Table 3.
Confusion matrix following a gain ratio + SVM classification combination using morphological features only.
| Morphology Features (Surface area, Volume, and Surface-Area-to-Volume Ratio Features) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Class | TP Rate | FP Rate | Precision | Recall | F-Measure | MCC | ROC Area | Confusion Matrix | Accuracy | ||
| HC | PD | PSP-RS | |||||||||
| HC | 0.605 | 0.185 | 0.657 | 0.605 | 0.630 | 0.429 | 0.710 | 23 | 12 | 3 | 65.0% |
| PD | 0.622 | 0.241 | 0.667 | 0.622 | 0.644 | 0.384 | 0.690 | 10 | 28 | 7 | |
| PSP-RS | 0.800 | 0.120 | 0.615 | 0.800 | 0.696 | 0.619 | 0.840 | 2 | 2 | 16 | |
TP, True Positive; FP, False Positive; MCC, Matthews Correlation Coefficient; ROC AUC, Area under the receiver operating characteristic curve; HC, Healthy Controls; PD, Parkinson's disease; PSP-RS, Progressive supranuclear palsy Richardson's syndrome.