Uncertainty-Guided Reliability Enhancement of Residual U-Net CT Segmentation in Medical Cancer Imaging

Authors

  • Amirhossein Nafei School of Electromechanical Engineering, Guangdong University of Technology, Guangdong, Guangzhou, China

https://doi.org/10.48314/isti.vi.47

Abstract

Reliable CT segmentation is a critical requirement for quantitative imaging and computer-aided clinical workflows. Although Residual U-Net (Res-U-Net) architectures achieve strong overlap performance on curated datasets, threshold-based binarization of probability maps often produces scattered false positives, particularly in low-contrast regions and near complex anatomical boundaries. This study analyzes the role of predictive uncertainty in improving the structural reliability of CT segmentation outputs. Monte-Carlo dropout is employed at inference time to estimate pixel-wise predictive variance, which is combined with mean probability and component size information within a connected-component framework. A component-level scoring rule is evaluated to suppress unstable, low-confidence regions while preserving coherent anatomical structures. Quantitative experiments demonstrate that uncertainty-aware filtering substantially reduces region-level false positives per scan and improves boundary stability while maintaining competitive Dice and IoU scores. An ablation study further shows that uncertainty penalization is the primary driver of false-positive reduction and that combining uncertainty with mild size regularization yields the most balanced performance. The results support the use of uncertainty-guided refinement as a practical reliability layer for Residual U-Net–based CT segmentation systems.

Keywords:

Computed tomography (CT), Lung segmentation, Residual U-Net, Uncertainty estimation, Monte-Carlo dropout, False positive removal, Connected components, Medical image segmentation

References

  1. [1] Kalender, W. A. (2011). Computed tomography: Fundamentals, system technology, image quality, applications (3rd ed.). Wiley-VCH.
  2. [2] National Lung Screening Trial Research Team. (2011). Reduced lung-cancer mortality with low-dose computed tomographic screening. The New England Journal of Medicine, 365(5), 395–409.
  3. [3] 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.
  4. [4] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778).
  5. [5] Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88.
  6. [6] Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 18(2), 203–211.
  7. [7] Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 (pp. 424–432). Springer.
  8. [8] Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N. Y., Kainz, B., Glocker, B., & Rueckert, D. (2018). Attention U-Net: Learning where to look for the pancreas (arXiv:1804.03999). arXiv. https://doi.org/10.48550/arXiv.1804.03999
  9. [9] Alom, M. Z., Hasan, M., Yakopcic, C., Taha, T. M., & Asari, V. K. (2019). Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation. Journal of Medical Imaging, 6(1), 014006.
  10. [10] Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (ICML) (pp. 1050–1059). PMLR.
  11. [11] Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? (arXiv:1703.04977). arXiv. https://doi.org/10.48550/arXiv.1703.04977
  12. [12] Kendall, A., Badrinarayanan, V., & Cipolla, R. (2015). Bayesian SegNet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding (arXiv:1511.02680). arXiv. https://doi.org/10.48550/arXiv.1511.02680
  13. [13] Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in Neural Information Processing Systems (pp. 6402–6413).
  14. [14] Kohl, S. A. A., Romera-Paredes, B., Meyer, C., De Fauw, J., Ledsam, J. R., Maier-Hein, K., Eslami, S. M. A., Rezende, D. J., & Ronneberger, O. (2018). A probabilistic U-Net for segmentation of ambiguous images (arXiv:1806.05034). arXiv.
  15. [15] Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297–302.
  16. [16] Sørensen, T. (1948). A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on Danish commons. Biologiske Skrifter / Kongelige Danske Videnskabernes Selskab, 5, 1–34.
  17. [17] Dubuisson, M.-P., & Jain, A. K. (1994). A modified Hausdorff distance for object matching. In Proceedings of the 12th International Conference on Pattern Recognition (Vol. 1, pp. 566–568). IEEE.
  18. [18] Serra, J. (1982). Image analysis and mathematical morphology. Academic Press.
  19. [19] Lancaster, H. L., Heuvelmans, M. A., & Oudkerk, M. (2022). Low-dose computed tomography lung cancer screening: Clinical evidence and implementation research. Journal of Internal Medicine, 292(1), 68–80. https://doi.org/10.1111/joim.13480
  20. [20] Guo, Z., Guo, N., Gong, K., Zhong, S., Li, Q., Kim, K., & Zhang, S. (2019). Gross tumor volume segmentation for head and neck cancer radiotherapy using deep learning: Evaluation with Dice and HD95. Frontiers in Oncology, 9, 176.
  21. [21] Khanna, A., Londhe, N. D., Gupta, S., & Semwal, A. (2020). A deep Residual U-Net convolutional neural network for automated lung segmentation in computed tomography images. Biocybernetics and Biomedical Engineering, 40(3), 1314-1327.‏
  22. [22] Khanna, A., Londhe, N. D., Gupta, S., & Semwal, A. (2020). A deep Residual U-Net convolutional neural network for automated lung segmentation in computed tomography images. Biocybernetics and Biomedical Engineering, 40(3), 1314-1327.‏
  23. [23] Miok, K., Nguyen-Doan, D., Zaharie, D., & Robnik-Šikonja, M. (2019, September). Generating data using Monte Carlo dropout. In 2019 IEEE 15th international conference on intelligent computer communication and processing (ICCP) (pp. 509-515). IEEE.

Published

2026-02-28

Issue

Articles in Press

Section

Articles

How to Cite

Nafei, A. (2026). Uncertainty-Guided Reliability Enhancement of Residual U-Net CT Segmentation in Medical Cancer Imaging. Information Sciences and Technological Innovations. https://doi.org/10.48314/isti.vi.47

Similar Articles

1-10 of 11

You may also start an advanced similarity search for this article.