摘要
目的探索基于B型超声影像与临床实验室指标构建血吸虫病肝纤维化分级诊断模型的可行性。方法收集2018—2022年江西省都昌县第二人民医院血吸虫病患者超声影像及临床实验室数据。以血吸虫病肝纤维化Ⅰ级病例为第1组,Ⅱ级和Ⅲ级病例为第2组;选取2018—2021年病例数据为训练集、2022年病例数据为验证集,构建机器学习二分类模型。采用ITK-SNAP软件标记影像特征,采用Python 3.7编程语言和PyRadiomics工具包提取影像特征。采用t检验或Mann-Whitney U检验比较两组样本间影像特征差异,并采用套索算法(least absolute shrinkage and selection operator,LASSO)进行关键影像特征筛选。采用Scikit-learn机器学习库进行机器学习建模,包括支持向量机(support vector machine,SVM)、随机森林(random forest,RF)、线性回归(linear regression,LR)和极端梯度提升(extreme gradient boosting,XGBoost)等4种模型。采用受试者工作特征曲线(receiver operating characteristic curve,ROC)进行最优机器学习模型筛选,并使用沙普利加和解释(SHapley Additive exPlanations,SHAP)评估对机器学习模型中超声影像鉴别特征贡献度最高的特征。结果2019—2022年,累计将491例血吸虫病患者超声影像和临床实验室检查数据纳入研究。累计提取了851项影像组学特征和54项临床实验室指标,经统计学检验(t=-5.98~4.80,U=6550~20994,P均<0.05)及LASSO回归特征筛选,纳入44项特征或指标进入下一步研究。临床实验室指标SVM机器学习模型训练集和验证集ROC曲线下面积(area under curve,AUC)分别为0.763和0.611,超声影像组学SVM机器学习模型训练集和验证集AUC分别为0.951和0.892,多模态SVM机器学习模型训练集和验证集AUC分别为0.960和0.913。机器学习模型中贡献度居前10位的特征或指标包括2项临床实验室指标和8项影像组学特征。结论超声影像组学和临床实验室指标相结合的多模态机器学习模型可用于血吸虫病肝纤维化智能识别,并可提升单类数据模型的分类效果。
Objective To investigate the feasibility of developing a grading diagnostic model for schistosomiasis-induced liver fibrosis based on B-mode ultrasonographic images and clinical laboratory indicators.Methods Ultrasound images and clinical laboratory testing data were captured from schistosomiasis patients admitted to the Second People's Hospital of Duchang County,Jiangxi Province from 2018 to 2022.Patients with grade Ⅰ schistosomiasis-induced liver fibrosis were enrolled in Group1,and patients with grade Ⅱ and Ⅲ schistosomiasis-induced liver fibrosis were enrolled in Group 2.The machine learning binary classification tasks were created based on patients' radiomics and clinical laboratory data from 2018 to 2021 as the training set,and patients' radiomics and clinical laboratory data in 2022 as the validation set.The features of ultrasonographic images were labeled with the ITK-SNAP software,and the features of ultrasonographic images were extracted using the Python 3.7 package and PyRadiomics toolkit.The difference in the features of ultrasonographic images was compared between groups with t test or Mann-Whitney U test,and the key imaging features were selected with the least absolute shrinkage and selection operator(LASSO) regression algorithm.Four machine learning models were created using the Scikit-learn repository,including the support vector machine(SVM),random forest(RF),linear regression(LR) and extreme gradient boosting(XGBoost).The optimal machine learning model was screened with the receiver operating characteristic curve(ROC),and features with the greatest contributions to the differentiation features of ultrasound images in machine learning models with the SHapley Additive exPlanations(SHAP) method.Results The ultrasonographic imaging data and clinical laboratory testing data from 491 schistosomiasis patients from 2019 to 2022 were included in the study,and a total of 851 radiomics features and 54 clinical laboratory indicators were captured.Following statistical tests(t =-5.98 to 4.80,U = 6 550 to 20 994,all P values < 0.05) and screening of key features with LASSO regression,44 features or indicators were included for the subsequent modeling.The areas under ROC curve(AUCs) were 0.763 and 0.611 for the training and validation sets of the SVM model based on clinical laboratory indicators,0.951and 0.892 for the training and validation sets of the SVM model based on radiomics,and 0.960 and 0.913 for the training and validation sets of the multimodal SVM model.The 10 greatest contributing features or indicators in machine learning models included2 clinical laboratory indicators and 8 radiomics features.Conclusions The multimodal machine learning models created based on ultrasound-based radiomics and clinical laboratory indicators are feasible for intelligent identification of schistosomiasis-induced liver fibrosis,and are effective to improve the classification effect of one-class data models.
作者
郭照宇
邵菊萍
邹小青
赵琴平
钱沛君
王文雅
黄璐璐
薛靖波
许静
杨坤
周晓农
李石柱
GUO Zhaoyu;SHAO Juping;ZOU Xiaoqing;ZHAO Qinping;QIAN Peijun;WANG Wenya;HUANG Lulu;XUE Jingbo;XU Jing;YANG Kun;ZHOU Xiaonong;LI Shizhu(National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases,National Institute of Parasitic Diseases,Chinese Center for Disease Control and Prevention(Chinese Center for Tropical Diseases Research),National Health Commission Key Laboratory of Parasite and Vector Biology,WHO Collaborating Centre for Tropical Diseases,National Center for International Research on Tropical Diseases,Ministry of Science and Technology,Shanghai 200025,China;The Second People’s Hospital of Duchang County,Jiujiang City,Jiangxi Province,China;School of Basic Medical Sciences,Wuhan University,China;National Health Commission Key Laboratory on Parasitic Disease Control and Prevention,Jiangsu Provincial Key Laboratory on Parasite and Vector Control Technology,Jiangsu Institute of Parasitic Diseases,China;School of Global Health,Shanghai Jiao Tong University School of Medicine and Chinese Center for Tropical Diseases Research,Shanghai 200025,China)
出处
《中国血吸虫病防治杂志》
CAS
CSCD
北大核心
2024年第3期251-258,共8页
Chinese Journal of Schistosomiasis Control
基金
国家重点研发计划(2021YFC2300800,2021YFC2300804)
国家自然科学基金(32161143036,32311540013)
“一带一路”澜湄热带病防控联合实验室项目(21410750200)
上海市加强公共卫生体系建设三年行动计划(2023—2025年)重点学科项目。
关键词
血吸虫病
肝纤维化
超声影像
影像组学
诊断模型
Schistosomiasis
Liver fibrosis
Ultrasound imaging
Radiomics
Diagnostic model
