 0.9. This provides a noninvasive and rapid method for detection of CSPH (ClincialTrials.gov numbers: NCT03138915 and NCT03766880).
BACKGROUND & AIMS: Noninvasive and accurate methods are needed to identify patients with clinically significant portal hypertension (CSPH). We investigated the ability of deep convolutional neural network (CNN) analysis of computed tomography (CT) or magnetic resonance (MR) to identify patients with CSPH. METHODS: We collected liver and spleen images from patients who underwent contrast-enhanced CT or MR analysis within 14 days of transjugular catheterization for hepatic venous pressure gradient measurement. The CT cohort comprised participants with cirrhosis in the CHESS1701 study, performed at 4 university hospitals in China from August 2016 through September 2017. The MR cohort comprised participants with cirrhosis in the CHESS1802 study, performed at 8 university hospitals in China and 1 in Turkey from December 2018 through April 2019. Patients with CSPH were identified as those with a hepatic venous pressure gradient of 10 mm Hg or higher. In total, we analyzed 10,014 liver images and 899 spleen images collected from 679 participants who underwent CT analysis, and 45,554 liver and spleen images from 271 participants who underwent MR analysis. For each cohort, participants were shuffled and then sampled randomly and equiprobably for 6 times into training, validation, and test data sets (ratio, 3:1:1). Therefore, a total of 6 deep CNN models for each cohort were developed for identification of CSPH. RESULTS: The CT-based CNN analysis identified patients with CSPH with an area under the receiver operating characteristic curve (AUC) value of 0.998 in the training set (95% CI, 0.996-1.000), an AUC of 0.912 in the validation set (95% CI, 0.854-0.971), and an AUC of 0.933 (95% CI, 0.883-0.984) in the test data sets. The MR-based CNN analysis identified patients with CSPH with an AUC of 1.000 in the training set (95% CI, 0.999-1.000), an AUC of 0.924 in the validation set (95% CI, 0.833-1.000), and an AUC of 0.940 in the test data set (95% CI, 0.880-0.999). When the model development procedures were repeated 6 times, AUC values for all CNN analyses were 0.888 or greater, with no significant differences between rounds (P > .05). CONCLUSIONS: We developed a deep CNN to analyze CT or MR images of liver and spleen from patients with cirrhosis that identifies patients with CSPH with an AUC value of 0.9. This provides a noninvasive and rapid method for detection of CSPH (ClincialTrials.gov numbers: NCT03138915 and NCT03766880).
Authors: Jérémy Dana; Aïna Venkatasamy; Antonio Saviano; Joachim Lupberger; Yujin Hoshida; Valérie Vilgrain; Pierre Nahon; Caroline Reinhold; Benoit Gallix; Thomas F Baumert Journal: Hepatol Int Date: 2022-02-09 Impact factor: 9.029
Authors: Maria El Homsi; Michael Chung; Adam Bernheim; Adam Jacobi; Michael J King; Sara Lewis; Bachir Taouli Journal: Eur J Radiol Open Date: 2020-06-07