Table 2 The performance comparison between the proposed model and some existing models
From: CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images
Models | Year | Number of scans | The nodule size | The number of nodules | Sensitivity |
|---|---|---|---|---|---|
Our model | – | 1010 | Diameter < 3 mm | 2635 | 83.82% |
Jiang et al. [20] | 2017 | 1006 | Diameter > 3 mm | – | 80.06% (with 4.7 false positives per scan) 94.00% (with 15.1 false positives per scan) |
Golan et al. [12] | 2016 | 1018 | Diameter ≥ 3 mm | 204 | 78.9% (with 20 false positives per scan) 71.2% (with 10 false positives per scan) |