基于胰腺CT的影像组学在预测糖耐量受损人群胰岛素抵抗中的应用价值  

Application value of pancreatic CT-based radiomics in predicting insulin resistance in people with impaired glucose tolerance

作　　者：布买丽亚木·买买提艾力 陈杰[1] Bumailiyamu Maimaitiaili;CHEN Jie(Department of Radiology and Medical Imaging,People’s Hospital of Xinjiang Uygur Autonomous Region,Urumqi 830001,China;Graduate School,Xijiang Medical University,Urumqi 830054,China)

机构地区：[1]新疆维吾尔自治区人民医院放射影像中心,新疆乌鲁木齐830001 [2]新疆医科大学研究生院,新疆乌鲁木齐830054

出　　处：《中国中西医结合影像学杂志》2024年第3期250-254,281,共6页Chinese Imaging Journal of Integrated Traditional and Western Medicine

基　　金：新疆维吾尔自治区自然科学基金(2022D01C137)。

摘　　要：目的:探讨基于CT胰腺平扫影像组学在预测糖耐量受损人群胰岛素抵抗(IR)中的应用价值。方法:回顾性收集首次确诊的糖耐量受损患者381例,依据稳态模型胰岛素抵抗指数(HOMA-IR)中位数,分为高IR组191例,低IR组190例;并按照8∶2的比例,随机分成训练集304例及测试集77例。勾画胰腺ROI,提取影像组学特征,通过降维和筛选后,选择最优特征。构建8种机器学习模型,并选取支持向量机(SVM)、多层感知机(MLP)、随机森林(RF)、自适应提升算法(AdaBoost)4种机器学习方法构建诊断预测模型。采用ROC曲线评价各影像组学模型的预测效能。结果:共提取1834个特征,采用Pearson相关系数分析筛选保留189个特征。通过最小绝对收缩和选择算子(LASSO)算法和5折交叉验证降维至23个主要组学特征。构建的SVM、MLP、RF、AdaBoost 4种预测模型在测试集中的AUC分别为0.723、0.731、0.807、0.681,其中RF模型的预测效果较好。结论:基于CT胰腺平扫影像组学特征构建的RF模型,对糖耐量受损人群的IR水平具有较好的预测效能。Objective:To explore the application value of pancreatic CT-based radiomics in predicting insulin resistance(IR)in people with impaired glucose tolerance.Methods:A total of 381 patients initially diagnosed with impaired glucose tolerance were retrospectively collected and were divided into two groups based on homeostasis model assessment of IR(HOMA-IR),a high-IR group(191 cases)and a low-IR group(190 cases).And all patients were randomly divided into the training cohort and the validation cohort at a ratio of 8∶2.Pancreatic ROIs were sketched and radiomics features were extracted,and the optimal features were selected after dimensionality reduction and screening.Eight machine learning models were constructed,and four machine learning methods(SVM,MLP,RF and AdaBoost)were selected to construct the diagnostic prediction model.ROC curve was used to evaluate the prediction performance of each radiomics model.Results:A total of 1834 features were extracted and 189 features were screened by Pearson’s correlation analysis.The dimensionality was reduced to 23 major radiomics features by LASSO method and 5-fold cross-validation.The AUCs of the four constructed prediction models based on SVM,MLP,RF and AdaBoost for the validation cohort were 0.723,0.731,0.807 and 0.681,respectively,with the better prediction efficiency of RF.Conclusion:The RF model based on pancreatic CT radiomics features has a better potential prediction for the IR level in people with impaired glucose tolerance.

关 键 词：胰岛素抵抗 影像组学 支持向量机 多层感知机 随机森林 自适应提升算法 体层摄影术 X线计算机 

分 类 号：R587.1[医药卫生—内分泌] R816.5[医药卫生—内科学]