基于CT图像的人体脂肪成分及影像组学在肝硬化不良结局预测中的应用

doi:10.19871/j.cnki.xfcrbzz.2025.04.010

摘要/Abstract

摘要： 目的探讨CT图像的人体脂肪成分分析在肝硬化患者中预测不良结局的价值,并联合肝脾影像组学模型,以提升风险评估能力。方法回顾性纳入243例2016年9月至2020年12月来自新疆维吾尔自治区中医院（184例）与香港中文大学（深圳）附属第二医院（59例）的肝硬化患者,其中包括153例病毒性肝炎相关肝硬化。所有患者根据随访期间（≥3个月）是否发生自发性细菌性腹膜炎等严重并发症分为无不良结局组（n=119）和不良结局组（n=124）;在第三腰椎水平定量测量脂肪成分,并提取肝脾区域的影像组学特征,构建多种机器学习模型评估其预测性能。结果脂肪模型在新疆维吾尔自治区中医院与香港中文大学（深圳）附属第二医院的受试者操作特征曲线（receiver operating characteristic curve,ROC曲线）的曲线下面积（area under the curve,AUC）分别为0.804和0.749,优于影像组学模型（AUC=0.767和0.712）;沙普利加性解释法（Shapley additive explanations,SHAP）结果显示,肌间隙脂肪体积比例和皮下脂肪体积是主要预测因子;联合模型的预测效能则有显著提升（AUC=0.856和0.780;综合判别改善指数=0.125, 0.163,P<0.05）。结论人体脂肪成分在肝炎相关肝硬化患者中可有效预测发生不良结局的风险,结合肝脾影像组学特征可进一步提升评估准确性,有望为病毒性肝病的个体化管理与早期干预提供新策略。

关键词: 肝硬化, 预后预测, 计算机断层扫描, 脂肪组织, 机器学习

Abstract: Objective This study aimed to explore the predictive efficacy of body adipose composition analysis using CT imaging for adverse outcomes in patients with cirrhosis and to enhance predictive performance by integrating a radiomics model based on liver and spleen regions. Method 243 patients with liver cirrhosis were retrospectively enrolled from two centers between September 2016 and December 2020, including 153 cases of hepatitis B or C virus-related cirrhosis. Patients were classified into non-adverse outcome group (n=119) and adverse outcome group (n=124) based on the occurrence of severe complications such as spontaneous bacterial peritonitis during the follow-up period (over 3 months). Quantitative measurements of body adipose composition were performed at the third lumbar vertebra level, and radiomic features of the liver and spleen were extracted. Multiple machine learning models were developed to evaluate predictive performance. Result The area under the receiver operating characteristic curve (AUC) for the adipose tissue model at the two centers was 0.804 and 0.749, respectively, outperforming the radiomics model (AUC=0.767 and 0.712). Shapley additive explanations (SHAP) analysis identified intermuscular fat ratio and subcutaneous fat volume as key predictors of adverse outcomes. The predictive efficacy of the combined model was significantly improved (AUC=0.856 and 0.780; integrated discrimination improvement index=0.125, 0.163, P<0.05). Conclusion body adipose composition can effectively predict the risk of adverse outcomes in patients with viral hepatitis-related cirrhosis. The integration of liver and spleen radiomics features further enhances predictive accuracy, offering a promising approach for individualized risk management and early intervention in viral liver diseases.

Key words: Liver cirrhosis, Prognostic prediction, Computed tomography, Adipose Tissue, Machine learning

中图分类号:

R575.2

谢囡霭, 梁译文, 罗梓欣, 邹观南, 郭峰, 蒋奕. 基于CT图像的人体脂肪成分及影像组学在肝硬化不良结局预测中的应用[J]. 新发传染病电子杂志, 2025, 10(4): 58-64.

Xie Nan'ai, Liang Yiwen, Luo Zixin, Zou Guannan, Guo Feng, Jiang Yi. Application of CT-based body adipose composition and radiomics in predicting adverse outcomes in patients with cirrhosis[J]. Electronic Journal of Emerging Infectious Diseases, 2025, 10(4): 58-64.

参考文献

[1] YE F, ZHAI M, LONG J, et al.The burden of liver cirrhosis in mortality: Results from the global burden of disease study[J].Front Public Health,2022,10:909455
[2] SEPANLOU SG, SAFIRI S, BISIGNANO C, et al.The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017[J].Lancet Gastroenterol Hepatol,2020,5(3):245-266.
[3] ZHOU J, SUN HC, WANG Z, et al.Guidelines for the diagnosis and treatment of primary liver cancer (2022 edition)[J].Liver Cancer,2023,12(5):405-444.
[4] FLEMING KM, AITHAL GP, CARD TR, et al.The rate of decompensation and clinical progression of disease in people with cirrhosis: a cohort study[J].Aliment Pharm Ther,2010,32(11-12):1343-1350.
[5] D'AMICO G, GARCIA-TSAO G, PAGLIARO L. Natural history and prognostic indicators of survival in cirrhosis: A systematic review of 118 studies[J].J Hepatol,2006,44(1):217-231.
[6] WAGNER R, ECKSTEIN SS, YAMAZAKI H, et al.Metabolic implications of pancreatic fat accumulation[J].Nat Rev Endocrinol,2022,18(1):43-54.
[7] EBADI M, DUNICHAND-HOEDL A R, RIDER E, et al. Higher subcutaneous adipose tissue radiodensity is associated with increased mortality in patients with cirrhosis[J].Jhep Rep,2022,4(7):100495.
[8] ZOU WY, ENCHAKALODY BE, ZHANG P, et al.Automated measurements of body composition in abdominal CT scans using artificial intelligence can predict mortality in patients with cirrhosis[J].Hepatol Commun,2021,5:1901-1910.
[9] YOO J, CHO H, LEE DH, et al.Prognostic role of computed tomography analysis using deep learning algorithm in patients with chronic hepatitis B viral infection[J].Clin Mol Hepatol,2023,29(4):1029.
[10] MALAKEH M, SHAHROKH AR, MOHAMAD S, et al.Design and Validation of Synchronous QCT Calibration Phantom: Practical Methodology[J].J Med Imaging Radiat,2019,50(1):157-162.
[11] KOTOWSKI K, KUCHARSKI D, MACHURA B, et al.Detecting liver cirrhosis in computed tomography scans using clinically-inspired and radiomic features[J].Comput Biol Med,2023,152:106378.
[12] WANG JC, FU R, TAO XW, et al.A radiomics-based model on non-contrast CT for predicting cirrhosis: make the most of image data[J].Biomark Res,2020,8(1):1-12.
[13] 林勇, 曾欣, 胡平方. 中国肝硬化临床诊治共识意见[J].临床肝胆病杂志,2023,39(9):2057-2073.
[14] LEE M O, CHOI YH, SHIN EC, et al.Hepatitis B virus X protein induced expression of interleukin 18 (IL-18): a potential mechanism for liver injury caused by hepatitis B virus (HBV) infection[J]. J Hepatol,2002,37(3):380-386.
[15] SHI Y, CHIEN N, FONG A, et al.Differential Characteristics and Survival Outcomes of Patients With Cirrhosis According to Underlying Liver Aetiology[J].Aliment Pharm Ther,2025,61(10):1622-1634.
[16] GOODPASTER BH, BERGMAN BC, BRENNAN AM, et al.Intermuscular adipose tissue in metabolic disease[J].Nat Rev Endocrinol,2023,19(5):285-298.
[17] KHAN IM, PERRARD XYD, BRUNNER G, et al.Intermuscular and perimuscular fat expansion in obesity correlates with skeletal muscle T cell and macrophage infiltration and insulin resistance[J].Int J Obesity,2015,39(11):1607-1618.
[18] MA JD, YU SZ, WANG FJ, et al.MicroRNA Transcriptomes Relate Intermuscular Adipose Tissue to Metabolic Risk[J].Int J Mol Sci,2013,14(4):8611-8624.
[19] EBADI M, BHANJI RA, TANDON P, et al.Review article: prognostic significance of body composition abnormalities in patients with cirrhosis[J].Aliment Pharm Ther,2020,52(4):600-618.
[20] KANG SH, KIM M, JEONG WK, et al.Prognostic effect of subcutaneous adipose tissue on survival outcome in patients with liver cirrhosis[J]. J Hepatol,2019,70(1):E654.
[21] ZHU MH, LI HY, YIN Y, et al.U-shaped relationship between subcutaneous adipose tissue index and mortality in liver cirrhosis[J].J Cachexia Sarcopeni,2023,14:508-516.
[22] FUCHS A, SAMOVSKI D, SMITH GI, et al.Associations Among Adipose Tissue Immunology, Inflammation, Exosomes and Insulin Sensitivity in People With Obesity and Nonalcoholic Fatty Liver Disease[J].Gastroenterology,2021,161(3):968-981.
[23] ENGELMANN C, AEHLING NF, SCHOB S, et al.Body fat composition determines outcomes before and after liver transplantation in patients with cirrhosis[J].Hepatol Commun,2022,6(8):2198-2209.
[24] GAGGINI M, CARLI F, GASTALDELLI A.The color of fat and its central role in the development and progression of metabolic diseases[J].Horm Mol Biol Clin I,2017,31(1):20170060.