| LEVERAGE PAPER RESULTS SUMMARY | |
| ================================ | |
| Experiment Timestamp: 20251124_180934 | |
| Model Architecture: DEEPL3_UNET | |
| WMH Segmentation: Binary vs Three-class Classification Comparison | |
| DATASET INFORMATION: | |
| -------------------- | |
| Training Images: 2050 | |
| Test Images: 350 | |
| Image Size: (256, 256) | |
| Classes: Background (0), Normal WMH (1), Abnormal WMH (2) | |
| METHODOLOGY: | |
| ------------ | |
| Architecture: DEEPL3_UNET | |
| Loss Functions: | |
| - Scenario 1: weighted_bce | |
| - Scenario 2: weighted_categorical | |
| Training Epochs: 50 | |
| Batch Size: 8 | |
| Learning Rate: 0.0001 | |
| PERFORMANCE RESULTS: | |
| -------------------- | |
| | Scenario 1 (Binary) | Scenario 2 (3-class) | Improvement | |
| --------------------|---------------------|----------------------|------------ | |
| Accuracy | 0.9751 | 0.9915 | +0.0164 | |
| Precision | 0.2306 | 0.4637 | +0.2331 | |
| Recall | 0.9838 | 0.7961 | -0.1876 | |
| Dice Coefficient | 0.3736 | 0.5861 | +0.2125 | |
| IoU Coefficient | 0.2297 | 0.4145 | +0.1848 | |
| STATISTICAL SIGNIFICANCE: | |
| ------------------------- | |
| DICE COEFFICIENT: | |
| Test: Paired t-test | |
| t-statistic: 9.1289 | |
| p-value: 0.0000 | |
| Effect Size (Cohen's d): 0.5655 | |
| 95% Confidence Interval: [0.1278, 0.1983] | |
| Result: SIGNIFICANT improvement | |
| IoU COEFFICIENT: | |
| Test: Paired t-test | |
| t-statistic: 9.2000 | |
| p-value: 0.0000 | |
| Effect Size (Cohen's d): 0.6282 | |
| 95% Confidence Interval: [0.1177, 0.1821] | |
| Result: SIGNIFICANT improvement | |
| KEY FINDINGS: | |
| ------------- | |
| 1. Three-class segmentation shows 72.03% improvement in Dice coefficient | |
| 2. Three-class segmentation shows 99.70% improvement in IoU coefficient | |
| 3. Dice analysis confirms significant improvement | |
| 4. IoU analysis confirms significant improvement | |
| 5. Post-processing provided substantial improvements in both scenarios | |