Computer-Aided Lung Nodule Recognition by SVM Classifier Based on Combination of Random Undersampling and SMOTE

<div>Original data distributions of 2D and 3D features. (a) Original data distribution of 2D features of circularity and elongation. (b) Original data distribution of 2D features of compactness and moment. (c) Original data distribution of 3D features of surface-area and volume. (d) Original data distribution of 3D features of sphericity and centroid-offset.</div>

Computational and Mathematical Methods in Medicine

fig6

Figure 6

Figure 6: Computer-Aided Lung Nodule Recognition by SVM Classifier Based on Combination of Random Undersampling and SMOTE 