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

Abstract

Objective: 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).

Material and methods: 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.

Results: 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.

Conclusions: 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.

Keywords: algorithms; area under the curve; lung neoplasms; machine learning; magnetic resonance imaging.

Figure 1

Segmentation of a nodule in the upper right lobe on T2-weighted images.

Figure 2

Flow chart for the data processing.

Figure 3

Combination of the pipelines for radiomics analysis.

Figure 4

AUC heat map in each dataset showed the performance of 2D and 3D features combined with different machine learning methods in distinguishing solitary pulmonary lesions. It can be clearly seen that the 3D feature group has much more machine learning combinations with higher AUC than 2D feature group in the test dataset. AB, Adaboost; AE, auto-encoder; ANOVA, analysis of variance; DT, decision tree; FN, feature numbers; GP, Gaussian process; LASSO, least absolute shrinkage and selection operator; LDA, linear discriminant analysis; LR, logistic regression; NB, naive Bayes; PCA, principal component analysis; PCC, Pearson correlation coefficient; RF, random forest; RFE, recursive feature elimination; SVM, support vector machine; Unitnorm, Min-max Normalization; Unit with Zerocenter, Mean Normalization; Zscorenorm, Z-score normalization.

Figure 5

Receiver operating characteristic curves for 2D features, 2D + clinical features, 2D + 3D features, 3D features, and 3D + clinical features in distinguishing malignant from benign solitary pulmonary lesions.

Figure 6

The precision-recall plots of optimal models based on different features.