TY - JOUR
T1 - Deep Convolutional Neural Network-Aided Detection of Portal Hypertension in Patients With Cirrhosis
AU - Liu, Yanna
AU - Ning, Zhenyuan
AU - Örmeci, Necati
AU - An, Weimin
AU - Yu, Qian
AU - Han, Kangfu
AU - Huang, Yifei
AU - Liu, Dengxiang
AU - Liu, Fuquan
AU - Li, Zhiwei
AU - Ding, Huiguo
AU - Luo, Hongwu
AU - Zuo, Changzeng
AU - Liu, Changchun
AU - Wang, Jitao
AU - Zhang, Chunqing
AU - Ji, Jiansong
AU - Wang, Wenhui
AU - Wang, Zhiwei
AU - Wang, Weidong
AU - Yuan, Min
AU - Li, Lei
AU - Zhao, Zhongwei
AU - Wang, Guangchuan
AU - Li, Mingxing
AU - Liu, Qingbo
AU - Lei, Junqiang
AU - Liu, Chuan
AU - Tang, Tianyu
AU - Akçalar, Seray
AU - Çelebioğlu, Emrecan
AU - Üstüner, Evren
AU - Bilgiç, Sadık
AU - Ellik, Zeynep
AU - Asiller, Özgün Ömer
AU - Liu, Zaiyi
AU - Teng, Gaojun
AU - Chen, Yaolong
AU - Hou, Jinlin
AU - Li, Xun
AU - He, Xiaoshun
AU - Dong, Jiahong
AU - Tian, Jie
AU - Liang, Ping
AU - Ju, Shenghong
AU - Zhang, Yu
AU - Qi, Xiaolong
N1 - Publisher Copyright:
© 2020 AGA Institute
PY - 2020/12
Y1 - 2020/12
N2 - 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).
AB - 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).
KW - AI
KW - Deep Learning
KW - Diagnostic
KW - HVPG
UR - http://www.scopus.com/inward/record.url?scp=85086133812&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086133812&partnerID=8YFLogxK
U2 - 10.1016/j.cgh.2020.03.034
DO - 10.1016/j.cgh.2020.03.034
M3 - Article
C2 - 32205218
AN - SCOPUS:85086133812
SN - 1542-3565
VL - 18
SP - 2998-3007.e5
JO - Clinical Gastroenterology and Hepatology
JF - Clinical Gastroenterology and Hepatology
IS - 13
ER -