目的 开发一种基于剪切波弹性成像（SWE）影像组学的机器学习（ML）模型,用于预测2型糖尿病（T2DM）合并非酒精性脂肪性肝病（NAFLD）患者进展为肝纤维化的风险,以期可以通过早期非手术干预来减少患者未来需要接受外科手术的风险。方法 回顾性分析218例T2DM合并NAFLD患者的SWE图像资料。利用3D Slicer软件进行肝脏区域的图像分割与影像组学特征提取。在经过特征筛选后,采用随机森林、支持向量机和极端梯度提升（XGBoost）这3种ML算法构建预测模型。模型性能通过受试者工作特征（ROC）曲线、校准曲线及决策曲线分析（DCA）进行评估,以确定最优的ML预测模型。结果 218例患者中,40例（18.3%）初诊肝脏硬度测量值≥6.5 kPa,提示存在肝纤维化风险。通过对每位患者SWE图像进行区域分割,共提取出849个影像组学特征。经过数据标准化和特征筛选后,确定了5个与肝纤维化密切相关的影像组学特征。基于这些影像组学特征构建3种ML模型,其中,XGBoost模型在区分能力上表现最优,ROC曲线下面积达到0.864。校正曲线和DCA曲线提示其预测概率在0.4~0.7范围内时能准确提示患者存在肝纤维化风险。结论 本研究基于肝脏SWE的影像组学特征成功训练并验证了XGBoost模型,证明了其在预测T2DM合并NAFLD患者中肝纤维化进展风险方面的应用潜力。
Objective To develop a machine learning （ML） model based on shear wave elastography （SWE） radiomics for predicting the risk of hepatic fibrosis progression in patients with type 2 diabetes mellitus （T2DM） and non-alcoholic fatty liver disease （NAFLD）, aiming to reduce the necessity for surgery through early non-surgical interventions. Methods A retrospective analysis was performed on SWE image data of 218 patients with T2DM and NAFLD. Liver region image segmentation and radiomics feature extraction were conducted using the 3D Slicer software. After feature selection, random forest, support vector machine, and extreme gradient boosting （XGBoost） were employed to build ML predictive models. The performance of the models was evaluated using receiver operating characteristic （ROC） curves, calibration curves, and decision curve analyses （DCA） to determine the optimal ML predictive model. Results Among the 218 patients, 40 （18.3%） had an initial liver stiffness ≥ 6.5 kPa, indicating a risk of hepatic fibrosis. A total of 849 radiomics features were extracted from each segmented SWE image. After data standardization and feature selection, five radiomics features closely associated with hepatic fibrosis were identified. Three ML models were constructed based on these radiomic features, and the XGBoost model demonstrated optimal discriminatory ability, achieving an area under the ROC curve of 0.864. The calibration curve and DCA curve indicated that the model accurately predicted the risk of hepatic fibrosis when the predicted probability was within the range of 0.4-0.7. Conclusion This study has successfully trained and validated an XGBoost model based on hepatic SWE radiomics features, demonstrating its potential applicability in predicting the risk of hepatic fibrosis progression in T2DM patients with NAFLD.
[1] 刘阳, 陈冉, 于世家, 等. 2型糖尿病合并非酒精性脂肪肝发病机制的研究进展[J]. 基础医学与临床, 2018, 38(8): 1163-1167.
[2] Younossi ZM, Golabi P, de Avila L, et al. The global epidemiology of NAFLD and NASH in patients with type 2 diabetes: a systematic review and meta-analysis[J]. J Hepatol, 2019, 71(4): 793-801.
[3] Taylor RS, Taylor RJ, Bayliss S, et al.Association between fibrosis stage and outcomes of patients with nonalcoholic fatty liver disease: a systematic review and meta-analysis[J]. Gastroenterology, 2020, 158(6): 1611-1625.
[4] 杨薇, 李源, 杨永林. 瞬时弹性成像技术(TE)对肝纤维化诊断价值的研究进展[J]. 中西医结合心血管病电子杂志, 2018, 6(9): 29-30.
[5] 冯源, 兰晓莉. 影像组学介绍[J]. 中华核医学与分子影像杂志, 2023, 43(1): 55-60.
[6] 石镇维, 刘再毅. 影像组学研究的困境和出路[J]. 中华放射学杂志, 2022, 56(1): 9-11.
[7] Sim KC, Kim MJ, Cho Y, et al.Diagnostic feasibility of magnetic resonance elastography radiomics analysis for the assessment of hepatic fibrosis in patients with nonalcoholic fatty liver disease[J]. J Comput Assist Tomogr, 2022, 46(4): 505-513.
[8] D'Souza JC, Sultan LR, Hunt SJ, et al. B-mode ultrasound for the assessment of hepatic fibrosis: a quantitative multiparametric analysis for a radiomics approach[J]. Sci Rep, 2019, 9(1): 8708.
[9] American Diabetes Association.2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes—2020[J]. Diabetes Care, 2020, 43(Suppl 1): S14-S31.
[10] European Association for the Study of the Liver (EASL), European Association for the Study of Diabetes (EASD), European Association for the Study of Obesity (EASO). EASL-EASD-EASO Clinical Practice Guidelines for the management of non-alcoholic fatty liver disease[J]. Diabetologia, 2016, 59(6): 1121-1140.
[11] Siddiqui MS, Vuppalanchi R, Van Natta ML, et al.Vibration-controlled transient elastography to assess fibrosis and steatosis in patients with nonalcoholic fatty liver disease[J]. Clin Gastroenterol Hepatol, 2019, 17(1): 156-163.
[12] Singh S, Allen AM, Wang Z, et al.Fibrosis progression in nonalcoholic fatty liver vs nonalcoholic steatohepatitis: a systematic review and meta-analysis of paired-biopsy studies[J]. Clin Gastroenterol Hepatol, 2015, 13(4): 643-654.
[13] Lee HW, Wong GL, Kwok R, et al.Serial transient elastography examinations to monitor patients with type 2 diabetes: a prospective cohort study[J]. Hepatology, 2020, 72(4): 1230-1241.
[14] Uddin S, Khan A, Hossain ME, et al.Comparing different supervised machine learning algorithms for disease prediction[J]. BMC Med Inform Decis Mak, 2019, 19(1): 281.
[15] Rodríguez-Pérez R, Bajorath J.Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions[J]. J Comput Aided Mol Des, 2020, 34(10):1013-1026.
[16] Delabays C, Demartines N, Joliat GR, et al.Enhanced recovery after liver surgery in cirrhotic patients: a systematic review and meta-analysis[J]. Perioper Med (Lond), 2024, 13(1):24.
[17] Tacke F, Weiskirchen R.An update on the recent advances in antifibrotic therapy[J]. Expert Rev Gastroenterol Hepatol, 2018, 12(11):1143-1152.
