Wan Qi, Zhou Jiaxuan, Xia Xiaoying, Hu Jianfeng, Wang Peng, Peng Yu, Zhang Tianjing, Sun Jianqing, Song Yang, Yang Guang, Li Xinchun
Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
Philips Healthcare, Guangzhou, China.
Front Oncol. 2021 Nov 18;11:683587. doi: 10.3389/fonc.2021.683587. eCollection 2021.
To 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).
A 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.
The 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.
After 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.
基于磁共振（MR）T2加权成像（T2WI），评估二维和三维影像组学特征结合不同机器学习方法对脾脏病变（SPL）进行分类的性能。
共纳入132例经病理证实的SPL患者，随机分为训练组（n = 92）和测试组（n = 40）。每位患者共提取1692个三维和1231个二维影像组学特征。对影像组学特征和临床数据进行评估。比较了总共1260个分类模型，包括3种归一化方法、2种降维算法、3种特征选择方法以及10个分类器，每个分类器使用7种不同数量的特征（限制在3 - 9个）。在训练数据集上采用十折交叉验证来选择候选最终模型。采用受试者操作特征曲线（AUC）下面积、精确召回率图和马修斯相关系数来评估机器学习方法的性能。
三维特征显著优于二维特征，在验证组和测试组中，三维特征有更多机器学习组合的AUC大于0.7（分别为129个和11个）。特征选择方法方差分析（ANOVA）、递归特征消除（RFE）以及分类器逻辑回归（LR）、线性判别分析（LDA）、支持向量机（SVM）、高斯过程（GP）表现相对较好。测试数据集中三维影像组学特征的最佳性能（AUC = 0.824，AUC-PR = 0.927，MCC = 0.514）高于二维特征（AUC = 0.740，AUC-PR = 0.846，MCC = 0.404）。联合三维和二维特征（AUC = 0.813，AUC-PR = 0.926，MCC = 0.563）与三维特征结果相似。将临床特征与三维和二维影像组学特征相结合，AUC分别略有提高至0.836（AUC-PR = 0.918，MCC = 0.620）和0.780（AUC-PR = 0.900，MCC = 0.574）。
经过算法优化，基于二维特征的影像组学模型在鉴别恶性和良性SPL方面取得了良好结果，但由于有更多性能更好的机器学习算法组合，三维特征仍然更受青睐。在本研究中，特征选择方法ANOVA和RFE以及分类器LR、LDA、SVM和GP更有可能在三维特征上表现出更好的诊断性能。
