Abstract
The volume-wise labeling of 3D medical images is expertise-demanded and time-consuming; hence semi-supervised learning (SSL) is highly desirable for training with limited labeled data. Imbalanced class distribution is a severe problem that bottlenecks the real-world application of these methods but was not addressed much. Aiming to solve this issue, we present a novel Dual-debiased Heterogeneous Co-training (DHC) framework for semi-supervised 3D medical image segmentation. Specifically, we propose two loss weighting strategies, namely Distribution-aware Debiased Weighting (DistDW) and Difficulty-aware Debiased Weighting (DiffDW), which leverage the pseudo labels dynamically to guide the model to solve data and learning biases. The framework improves significantly by co-training these two diverse and accurate sub-models. We also introduce more representative benchmarks for class-imbalanced semi-supervised medical image segmentation, which can fully demonstrate the efficacy of the class-imbalance designs. Experiments show that our proposed framework brings significant improvements by using pseudo labels for debiasing and alleviating the class imbalance problem. More importantly, our method outperforms the state-of-the-art SSL methods, demonstrating the potential of our framework for the more challenging SSL setting. Code and models are available at: https://github.com/xmed-lab/DHC.
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
Similar content being viewed by others
References
Basak, H., Ghosal, S., Sarkar, R.: Addressing class imbalance in semi-supervised image segmentation: a study on cardiac mri. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13438, pp. 224–233. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-16452-1_22
Chen, B., Jiang, J., Wang, X., Wan, P., Wang, J., Long, M.: Debiased self-training for semi-supervised learning. Adv. Neural Inf. Process. Syst. 35, 32424–32437 (2022)
Chen, H., et al.: An embarrassingly simple baseline for imbalanced semi-supervised learning. arXiv preprint arXiv:2211.11086 (2022)
Chen, X., Yuan, Y., Zeng, G., Wang, J.: Semi-supervised semantic segmentation with cross pseudo supervision. In: CVPR, pp. 2613–2622 (2021)
Guo, L.Z., Li, Y.F.: Class-imbalanced semi-supervised learning with adaptive thresholding. In: ICML, pp. 8082–8094. PMLR (2022)
Jeffreys, H.: An invariant form for the prior probability in estimation problems. Proc. Royal Soc. Lond. Ser. A. Math. Phys. Sci. 186(1007), 453–461 (1946)
Ji, Y., et al.: Amos: a large-scale abdominal multi-organ benchmark for versatile medical image segmentation. arXiv preprint arXiv:2206.08023 (2022)
Krogh, A., Vedelsby, J.: Neural network ensembles, cross validation, and active learning. Adv. Neural Inf. Process. Syst. 7, 1–8 (1994)
Landman, B., Xu, Z., Igelsias, J., Styner, M., Langerak, T., Klein, A.: 2015 miccai multi-atlas labeling beyond the cranial vault-workshop and challenge (2015). https://doi.org/10.7303/syn3193805
Lin, Y., Yao, H., Li, Z., Zheng, G., Li, X.: Calibrating label distribution for class-imbalanced barely-supervised knee segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13438, pp. 109–118. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-16452-1_11
Luo, X., et al.: Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 318–329. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_30
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural Inf. Process. Syst. 33, 596–608 (2020)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. Adv. Neural Inf. Process. Syst. 30, 1–10 (2017)
Wang, J., Lukasiewicz, T.: Rethinking bayesian deep learning methods for semi-supervised volumetric medical image segmentation. In: CVPR, pp. 182–190 (2022)
Wang, X., Wu, Z., Lian, L., Yu, S.X.: Debiased learning from naturally imbalanced pseudo-labels. In: CVPR, pp. 14647–14657 (2022)
Wang, Y., et al.: Semi-supervised semantic segmentation using unreliable pseudo-labels. In: CVPR, pp. 4248–4257 (2022)
Wei, C., Sohn, K., Mellina, C., Yuille, A., Yang, F.: Crest: a class-rebalancing self-training framework for imbalanced semi-supervised learning. In: CVPR, pp. 10857–10866 (2021)
Wu, H., Wang, Z., Song, Y., Yang, L., Qin, J.: Cross-patch dense contrastive learning for semi-supervised segmentation of cellular nuclei in histopathologic images. In: CVPR, pp. 11666–11675 (2022)
Wu, Y., Wu, Z., Wu, Q., Ge, Z., Cai, J.: Exploring smoothness and class-separation for semi-supervised medical image segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13435, pp. 34–43. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-16443-9_4
You, C., Zhao, R., Staib, L.H., Duncan, J.S.: Momentum contrastive voxel-wise representation learning for semi-supervised volumetric medical image segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13434, pp. 639–652. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-16440-8_61
Yu, L., Wang, S., Li, X., Fu, C.-W., Heng, P.-A.: Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 605–613. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_67
Acknowledgement
This work was supported in part by a grant from Hong Kong Innovation and Technology Commission (Project no. ITS/030/21) and in part by a research grant from Beijing Institute of Collaborative Innovation (BICI) under collaboration with HKUST under Grant HCIC-004 and in part by grants from Foshan HKUST Projects under Grants FSUST21-HKUST10E and FSUST21-HKUST11E.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Li, X. (2023). DHC: Dual-Debiased Heterogeneous Co-training Framework for Class-Imbalanced Semi-supervised Medical Image Segmentation. 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_56
Download citation
DOI: https://doi.org/10.1007/978-3-031-43898-1_56
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)