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

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

Computational and Mathematical Methods in Medicine

fig7

Figure 7

Figure 7: Computer-Aided Lung Nodule Recognition by SVM Classifier Based on Combination of Random Undersampling and SMOTE 