LEVERAGE PAPER RESULTS SUMMARY
    ================================
    Experiment Timestamp: 20251124_171430
    WMH Segmentation: Binary vs Three-class Classification Comparison

    DATASET INFORMATION:
    --------------------
    Training Images: 1044 
    Test Images: 161
    Image Size: (256, 256)
    Classes: Background (0), Normal WMH (1), Abnormal WMH (2)

    METHODOLOGY:
    ------------
    Architecture: Enhanced U-Net with Batch Normalization and Dropout
    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            | 0.9860            | 0.9946             | +0.0086
    Precision           | 0.3462           | 0.6029            | +0.2567
    Recall              | 0.9650              | 0.8342               | -0.1307
    Dice Coefficient    | 0.5096                | 0.7000                 | +0.1904
    IoU Coefficient     | 0.3419                 | 0.5384                  | +0.1965

    STATISTICAL SIGNIFICANCE:
    -------------------------
    DICE COEFFICIENT:
    Test: Paired t-test
    t-statistic: 7.9888
    p-value: 0.0000
    Effect Size (Cohen's d): 0.4778
    95% Confidence Interval: [0.1090, 0.1807]
    Result: SIGNIFICANT improvement

    IoU COEFFICIENT:
    Test: Paired t-test
    t-statistic: 8.5581
    p-value: 0.0000
    Effect Size (Cohen's d): 0.5589
    95% Confidence Interval: [0.1121, 0.1793]
    Result: SIGNIFICANT improvement

    KEY FINDINGS:
    -------------
    1. Three-class segmentation shows 46.70% improvement in Dice coefficient
    2. Three-class segmentation shows 67.84% 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

    FILES GENERATED:
    ----------------
    - Models: scenario1_binary_model.h5, scenario2_multiclass_model.h5
    - Figures: training_curves.png/.pdf, comparison_visualization.png/.pdf, metrics_comparison.png/.pdf
    - Tables: comprehensive_results.csv/.xlsx, latex_table.tex
    - Statistics: statistical_analysis.json, statistical_report.txt
    - Predictions: All test predictions and ground truth data saved

    PUBLICATION READINESS:
    ----------------------
    ✓ High-resolution figures (300 DPI, PNG/PDF)
    ✓ LaTeX-formatted tables
    ✓ Comprehensive statistical analysis (Dice + IoU)
    ✓ Post-processing impact analysis
    ✓ Reproducible results with saved models
    ✓ Professional documentation