DataSheet_1_Diagnostic Performance of 2D and 3D T2WI-Based Radiomics Features With Machine Learning Algorithms to Distinguish Solid Solitary Pulmonary Lesion.csv

ObjectiveTo evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI).
Material and MethodsA total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3–9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches.
ResultsThe 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively.
ConclusionsAfter algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.

研究目的：本研究旨在评估基于磁共振（MR）T2加权成像（T2WI）的二维（2D）与三维（3D）放射组学特征，结合不同机器学习方法对孤立性肺病变（SPLs）进行分类的性能。
材料与方法：本研究共纳入132例经病理证实的SPLs患者，按随机原则分为训练集（n=92）与测试集（n=40）。每位患者共提取1692个3D放射组学特征及1231个2D放射组学特征。同时对放射组学特征与临床资料进行分析。本研究共对比了1260个分类模型，这些模型涵盖3种归一化方法、2种降维算法、3种特征选择方法，以及10种分类器，并分别采用3~9个不同数量的特征。通过在训练集上进行十折交叉验证以筛选候选最终模型。采用受试者工作特征曲线下面积（AUC）、精确率-召回率曲线（PR曲线）以及马修斯相关系数（MCC）评估各机器学习方法的性能。
研究结果：3D放射组学特征的性能显著优于2D特征：在验证集与测试集中，AUC大于0.7的机器学习组合数量更多（分别为129组与11组）。其中，方差分析（ANOVA）、递归特征消除（RFE）这两种特征选择方法，以及逻辑回归（LR）、线性判别分析（LDA）、支持向量机（SVM）、高斯过程（GP）这几种分类器展现出相对更优的性能。3D放射组学特征在测试集上的最优性能（AUC=0.824，AUC-PR=0.927，MCC=0.514）高于2D特征的最优性能（AUC=0.740，AUC-PR=0.846，MCC=0.404）。联合3D与2D特征的模型（AUC=0.813，AUC-PR=0.926，MCC=0.563）性能与3D特征模型相近。将临床特征分别与3D、2D放射组学特征结合后，AUC分别小幅提升至0.836（AUC-PR=0.918，MCC=0.620）与0.780（AUC-PR=0.900，MCC=0.574）。
研究结论：经算法优化后，基于2D特征的放射组学模型在良恶性SPLs鉴别中可取得较好的结果，但由于3D特征可获得更多性能更优的机器学习组合方案，因此仍优先选用3D特征。本研究中，方差分析（ANOVA）、递归特征消除（RFE）两种特征选择方法，以及逻辑回归（LR）、线性判别分析（LDA）、支持向量机（SVM）、高斯过程（GP）四种分类器更易在3D放射组学特征中展现出更优的诊断性能。