Abstract
Neural network prediction probabilities and accuracy are often only weakly-correlated. Inherent label ambiguity in training data for image segmentation aggravates such miscalibration. We show that logit consistency across stochastic transformations acts as a spatially varying regularizer that prevents overconfident predictions at pixels with ambiguous labels. Our boundary-weighted extension of this regularizer provides state-of-the-art calibration for prostate and heart MRI segmentation. Code is available at https://github.com/neerakara/BWCR.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abulnaga, S.M., et al.: Automatic segmentation of the placenta in BOLD MRI time series. In: Licandro, R., Melbourne, A., Abaci Turk, E., Macgowan, C., Hutter, J. (eds) Perinatal, Preterm and Paediatric Image Analysis. PIPPI 2022. Lecture Notes in Computer Science, vol. 13575. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-17117-8_1
Arpit, D., Wang, H., Zhou, Y., Xiong, C.: Ensemble of averages: improving model selection and boosting performance in domain generalization. In: Advances in Neural Information Processing Systems (2022)
Baumgartner, C.F., et al.: PHiSeg: capturing uncertainty in medical image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 119–127. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_14
Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37, 2514–2525 (2018)
Bloch, N., et al.: NCI-ISBI 2013 challenge: automated segmentation of prostate structures. https://wiki.cancerimagingarchive.net/display/Public/NCI-ISBI+2013+Challenge+-+Automated+Segmentation+of+Prostate+Structures (2015)
Bortsova, G., Dubost, F., Hogeweg, L., Katramados, I., de Bruijne, M.: Semi-supervised medical image segmentation via learning consistency under transformations. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 810–818. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_90
Cui, W., et al.: Semi-supervised brain lesion segmentation with an adapted mean teacher model. In: Chung, A.C.S.., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 554–565. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_43
Englesson, E., Azizpour, H.: Generalized Jensen-Shannon divergence loss for learning with noisy labels. In: Advances in Neural Information Processing Systems (2021)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International conference on machine learning. PMLR (2017)
Hong, S., et al.: Hypernet-ensemble learning of segmentation probability for medical image segmentation with ambiguous labels. arXiv preprint arXiv:2112.06693 (2021)
Hoopes, A., Mora, J.S., Dalca, A.V., Fischl, B., Hoffmann, M.: SynthStrip: skull-stripping for any brain image. NeuroImage 260, 119474 (2022)
Islam, M., Glocker, B.: Spatially varying label smoothing: capturing uncertainty from expert annotations. In: Feragen, A., Sommer, S., Schnabel, J., Nielsen, M. (eds.) IPMI 2021. LNCS, vol. 12729, pp. 677–688. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78191-0_52
Kohl, S., et al.: A probabilistic U-Net for segmentation of ambiguous images. In: Advances in neural information processing systems (2018)
Larrazabal, A., Martinez, C., Dolz, J., Ferrante, E.: Maximum entropy on erroneous predictions (MEEP): improving model calibration for medical image segmentation. arXiv preprint arXiv:2112.12218 (2021)
Li, X., Yu, L., Chen, H., Fu, C.W., Xing, L., Heng, P.A.: Transformation-consistent self-ensembling model for semisupervised medical image segmentation. IEEE Trans. Neural Netw. Learn. Syst. 32, 523–534 (2020)
Liu, B., Ben Ayed, I., Galdran, A., Dolz, J.: The devil is in the margin: margin-based label smoothing for network calibration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
Luo, X., et al.: Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency. Med. Image Anal. 80, 102517 (2022)
Mehrtash, A., Wells, W.M., Tempany, C.M., Abolmaesumi, P., Kapur, T.: Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Trans. Med. Imaging 39, 3868–3878 (2020)
Monteiro, M., et al.: Stochastic segmentation networks: modelling spatially correlated aleatoric uncertainty. In: Advances in Neural Information Processing Systems (2020)
Müller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Advances in Neural Information Processing Systems (2019)
Murugesan, B., Adiga V, S., Liu, B., Lombaert, H., Ayed, I.B., Dolz, J.: Trust your neighbours: penalty-based constraints for model calibration. arXiv preprint arXiv:2303.06268 (2023)
Murugesan, B., Liu, B., Galdran, A., Ayed, I.B., Dolz, J.: Calibrating segmentation networks with margin-based label smoothing. arXiv preprint arXiv:2209.09641 (2022)
Nixon, J., Dusenberry, M.W., Zhang, L., Jerfel, G., Tran, D.: Measuring calibration in deep learning. In: CVPR Workshops (2019)
Paglieroni, D.W.: Distance transforms: Properties and machine vision applications. Graphical models and image processing, CVGIP (1992)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Sajjadi, M., Javanmardi, M., Tasdizen, T.: Regularization with stochastic transformations and perturbations for deep semi-supervised learning. In: Advances in neural information processing systems (2016)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in neural information processing systems (2017)
Tustison, N.J., et al.: N4itk: improved N3 bias correction. IEEE Trans. Med. Imaging 29, 1310–1320 (2010)
Wang, G., Li, W., Aertsen, M., Deprest, J., Ourselin, S., Vercauteren, T.: Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing 338, 34–45 (2019)
Wu, Y., et al.: Mutual consistency learning for semi-supervised medical image segmentation. Med. Image Anal. 81, 102530 (2022)
Zhang, L., et al.: Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans. Med. Imaging 39, 2531–2540 (2020)
Acknowledgements
This research is supported by NIH NIBIB NAC P41EB015902, IBM, and the Swiss National Science Foundation under project P500PT-206955.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Karani, N., Dey, N., Golland, P. (2023). Boundary-Weighted Logit Consistency Improves Calibration of Segmentation Networks. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14222. Springer, Cham. https://doi.org/10.1007/978-3-031-43898-1_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-43898-1_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43897-4
Online ISBN: 978-3-031-43898-1
eBook Packages: Computer ScienceComputer Science (R0)
