基于影像组学与临床实验室指标构建血吸虫病肝纤维化分级诊断模型

扫码查看

原文链接

NETL
NSTL
万方数据

中文摘要：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 ma-chine,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=6 550～20 994,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.

外文标题：Development of a grading diagnostic model for schistosomiasis-induced liver fibrosis based on radiomics and clinical laboratory indicators

外文摘要：Objective To investigate the feasibility of developing a grading diagnostic model for schistosomiasis-induced liv-er fibrosis based on B-mode ultrasonographic images and clinical laboratory indicators.Methods Ultrasound images and clini-cal 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 Group 1,and patients with grade Ⅱ and Ⅲ schistosomiasis-induced liver fibrosis were enrolled in Group 2.The machine learning bina-ry 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 pack-age 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 sup-port vector machine(SVM),random forest(RF),linear regression(LR)and extreme gradient boosting(XGBoost).The optimal ma-chine learning model was screened with the receiver operating characteristic curve(ROC),and features with the greatest contribu-tions 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 pa-tients 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 fea-tures 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,0.951 and 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 vali-dation sets of the multimodal SVM model.The 10 greatest contributing features or indicators in machine learning models included 2 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.

外文关键词：

SchistosomiasisLiver fibrosisUltrasound imagingRadiomicsDiagnostic model

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

展开 >

作者单位：

传染病溯源预警与智能决策全国重点实验室、中国疾病预防控制中心寄生虫病预防控制所(国家热带病研究中心)、国家卫生健康委员会寄生虫病原与媒介生物学重点实验室、WHO热带病合作中心、科技部国家级热带病国际联合研究中心(上海 200025)

江西省九江市都昌县第二人民医院

武汉大学基础医学院

国家卫生健康委员会寄生虫病预防与控制技术重点实验室、江苏省寄生虫与媒介控制技术重点实验室、江苏省血吸虫病防治研究所

上海交通大学医学院-国家热带病研究中心全球健康学院(上海 200025)

展开 >

关键词：

血吸虫病肝纤维化超声影像影像组学诊断模型

基金：

国家重点研发计划国家重点研发计划国家自然科学基金国家自然科学基金"一带一路"澜湄热带病防控联合实验室项目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

项目编号：

2021YFC23008002021YFC2300804321611430363231154001321410750200

出版年：

2024

DOI：

10.16250/j.32.1374.2024110

中国血吸虫病防治杂志

中华预防医学会,江苏省血吸虫病防治研究所

中国血吸虫病防治杂志

CSTPCD北大核心

影响因子：1.405

ISSN：1005-6661

年,卷(期)：2024.36(3)