Background/Aims The prediction of clinical outcomes in patients with chronic hepatitis B (CHB) is paramount for effective management. This study aimed to evaluate the prognostic value of computed tomography (CT) analysis using deep learning algorithms in patients with CHB. Methods: This retrospective study included 2,169 patients with CHB without hepatic decompensation who underwent contrast-enhanced abdominal CT for hepatocellular carcinoma (HCC) surveillance between January 2005 and June 2016. Liver and spleen volumes and body composition measurements including subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and skeletal muscle indices were acquired from CT images using deep learning-based fully automated organ segmentation algorithms. We assessed the significant predictors of HCC, hepatic decompensation, diabetes mellitus (DM), and overall survival (OS) using Cox proportional hazard analyses. Results: During a median follow-up period of 103.0 months, HCC (n=134, 6.2%), hepatic decompensation (n=103, 4.7%), DM (n=432, 19.9%), and death (n=120, 5.5%) occurred. According to the multivariate analysis, standardized spleen volume significantly predicted HCC development (hazard ratio [HR]=1.01, P=0.025), along with age, sex, albumin and platelet count. Standardized spleen volume (HR=1.01, P<0.001) and VAT index (HR=0.98, P=0.004) were significantly associated with hepatic decompensation along with age and albumin. Furthermore, VAT index (HR=1.01, P=0.001) and standardized spleen volume (HR=1.01, P=0.001) were significant predictors for DM, along with sex, age, and albumin. SAT index (HR=0.99, P=0.004) was significantly associated with OS, along with age, albumin, and MELD. Conclusions: Deep learning-based automatically measured spleen volume, VAT, and SAT indices may provide various prognostic information in patients with CHB.
Citations
Citations to this article as recorded by
Reply to: “A machine learning model to predict liver-related outcomes after the functional cure of chronic hepatitis B: Is cirrhosis driving the performance?” Moon Haeng Hur, Jeong-Hoon Lee Journal of Hepatology.2025; 82(3): e143. CrossRef
Early prediction of adverse outcomes in liver cirrhosis using a CT-based multimodal deep learning model Nanai Xie, Yiwen Liang, Zixin Luo, Jing Hu, Ruiquan Ge, Xiang Wan, Changmiao Wang, Guannan Zou, Feng Guo, Yi Jiang Abdominal Radiology.2025; 51(1): 137. CrossRef
Correspondence to editorial on “Hepatocellular carcinoma prediction model performance decreases with long-term antiviral therapy in chronic hepatitis B patients” Xiaoqian Xu, Hong You, Jidong Jia, Yuanyuan Kong Clinical and Molecular Hepatology.2024; 30(4): 994. CrossRef
Deep learning assisted biomarker development in patients with chronic hepatitis B: Editorial on “Prognostic role of computed tomography analysis using deep learning algorithm in patients with chronic hepatitis B viral infection” Yong Eun Chung Clinical and Molecular Hepatology.2024; 30(4): 669. CrossRef
Decreasing performance of HCC prediction models during antiviral therapy for hepatitis B: what else to keep in mind: Editorial on “Hepatocellular carcinoma prediction model performance decreases with long-term antiviral therapy in chronic hepatitis B pati Beom Kyung Kim Clinical and Molecular Hepatology.2024; 30(4): 656. CrossRef
Assessment of body composition and prediction of infectious pancreatic necrosis via non-contrast CT radiomics and deep learning Bingyao Huang, Yi Gao, Lina Wu Frontiers in Microbiology.2024;[Epub] CrossRef
Jeayeon Park, Sung Won Chung, Yun Bin Lee, Hyunjae Shin, Moon Haeng Hur, Heejin Cho, Min Kyung Park, Jeonghwan Youk, Ji Yun Lee, Jeong-Ok Lee, Su Jong Yu, Yoon Jun Kim, Jung-Hwan Yoon, Tae Min Kim, Jeong-Hoon Lee
Clin Mol Hepatol 2023;29(3):794-809. Published online May 17, 2023
Background/Aims Chronic hepatitis B (CHB) is a risk factor for non-Hodgkin lymphoma (NHL). Our recent study suggested that antiviral treatment may reduce the incidence of NHL in CHB patients. This study compared the prognoses of hepatitis B virus (HBV)-associated diffuse large B-cell lymphoma (DLBCL) patients receiving antiviral treatment and HBV-unassociated DLBCL patients.
Methods This study comprised 928 DLBCL patients who were treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone (R-CHOP) at two referral centers in Korea. All patients with CHB received antiviral treatment. Time-to-progression (TTP) and overall survival (OS) were the primary and secondary endpoints, respectively.
Result s: Among the 928 patients in this study, 82 were hepatitis B surface antigen (HBsAg)-positive (the CHB group) and 846 were HBsAg-negative (the non-CHB group). The median follow-up time was 50.5 months (interquartile range [IQR]=25.6–69.7 months). Multivariable analyses showed longer TTP in the CHB group than the non-CHB group both before inverse probability of treatment weighting (IPTW; adjusted hazard ratio [aHR]=0.49, 95% confidence interval [CI]=0.29–0.82, p=0.007) and after IPTW (aHR=0.42, 95% CI=0.26–0.70, p<0.001). The CHB group also had a longer OS than the non-CHB group both before IPTW (HR=0.55, 95% CI=0.33–0.92, log-rank p=0.02) and after IPTW (HR=0.53, 95% CI=0.32–0.99, log-rank p=0.02). Although liver-related deaths did not occur in the non-CHB group, two deaths occurred in the CHB group due to hepatocellular carcinoma and acute liver failure, respectively.
Conclusions Our findings indicate that HBV-associated DLBCL patients receiving antiviral treatment have significantly longer TTP and OS after R-CHOP treatment than HBV-unassociated DLBCL patients.
Citations
Citations to this article as recorded by
Chronic hepatitis b coinfection and survival in pediatric T-ALL: A propensity-matched analysis Yutong Zhang, Ruihong Wu, Yuan Zhang, Yufei Zhao, Xiaodan Zhong, Xianmei Jin, Chao Zhang, Jian Chang iScience.2026; 29(1): 114319. CrossRef
Letter regarding “Treated chronic hepatitis B is a good prognostic factor of diffuse large B-cell lymphoma” Chi Hsiao, Yung-Po Liaw Clinical and Molecular Hepatology.2023; 30(1): 109. CrossRef
First
Prev
