An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension

doi:10.1016/j.xcrm.2022.100563

	An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension
	Yu, Qian 1; Huang, Yifei 2; Li, Xiaoguo 2; Pavlides, Michael 3; Liu, Dengxiang 4; Luo, Hongwu 5; Ding, Huiguo 6; An, Weimin 7; Liu, Fuquan 8; Zuo, Changzeng 4; Lu, Chunqiang 1; Tang, Tianyu 1; Wang, Yuancheng 1; Huang, Shan 1; Liu, Chuan 2; Zheng, Tianlei 2; Kang, Ning 2; Liu, Changchun 7; Wang, Jitao 4; Akcalar, Seray 9; Celebioglu, Emrecan 9; Ustuner, Evren 9; Bilgic, Sadik 9; Fang, Qu 10; Fu, Chi-Cheng 10; Zhang, Ruiping 11; Wang, Chengyan 12; Wei, Jingwei13,14 ; Tian, Jie 13,14; Ormeci, Necati 15; Ellik, Zeynep 15; Asiller, Ozgun Omer 15; Ju, Shenghong 1; Qi, Xiaolong 2
发表期刊	CELL REPORTS MEDICINE
ISSN	2666-3791
	2022-03-15
卷号	3 期号:3 页码:13
通讯作者	Ju, Shenghong(jsh@seu.edu.cn) ; Qi, Xiaolong(qixiaolong@vip.163.com)
摘要	The hepatic venous pressure gradient (HVPG) is the gold standard for cirrhotic portal hypertension (PHT), but it is invasive and specialized. Alternative non-invasive techniques are needed to assess the hepatic venous pressure gradient (HVPG). Here, we develop an auto-machine-learning CT radiomics HVPG quantitative model (aHVPG), and then we validate the model in internal and external test datasets by the area under the receiver operating characteristic curves (AUCs) for HVPG stages (>10, >12, >16, and >20 mm Hg) and compare the model with imaging-and serum-based tools. The final aHVPG model achieves AUCs over 0.80 and outperforms other non-invasive tools for assessing HVPG. The model shows performance improvement in identifying the severity of PHT, which may help non-invasive HVPG primary prophylaxis when transjugular HVPG measurements are not available.
关键词	venous pressure gradient (HVPG)
DOI	10.1016/j.xcrm.2022.100563
关键词[WOS]	ESOPHAGEAL-VARICES ; SPLEEN STIFFNESS ; ACCURATE MARKER ; FIBROSIS ; RISK ; DIAGNOSIS ; INDEX ; SCORE
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[81830053] ; National Natural Science Foundation of China (NSFC)[61821002]
项目资助者	National Natural Science Foundation of China (NSFC)
WOS研究方向	Cell Biology ; Research & Experimental Medicine
WOS类目	Cell Biology ; Medicine, Research & Experimental
WOS记录号	WOS:000787071300017
出版者	ELSEVIER
引用统计	被引频次：11[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/173211/48423
专题	中国科学院分子影像重点实验室
通讯作者	Ju, Shenghong; Qi, Xiaolong
作者单位	1.Southeast Univ, Zhongda Hosp, Sch Med, Dept Radiol, Nanjing, Peoples R China 2.Lanzhou Univ, Hosp 1, Inst Portal Hypertens, CHESS Ctr, Lanzhou, Peoples R China 3.Univ Oxford, John Radcliffe Hosp, Oxford Ctr Magnet Resonance Res, Radcliffe Dept Med, Oxford, England 4.Xingtai Peoples Hosp, CHESS Working Party, Xingtai, Peoples R China 5.Cent South Univ, Xiangya Hosp 3, Dept Gen Surg, Changsha, Peoples R China 6.Capital Med Univ, Beijing Youan Hosp, Dept Gastroenterol & Hepatol, Beijing, Peoples R China 7.Fifth Med Ctr PLA Gen Hosp, Dept Radiol, Beijing, Peoples R China 8.Capital Med Univ, Beijing Shijitan Hosp, Dept Intervent Therapy, Beijing, Peoples R China 9.Ankara Univ, Sch Med, Dept Radiol, Ankara, Turkey 10.Shanghai Aitrox Technol Corp, Shanghai, Peoples R China 11.Shanxi Med Univ, Hosp 3, Shanxi Bethune Hosp, Dept Radiol, Taiyuan, Shanxi, Peoples R China 12.Fudan Univ, Human Phenome Inst, Shanghai, Peoples R China 13.Chinese Acad Sci, Inst Automat, Key Lab Mol Imaging, Beijing, Peoples R China 14.Beijing Key Lab Mol Imaging, Beijing, Peoples R China 15.Ankara Univ, Sch Med, Dept Gastroenterol, Ankara, Turkey
推荐引用方式 GB/T 7714	Yu, Qian,Huang, Yifei,Li, Xiaoguo,et al. An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension[J]. CELL REPORTS MEDICINE,2022,3(3):13.
APA	Yu, Qian.,Huang, Yifei.,Li, Xiaoguo.,Pavlides, Michael.,Liu, Dengxiang.,...&Qi, Xiaolong.(2022).An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension.CELL REPORTS MEDICINE,3(3),13.
MLA	Yu, Qian,et al."An imaging-based artificial intelligence model for non-invasive grading of hepatic venous pressure gradient in cirrhotic portal hypertension".CELL REPORTS MEDICINE 3.3(2022):13.