Abstract
Computer-aided diagnosis is driven by data, the difference in the distribution of training and testing data leads to significant degradation in semantic segmentation model performance, known as the domain shift phenomenon. The unsupervised domain adaption method has become one of the solutions. Unsupervised domain adaption based on feature alignment is the mainstream method to reinforce feature alignment by reducing the variance of domain invariant features within a batch. However, when processing unsupervised domain adaption segmentation tasks of medical images, the feature alignment-based methods cannot learn domain invariant features stably due to the characteristics of a considerable distribution distance between features in the same category in medical images, resulting in degraded segmentation performance. To address this problem, we propose the Category Prototype Alignment Network(CPAN). First, we refine the category representative features from the domain invariant features. Second, unlike previous feature alignment methods, we construct category prototypes updated by multiple representative features to represent category features, and perform category alignment by reducing the distribution differences of category prototypes across domains, thus stabilizing feature alignment and enabling the network to learn category representative features. Experimental results of cross-domain thyroid ultrasound image segmentation show that our proposed method achieves comparable or even higher performance than current state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allioui, H., Mohammed, M.A., et al.: A multi-agent deep reinforcement learning approach for enhancement of covid-19 CT image segmentation. J. Personalized Med. 12(2), 309 (2022)
Zhao, S., Yue, X., et al.: A review of single-source deep unsupervised visual domain adaptation. IEEE Trans. Neural Netw. Learn. Syst. 33(2), 473–493 (2020)
Kim, H.E., Cosa-Linan, A., et al.: Transfer learning for medical image classification: a literature review. BMC Med. Imaging 22(1), 69 (2022)
Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM Trans. Intell. Syst. Technol. (TIST) 11(5), 1–46 (2020)
Yang, Y., Soatto, S.: Fda: Fourier domain adaptation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4085–4095 (2020)
Tsai, Y.-H., Hung, W.-C., et al.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472–7481 (2018)
Yuan, B., Zhao, D., et al.: Birds of a feather flock together: category-divergence guidance for domain adaptive segmentation. IEEE Trans. Image Process. 31, 2878–2892 (2022)
Li, Z., Togo, R., et al.: Learning intradomain style-invariant representation for unsupervised domain adaptation of semantic segmentation. Pattern Recogn. 132, 108911 (2022)
Chang, W.-L., Wang, H.-P., et al.: All about structure: Adapting structural information across domains for boosting semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1900–1909 (2019)
Wang, Z., Yu, M., et al.: Differential treatment for stuff and things: a simple unsupervised domain adaptation method for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12635–12644 (2020)
Liu, J., Liu, H., et al.: Automated cardiac segmentation of cross-modal medical images using unsupervised multi-domain adaptation and spatial neural attention structure. Med. Image Anal. 72, 102135 (2021)
Jiang, K., Quan, L., Gong, T.: Disentangled representation and crossmodality image translation based unsupervised domain adaptation method for abdominal organ segmentation. Int. J. Comput. Assist. Radiol. Surg. 17(6), 1101–1113 (2022)
Shin, S.Y., Lee, S., Summers, R.M.: Unsupervised domain adaptation for small bowel segmentation using disentangled representation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 282–292. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87199-4_27
Chen, L.-C., Papandreou, G., et al.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Deng, J., Dong, W., et al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Liu, Z., Zhu, Z., et al.: Margin preserving self-paced contrastive learning towards domain adaptation for medical image segmentation. IEEE J. Biomed. Health Inform. 26(2), 638–647 (2022)
Luo, Y., Zheng, L., et al.: Taking a closer look at domain shift: Category-level adversaries for semantics consistent domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2507–2516 (2019)
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 Singapore Pte Ltd.
About this paper
Cite this paper
Yu, M., Xu, Z., Gao, J., Yu, J., Zhao, M. (2023). An Unsupervised Domain Adaptive Network Based on Category Prototype Alignment for Medical Image Segmentation. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14088. Springer, Singapore. https://doi.org/10.1007/978-981-99-4749-2_15
Download citation
DOI: https://doi.org/10.1007/978-981-99-4749-2_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4748-5
Online ISBN: 978-981-99-4749-2
eBook Packages: Computer ScienceComputer Science (R0)