Abstract
Deep learning-based segmentation methods are vulnerable to unforeseen data distribution shifts during deployment, e.g. change of image appearances or contrasts caused by different scanners, unexpected imaging artifacts etc. In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples. Both contributions improve model generalization and robustness with limited data. The cooperative training framework consists of a fast-thinking network (FTN) and a slow-thinking network (STN). The FTN learns decoupled image features and shape features for image reconstruction and segmentation tasks. The STN learns shape priors for segmentation correction and refinement. The two networks are trained in a cooperative manner. The latent space augmentation generates challenging examples for training by masking the decoupled latent space in both channel-wise and spatial-wise manners. We performed extensive experiments on public cardiac imaging datasets. Using only 10 subjects from a single site for training, we demonstrated improved cross-site segmentation performance, and increased robustness against various unforeseen imaging artifacts compared to strong baseline methods. Particularly, cooperative training with latent space data augmentation yields 15% improvement in terms of average Dice score when compared to a standard training method.
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
Shen, D., et al.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)
Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
Dou, Q., et al.: Domain generalization via model-agnostic learning of semantic features. In: Wallach, H.M., et al. (eds.) NeurIPS 2019, pp. 6447–6458 (2019)
Albuquerque, I., et al.: Improving out-of-distribution generalization via multi-task self-supervised pretraining. arXiv preprint arXiv:2003.13525 (2020)
Chattopadhyay, P., Balaji, Y., Hoffman, J.: Learning to balance specificity and invariance for in and out of domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 301–318. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_18
Wang, S., Yu, L., Li, C., Fu, C.-W., Heng, P.-A.: Learning from extrinsic and intrinsic supervisions for domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 159–176. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_10
Shankar, S., et al.: Generalizing across domains via cross-gradient training. In: ICLR (2018). OpenReview.net
Daniel, K.: Thinking, fast and slow (2017)
Shorten, C., et al.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 60 (2019)
Zhang, L., et al.: Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation. IEEE Trans. Med. Imaging 39(7), 2531–2540 (2020)
Chen, C., et al.: Improving the generalizability of convolutional neural network-based segmentation on CMR images. Front. Cardiovasc. Med. 7, 105 (2020)
Devries, T., et al.: Improved regularization of convolutional neural networks with cutout. CoRR, abs/1708.04552 (2017)
Lopes, R.G., et al.: Improving robustness without sacrificing accuracy with patch gaussian augmentation. CoRR, abs/1906.02611 (2019)
Zhou, Z., et al.: Models genesis: generic autodidactic models for 3D medical image analysis. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 384–393. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_42
Zhou, Z., et al.: Models genesis. Med. Image Anal. 67, 101840 (2021)
Miyato, T., Maeda, S.-I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. TPAMI 41, 1979–1993 (2018)
Chen, C., et al.: Realistic adversarial data augmentation for MR image segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 667–677. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_65
Zhang, X., et al.: Deep adversarial data augmentation for extremely low data regimes. IEEE Trans. Circuits Syst. Video Technol. 31(1), 15–28 (2021)
Zhao, L., et al.: Maximum-entropy adversarial data augmentation for improved generalization and robustness. In: NeurIPS (2020)
Zheng, W., Chen, Z., Lu, J., Zhou, J.: Hardness-aware deep metric learning. In: CVPR, pp. 72–81 (2019)
Zhang, Y., et al.: A survey on multi-task learning. arXiv preprint arXiv:1707.08114 (2017)
Larrazabal, A.J., Martinez, C., Ferrante, E.: Anatomical priors for image segmentation via post-processing with denoising autoencoders. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 585–593. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_65
Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., Jodoin, P.-M.: Cardiac MRI segmentation with strong anatomical guarantees. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 632–640. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_70
Tishby, N., et al.: The information bottleneck method. arXiv preprint physics/0004057 (2000)
Huang, Z., Wang, H., Xing, E.P., Huang, D.: Self-challenging improves cross-domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 124–140. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_8
Tompson, J., et al.: Efficient object localization using convolutional networks. In: CVPR, pp. 648–656. IEEE Computer Society (2015)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR, June 2017
Goodfellow, I.J., et al.: Explaining and harnessing adversarial examples. In: ICLR (2015)
Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? TMI 0062(11), 2514–2525 (2018)
Campello, V.M., et al.: Multi-centre, multi-vendor and multi-disease cardiac segmentation: the M&Ms challenge. IEEE Trans. Med. Imaging (under review)
Pérez-García, F., et al.: TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. arXiv:2003.04696 [cs, eess, stat], March 2020
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
Xu, Z., et al.: Robust and generalizable visual representation learning via random convolutions. In: ICLR (2021)
Cubuk, E.D., et al.: Autoaugment: learning augmentation strategies from data. In: CVPR, pp. 113–123 (2019)
Shaw, R., et al.: MRI k-space motion artefact augmentation: model robustness and task-specific uncertainty. In: Jorge Cardoso, M., et al. (eds.) Proceedings of Machine Learning Research, MIDL, London, UK, 08–10 July 2019, vol. 102, pp. 427–436. PMLR (2019)
Christ, P.F., et al.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 415–423. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_48
Acknowledgment
This work was supported by the SmartHeart EPSRC Programme Grant (EP/P001009/1).
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
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, C., Hammernik, K., Ouyang, C., Qin, C., Bai, W., Rueckert, D. (2021). Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12903. Springer, Cham. https://doi.org/10.1007/978-3-030-87199-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-87199-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87198-7
Online ISBN: 978-3-030-87199-4
eBook Packages: Computer ScienceComputer Science (R0)
