Abstract
Unsupervised domain adaptation (UDA) has gained great popularity in mitochondria segmentation, aiming to improve the adaptability of models from the labeled source domain to the unlabeled target domain via domain alignment. However, existing UDA methods only focus on aligning domains on the prediction level, while ignoring the feature space containing more adequate information than the predictions. In this paper, we propose a class-aware domain adaptation method for mitochondria segmentation on the feature level, which relies on the prototype representation to achieve more fine-grained alignment. In particular, we first extract the feature centroids of classes from the source domain as prototypes. Leveraging the extracted prototypes as a bridge, we constrain that features belonging to the same class but from different domains are pulled closer to each other, achieving the class-aware alignment. Meanwhile, we derive a segmentation prediction directly from feature space based on the distance between target features and source prototypes. By incorporating a pseudo label to supervise the learning of this prediction, the feature distribution gap across domains is further reduced. Furthermore, to take full advantage of the potential of target domain, we propose an intra-domain consistency constraint to maintain consistent predictions of samples perturbed differently from the target image. Extensive experiments on different datasets demonstrate the superiority of our proposed method over existing UDA methods. Code is available at https://github.com/Danyin813/CAFA.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bermúdez-Chacón, R., Altingövde, O., Becker, C., Salzmann, M., Fua, P.: Visual correspondences for unsupervised domain adaptation on electron microscopy images. IEEE Trans. Med. Imaging 39(4), 1256–1267 (2019)
Bermúdez-Chacón, R., Márquez-Neila, P., Salzmann, M., Fua, P.: A domain-adaptive two-stream u-net for electron microscopy image segmentation. In: ISBI (2018)
Franco-Barranco, D., Muñoz-Barrutia, A., Arganda-Carreras, I.: Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes. Neuroinformatics 20(2), 437–450 (2022)
Franco-Barranco, D., Pastor-Tronch, J., González-Marfil, A., Muñoz-Barrutia, A., Arganda-Carreras, I.: Deep learning based domain adaptation for mitochondria segmentation on EM volumes. Comput. Methods Programs Biomed. 222, 106949 (2022)
Gerhard, S., Funke, J., Martel, J., Cardona, A., Fetter, R.: Segmented anisotropic ssTEM dataset of neural tissue. Figshare (2013)
Guan, D., Huang, J., **ao, A., Lu, S.: Domain adaptive video segmentation via temporal consistency regularization. In: ICCV (2021)
Huang, W., Liu, X., Cheng, Z., Zhang, Y., **ong, Z.: Domain adaptive mitochondria segmentation via enforcing inter-section consistency. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13434, pp. 89–98. Springer, Cham (2022)
Jiang, Z., et al.: Prototypical contrast adaptation for domain adaptive semantic segmentation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 36–54. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19830-4_3
Li, M., Chen, C., Liu, X., Huang, W., Zhang, Y., **ong, Z.: Advanced deep networks for 3d mitochondria instance segmentation. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE (2022)
Li, Z., Chen, X., Zhao, J., **ong, Z.: Contrastive learning for mitochondria segmentation. In: EMBC (2021)
Liu, D., et al.: PDAM: a panoptic-level feature alignment framework for unsupervised domain adaptive instance segmentation in microscopy images. IEEE Trans. Med. Imaging 40(1), 154–165 (2020)
Lucchi, A., Li, Y., Fua, P.: Learning for structured prediction using approximate subgradient descent with working sets. In: CVPR (2013)
Luo, Y., Zheng, L., Guan, T., Yu, J., Yang, Y.: 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)
Mekuč, M.Ž, Bohak, C., Hudoklin, S., Kim, B.H., Kim, M.Y., Marolt, M., et al.: Automatic segmentation of mitochondria and endolysosomes in volumetric electron microscopy data. Comput. Biol. Med. 119, 103693 (2020)
Mumcuoglu, E., Hassanpour, R., Tasel, S., Perkins, G., Martone, M., Gurcan, M.: Computerized detection and segmentation of mitochondria on electron microscope images. J. Microsc. 246(3), 248–265 (2012)
Peng, J., Yi, J., Yuan, Z.: Unsupervised mitochondria segmentation in EM images via domain adaptive multi-task learning. IEEE J. Sel. Top. Signal Process. 14(6), 1199–1209 (2020)
Roels, J., Hennies, J., Saeys, Y., Philips, W., Kreshuk, A.: Domain adaptive segmentation in volume electron microscopy imaging. In: ISBI (2019)
Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural. Inf. Process. Syst. 33, 596–608 (2020)
Vu, T.H., Jain, H., Bucher, M., Cord, M., Pérez, P.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2517–2526 (2019)
Wei, D., et al.: MitoEM dataset: large-scale 3D mitochondria instance segmentation from EM images. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12265, pp. 66–76. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59722-1_7
Wu, S., Chen, C., **ong, Z., Chen, X., Sun, X.: Uncertainty-aware label rectification for domain adaptive mitochondria segmentation. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 191–200. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87199-4_18
Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., Wen, F.: Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12414–12424 (2021)
Acknowledgement
This work was supported by the National Natural Science Foundation of China under Grant 62076230.
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
Yin, D., Huang, W., **ong, Z., Chen, X. (2023). Class-Aware Feature Alignment for Domain Adaptative Mitochondria Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14223. Springer, Cham. https://doi.org/10.1007/978-3-031-43901-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-43901-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43900-1
Online ISBN: 978-3-031-43901-8
eBook Packages: Computer ScienceComputer Science (R0)