Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study

Conclusion: This work provides a comprehensive evaluation of uncertainty estimation methods and showed that Deep Ensembles outperformed other methods in most cases. Significance: Neural network uncertainty measures can help identify potentially inaccurate segmentations and alert users for manual review.
Source: IEEE Transactions on Biomedical Engineering - Category: Biomedical Engineering Source Type: research