目的:本研究旨在评估深度迁移学习(DTL)和临床影像组学在区分胸腺瘤和胸腺囊肿方面的可行性和有效性。
方法:回顾性收集196例经病理诊断为胸腺瘤和胸腺囊肿的患者的临床和影像学资料。(训练队列:n=137;内部验证队列:n=59)。一个独立的外部验证队列包括来自中心2的68名胸腺瘤和胸腺囊肿患者。在对比增强胸部计算机断层扫描(CT)图像上进行感兴趣区域(ROI)勾画,构建了八个DTL模型,包括Densenet169,MobilenetV2,Resnet101,Resnet18,Resnet34,Resnet50,Vgg13,Vgg16。从胸腺瘤和胸腺囊肿患者的CT图像的ROI中提取影像组学特征,使用观察者内相关系数(ICC)进行特征选择,Spearman相关分析,和最小绝对收缩和选择算子(LASSO)算法。单变量分析和多变量逻辑回归(LR)用于选择临床放射学特征。六个机器学习分类器,包括LR,支持向量机(SVM),k-最近邻(KNN),光梯度升压机(LightGBM),自适应提升(AdaBoost),和多层感知器(MLP),用于构建影像组学和临床放射学模型。将来自影像组学和临床放射学模型的选定特征融合以构建组合模型。接收机工作特性曲线(ROC),校正曲线,和决策曲线分析(DCA)用于评价歧视,校准,和模型的临床实用性,分别。Delong检验用于比较不同模型之间的AUC。K均值聚类用于将胸腺瘤或胸腺囊肿的病变细分为亚区域,和传统的影像组学方法用于提取特征,并使用相关分析比较影像组学和DTL模型反映肿瘤内异质性的能力。
结果:基于DTL的Densenet169表现最好,内部验证队列AUC为0.933(95%CI:0.875-0.991),外部验证队列AUC为0.962(95%CI:0.923-1.000).AdaBoost分类器在内部和外部验证队列中实现了0.965(95%CI:0.923-1.000)和0.959(95%CI:0.919-1.000)的AUC,分别,用于Radiomics模型。在临床放射学模型中,LightGBM分类器的AUC为0.805(95%CI:0.690-0.920)和0.839(95%CI:0.736-0.943)。内部和外部验证队列中联合模型的AUC为0.933(95%CI:0.866-1.000)和0.945(95%CI:0.897-0.994),分别。德隆测试的结果表明,Radiomics模型,DTL模型,联合模型在内部和外部验证队列中均优于临床放射学模型(内部验证队列中的p值分别为0.002、0.004和0.033,而在外部验证队列中,p值分别为0.014、0.006和0.015)。但三个模型之间的性能没有统计学差异(所有p值<0.05)。相关分析表明,在量化胸腺瘤和胸腺囊肿之间的瘤内异质性差异方面,放射组学的表现优于DTL。
结论:开发的DTL模型和基于影像组学和临床放射学特征的组合模型在区分胸腺囊肿和胸腺瘤方面取得了优异的诊断性能。它们可以作为辅助临床决策的潜在工具,特别是当内窥镜活检具有高风险时。
This study aims to evaluate the feasibility and effectiveness of deep transfer learning (DTL) and clinical-radiomics in differentiating thymoma from thymic cysts.
Clinical and imaging data of 196 patients pathologically diagnosed with thymoma and thymic cysts were retrospectively collected from center 1. (training cohort: n = 137; internal validation cohort: n = 59). An independent external validation cohort comprised 68 thymoma and thymic cyst patients from center 2. Region of interest (ROI) delineation was performed on contrast-enhanced chest computed tomography (CT) images, and eight DTL models including Densenet 169, Mobilenet V2, Resnet 101, Resnet 18, Resnet 34, Resnet 50, Vgg 13, Vgg 16 were constructed. Radiomics features were extracted from the ROI on the CT images of thymoma and thymic cyst patients, and feature selection was performed using intra-observer correlation coefficient (ICC), Spearman correlation analysis, and least absolute shrinkage and selection operator (LASSO) algorithm. Univariate analysis and multivariable logistic regression (LR) were used to select clinical-radiological features. Six machine learning classifiers, including LR, support vector machine (SVM), k-nearest neighbors (KNN), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), and Multilayer Perceptron (MLP), were used to construct Radiomics and Clinico-radiologic models. The selected features from the Radiomics and Clinico-radiologic models were fused to build a Combined model. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical utility of the models, respectively. The Delong test was used to compare the AUC between different models. K-means clustering was used to subdivide the lesions of thymomas or thymic cysts into subregions, and traditional radiomics methods were used to extract features and compare the ability of Radiomics and DTL models to reflect intratumoral heterogeneity using correlation analysis.
The Densenet 169 based on DTL performed the best, with AUC of 0.933 (95% CI: 0.875-0.991) in the internal validation cohort and 0.962 (95% CI: 0.923-1.000) in the external validation cohort. The AdaBoost classifier achieved AUC of 0.965 (95% CI: 0.923-1.000) and 0.959 (95% CI: 0.919-1.000) in the internal and external validation cohorts, respectively, for the Radiomics model. The LightGBM classifier achieved AUC of 0.805 (95% CI: 0.690-0.920) and 0.839 (95% CI: 0.736-0.943) in the Clinico-radiologic model. The AUC of the Combined model in the internal and external validation cohorts was 0.933 (95% CI: 0.866-1.000) and 0.945 (95% CI: 0.897-0.994), respectively. The results of the Delong test showed that the Radiomics model, DTL model, and Combined model outperformed the Clinico-radiologic model in both internal and external validation cohorts (p-values were 0.002, 0.004, and 0.033 in the internal validation cohort, while in the external validation cohort, the p-values were 0.014, 0.006, and 0.015, respectively). But there was no statistical difference in performance among the three models (all p-values <0.05). Correlation analysis showed that radiomics performed better than DTL in quantifying intratumoral heterogeneity differences between thymoma and thymic cysts.
The developed DTL model and the Combined model based on radiomics and clinical-radiologic features achieved excellent diagnostic performance in differentiating thymic cysts from thymoma. They can serve as potential tools to assist clinical decision-making, particularly when endoscopic biopsy carries a high risk.