Table 5.
Main techniques and comparative analysis of the selected four-type classification. U: User-defined features. G: Generic features. D: deep features. 3D: 3D features. O: other methods. Acc: accuracy. Sen: sensitivity. Spe: specificity.
| Author | Year | Database | Features | Classifier | Performance |
|---|---|---|---|---|---|
| Liu et al. [18] | 2018 | LIDC-IDRI, ELCAP | U, D, 3D | CNNs | Acc: 92.3% and 90.3% |
| Yuan et al. [96] | 2018 | U, G, D, 3D | SVM | Acc: 93.1% and 93.9% | |
| Mao et al. [95] | 2018 | ELCAP | U, D | Softmax | Acc: 95.5% |
| Mao et al. [99] | 2016 | ELCAP | U | SVM, clustering | Acc: over 90% |
| Mao et al. [107] | 2016 | ELCAP | G | Ensemble classifier | Acc: 92% |
| Zhang et al. [70] | 2014 | ELCAP | U, G | SVM, pLSA | Acc: 89% |
| Zhang et al. [132] | 2014 | ELCAP | O | Acc: about 88% | |
| Zhang et al. [102] | 2013 | ELCAP | U | SVM | Acc: 82.5% |
| Zhang et al. [17] | 2013 | ELCAP | G | CPMw | Precision: 0.916 |
| Song et al. [71] | 2012 | ELCAP | U, G | SVM | Acc: about 87.5% |
| Farag et al. [76] | 2010 | ELCAP | G | LDA | Acc: 81.5% |
| Farag et al. [72] | 2010 | ELCAP | G | LDA | Acc: 78.23% |