Table 1.
Study and comparison of the proposed method and various deep learning and machine learning methods
Method | Patch size | Type | DSC | PPV | Sensitivity |
---|---|---|---|---|---|
Proposed | 16 × 64 | Meningioma | 0.84 | 0.88 | 0.89 |
16 × 32 | 0.83 | 0.85 | 0.87 | ||
16 × 16 | 0.81 | 0.82 | 0.83 | ||
16 × 64 | Glioma | 0.82 | 0.84 | 0.86 | |
16 × 32 | 0.81 | 0.825 | 0.85 | ||
16 × 16 | 0.78 | 0.80 | 0.81 | ||
0.85 | 0.86 | ||||
CNN [27] | 16 × 16 | Glioma | 0.88 | 0.89 | 0.92 |
SVM [5] | Glioma | 0.80 | 0.81 | 0.82 | |
KNN, SVM [18] | Various | 0.81 | 0.815 | 0.83 | |
ANN [23] | Various | 0.83 | 0.82 | 0.84 | |
RescueNet [32] | Gliomas | 0.94 | 0.85 | 0.88 | |
3D-GAN [33] | Gliomas | 0.87 | 0.88 | 0.88 |