Abstract
Despite the remarkable advance in unsupervised cross-domain image segmentation, existing works suffer from two main limitations. They either ignore the semantics preservation when transferring knowledge from source domain to target domain, or ignore to fully explore the rich information of the large amount of unlabeled data in target domain, leading to a bias segmentation model. To address these issues, we propose a novel semantics-preserved cross-domain image segmentation method with a new diverse image perturbation in the target domain, improving the capacity and robustness of the model. We also propose an effective test-time ensembling strategy for a more confident prediction result.
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
Liu, X., et al.: A review of deep-learning-based medical image segmentation methods. Sustainability 13(3), 1224 (2021)
Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM Trans. Intell. Syst. Technol. (TIST) 11(5), 1–46 (2020)
Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM TIST 11(5), 1–46 (2020)
Liu, X., Yoo, C., et al.: Deep unsupervised domain adaptation: a review of recent advances and perspectives. APSIPA Trans. Inf. Process. 11(1) (2022)
Wu, F., Zhuang, X.: CF distance: a new domain discrepancy metric and application to explicit domain adaptation for cross-modality cardiac image segmentation. IEEE Trans. Med. Imaging 39(12), 4274–4285 (2020)
Li, Y., et al.: Bidirectional learning for domain adaptation of semantic segmentation. CVPR, pp. 6936–6945 (2019)
Wang, R., Zheng, G.: Cycmis: cycle-consistent cross-domain medical image segmentation via diverse image augmentation. Med. Image Anal. 76, 102328 (2022)
Chen, C., Dou, Q., et al.: Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation. TMI 39(7), 2494–2505 (2020)
Huang, X., et al.: Multimodal unsupervised image-to-image translation. In: ECCV, pp. 172–189 (2018)
Diakogiannis, F.I., et al.: ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS J. Photogramm. Remote. Sens. 162(2020), 94–114 (2020)
Pang, S., Pang, C., et al.: Spineparsenet: spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation. TMI 40(1), 262–273 (2020)
Acknowledgment
This study was partially supported by the National Natural Science Foundation of China via project U20A20199 and by Shanghai Municipal Science and Technology Commission via Project 20511105205.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, X., Wang, R., Tao, R., Zheng, G. (2024). Semantics-Preserved Domain Adaptation with Target Diverse Perturbation and Test Ensembling for Image Segmentation. In: Wang, G., Yao, D., Gu, Z., Peng, Y., Tong, S., Liu, C. (eds) 12th Asian-Pacific Conference on Medical and Biological Engineering. APCMBE 2023. IFMBE Proceedings, vol 104. Springer, Cham. https://doi.org/10.1007/978-3-031-51485-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-51485-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-51484-5
Online ISBN: 978-3-031-51485-2
eBook Packages: EngineeringEngineering (R0)