Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis

doi:10.1016/j.cgh.2020.03.034

	Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis
	Liu, Yanna 1; Ning, Zhenyuan 2; Ormeci, Necati 3; An, Weimin 5; Yu, Qian 6; Han, Kangfu 2; Huang, Yifei 1; Liu, Dengxiang 8; Liu, Fuquan 9; Li, Zhiwei 11; Ding, Huiguo 10; Luo, Hongwu 12; Zuo, Changzeng 8; Liu, Changchun 5; Wang, Jitao 8; Zhang, Chunqing 13; Ji, Jiansong 14; Wang, Wenhui 1; Wang, Zhiwei 15; Wang, Weidong 16; Yuan, Min 17; Li, Lei 1; Zhao, Zhongwei 14; Wang, Guangchuan 13; Li, Mingxing 15; Liu, Qingbo 16; Lei, Junqiang 1; Liu, Chuan 1; Tang, Tianyu 6; Akcalar, Seray 4; Celebioglu, Emrecan 4; Ustuner, Evren 4; Bilgic, Sadik 4; Ellik, Zeynep 3; Asiller, Ozgun Omer 3; Liu, Zaiyi 18; Teng, Gaojun 7; Chen, Yaolong 19; Hou, Jinlin 20,21; Li, Xun 1; He, Xiaoshun 22; Dong, Jiahong 23; Tian, Jie 24; Liang, Ping 25; Ju, Shenghong 6; Zhang, Yu 2; Qi, Xiaolong 1
发表期刊	CLINICAL GASTROENTEROLOGY AND HEPATOLOGY
ISSN	1542-3565
	2020-12-01
卷号	18 期号:13 页码:2998-+
通讯作者	Ju, Shenghong(jsh0836@126.com) ; Zhang, Yu(yuzhang@smu.edu.cn) ; Qi, Xiaolong(qixiaolong@vip.163.com)
摘要	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 par-ticipants 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
关键词	HVPG Diagnostic Deep Learning AI
DOI	10.1016/j.cgh.2020.03.034
关键词[WOS]	ACCURATE MARKER ; FIBROSIS ; ELASTOGRAPHY ; DIAGNOSIS ; VARICES ; INDEX ; SCORE ; SERUM ; RISK
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation for Distinguished Young Scholars of China[81525014] ; National Natural Science Foundation of China[81600510] ; National Natural Science Foundation of China[81830053] ; Guangdong Science Fund for Distinguished Young Scholars[2018B030306019] ; Guangzhou Industry-Academia-Research Collaborative Innovation Major Project[201704020015]
项目资助者	National Natural Science Foundation for Distinguished Young Scholars of China ; National Natural Science Foundation of China ; Guangdong Science Fund for Distinguished Young Scholars ; Guangzhou Industry-Academia-Research Collaborative Innovation Major Project
WOS研究方向	Gastroenterology & Hepatology
WOS类目	Gastroenterology & Hepatology
WOS记录号	WOS:000589825300028
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：25[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41787
专题	中国科学院分子影像重点实验室
通讯作者	Ju, Shenghong; Zhang, Yu; Qi, Xiaolong
作者单位	1.Lanzhou Univ, Inst Portal Hypertens, Chinese Portal Hypertens Diag & Monitoring Study, Hosp 1, Lanzhou, Peoples R China 2.Southern Med Univ, Sch Biomed Engn, Guangzhou, Peoples R China 3.Ankara Univ, Sch Med, Dept Gastroenterol, Ankara, Turkey 4.Ankara Univ, Sch Med, Dept Radiol, Ankara, Turkey 5.Chinese Peoples Liberat Army Gen Hosp, Med Ctr 5, Dept Radiol, Beijing, Peoples R China 6.Southeast Univ, Med Sch, Zhongda Hosp, Dept Radiol, Nanjing, Peoples R China 7.Southeast Univ, Med Sch, Zhongda Hosp, Dept Intervent Radiol, Nanjing, Peoples R China 8.Xingtai Peoples Hosp, Chinese Portal Hypertens Diag & Monitoring Study, Xingtai, Peoples R China 9.Capital Med Univ, Dept Intervent Therapy, Beijing Shijitan Hosp, Beijing, Peoples R China 10.Capital Med Univ, Beijing Youan Hosp, Dept Gastroenterol & Hepatol, Beijing, Peoples R China 11.Third Peoples Hosp Shenzhen, Dept Hepatobiliary Surg, Shenzhen, Peoples R China 12.Cent South Univ, Dept Gen Surg, Xiangya Hosp 3, Changsha, Peoples R China 13.Shandong Univ, Shandong Prov Hosp, Dept Gastroenterol, Jinan, Peoples R China 14.Zhejiang Univ, Lishui Hosp, Key Lab Imaging Diag & Minimally Invas Intervent, Lishui, Peoples R China 15.Zhengzhou Univ, Affiliated Hosp 1, Dept Vasc & Endovasc Surg, Zhengzhou, Peoples R China 16.Southern Med Univ, Shunde Hosp, Dept Hepatobiliary Surg, Foshan, Peoples R China 17.Shanghai Publ Hlth Clin Ctr, Dept Intervent Radiol, Shanghai, Peoples R China 18.Guangdong Gen Hosp, Guangdong Acad Med Sci, Dept Radiol, Guangzhou, Peoples R China 19.Lanzhou Univ, Sch Basic Med Sci, Evidence Based Med Ctr, Lanzhou, Peoples R China 20.Southern Med Univ, Nanfang Hosp, Dept Hepatol Unit, Guangzhou, Peoples R China 21.Southern Med Univ, Nanfang Hosp, Infect Dis, Guangzhou, Peoples R China 22.Sun Yat Sen Univ, Affiliated Hosp 1, Organ Transplant Ctr, Guangzhou, Peoples R China 23.Tsinghua Univ, Beijing Tsinghua Changgung Hosp, Sch Clin Med, Dept Hepatopancreatobiliary Surg, Beijing, Peoples R China 24.Chinese Acad Sci, Inst Automat, Key Lab Mol Imaging, Beijing, Peoples R China 25.Chinese Peoples Liberat Army Gen Hosp, Dept Intervent Ultrasound, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Yanna,Ning, Zhenyuan,Ormeci, Necati,et al. Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis[J]. CLINICAL GASTROENTEROLOGY AND HEPATOLOGY,2020,18(13):2998-+.
APA	Liu, Yanna.,Ning, Zhenyuan.,Ormeci, Necati.,An, Weimin.,Yu, Qian.,...&Qi, Xiaolong.(2020).Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis.CLINICAL GASTROENTEROLOGY AND HEPATOLOGY,18(13),2998-+.
MLA	Liu, Yanna,et al."Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis".CLINICAL GASTROENTEROLOGY AND HEPATOLOGY 18.13(2020):2998-+.