Annotatsiya
This study evaluated mask overlap and pixel probability quality in endoscopic polyp segmentation. Validation-based threshold optimization and temperature scaling were examined on Kvasir-SEG. Three configurations were compared using an 80:10:10 split and random seeds 42, 7, and 2024. The UNet352 configuration with both procedures achieved mean Dice of 0.7900 and IoU of 0.6534. The fixed-threshold UNet256 baseline achieved 0.7405 and 0.5880, respectively. The Brier score decreased from 0.0591 to 0.0455 and negative log-likelihood from 0.2235 to 0.1719. Expected calibration error changed from 0.0224 to 0.0215.
References
1. Jha, D., Smedsrud, P. H., Riegler, M. A., Halvorsen, P., de Lange, T., Johansen, D., & Johansen, H. D. (2020). Kvasir-SEG: A segmented polyp dataset. In MultiMedia Modeling (Lecture Notes in Computer Science, Vol. 11962, pp. 451–462). Springer.
2. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (pp. 234–241). Springer.
3. Taha, A. A., & Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Medical Imaging, 15, Article 29.
4. Mehrtash, A., Wells, W. M., Tempany, C. M., Abolmaesumi, P., & Kapur, T. (2020). Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Transactions on Medical Imaging, 39(12), 3868–3878.
5. Jha, D., Smedsrud, P. H., Riegler, M. A., Johansen, D., de Lange, T., Halvorsen, P., & Johansen, H. D. (2019). ResUNet++: An advanced architecture for medical image segmentation. In Proceedings of the IEEE International Symposium on Multimedia (ISM) (pp. 225–230). IEEE.
6. Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., & Shao, L. (2020). PraNet: Parallel reverse attention network for polyp segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2020 (pp. 263–273). Springer.
7. Maier-Hein, L., Reinke, A., Godau, P., et al. (2024). Metrics reloaded: Recommendations for image analysis validation. Nature Methods, 21, 195–212.
8. Lipton, Z. C., Elkan, C., & Narayanaswamy, B. (2014). Optimal thresholding of classifiers to maximize F1 measure. In Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2014) (pp. 225–239). Springer.
9. Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (PMLR, Vol. 70, pp. 1321–1330).
10. Yeung, M., Rundo, L., Nan, Y., Sala, E., Schönlieb, C.-B., & Yang, G. (2023). Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation. Journal of Digital Imaging, 36, 739–752.
11. Roelofs, R., Cain, N., Shlens, J., & Mozer, M. C. (2022). Mitigating bias in calibration error estimation. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (PMLR, Vol. 151, pp. 4036–4054).
12. Ovadia, Y., Fertig, E., Ren, J., Nado, Z., Sculley, D., Nowozin, S., Dillon, J. V., Lakshminarayanan, B., & Snoek, J. (2019). Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems (Vol. 32).
13. Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 36th International Conference on Machine Learning (PMLR, Vol. 97, pp. 6105–6114).
14. Brier, G. W. (1950). Verification of forecasts expressed in terms of probability. Monthly Weather Review, 78(1), 1–3.