Abstract
Modern deep learning methods for semantic segmentation require labor-intensive labeling for large-scale datasets with dense pixel-level annotations. Recent data augmentation methods such as drop**, mixing image patches, and adding random noises suggest effective ways to address the labeling issues for natural images. However, they can only be restrictively applied to medical image segmentation as they carry risks of distorting or ignoring the underlying clinical information of local regions of interest in an image. In this paper, we propose a novel data augmentation method for medical image segmentation without losing the semantics of the key objects (e.g., polyps). This is achieved by perturbing the objects with quasi-imperceptible adversarial noises and training a network to expand discriminative regions with a guide of anti-adversarial noises. Such guidance can be realized by a consistency regularization between the two contrasting data, and the strength of regularization is automatically and adaptively controlled considering their prediction uncertainty. Our proposed method significantly outperforms various existing methods with high sensitivity and Dice scores and extensive experiment results with multiple backbones on two datasets validate its effectiveness.
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
Alfarra, M., Pérez, J.C., et al.: Combating adversaries with anti-adversaries. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 5992–6000 (2022)
Chaurasia, A., Culurciello, E.: Linknet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing, pp. 1–4. IEEE (2017)
Chen, L.C., Zhu, Y., et al.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 801–818 (2018)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. ar**v preprint ar**v:1708.04552 (2017)
Fan, D.-P., et al.: PraNet: parallel reverse attention network for polyp segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 263–273. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59725-2_26
Felder, S., Rabinovitz, H., et al.: Dermoscopic pattern of pigmented basal cell carcinoma, blue-white variant. Dermatol. Surg. 32(4), 569–570 (2006)
Ghiasi, G., Lin, T.Y., et al.: Dropblock: a regularization method for convolutional networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Goodfellow, I.J., Shlens, J., et al.: Explaining and harnessing adversarial examples. ar**v preprint ar**v:1412.6572 (2014)
Hu, Y., Zhong, Z., Wang, R., Liu, H., Tan, Z., Zheng, W.-S.: Data augmentation in logit space for medical image classification with limited training data. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 469–479. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87240-3_45
Jha, D., Riegler, M.A., et al.: Doubleu-net: a deep convolutional neural network for medical image segmentation. In: IEEE International Symposium on Computer-Based Medical Systems, pp. 558–564. IEEE (2020)
Jha, D., et al.: Kvasir-SEG: a segmented polyp dataset. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 451–462. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-37734-2_37
Juszczak, P., Duin, R.P.: Uncertainty sampling methods for one-class classifiers. In: Proceedings of ICML-03, Workshop on Learning with Imbalanced Data Sets II, pp. 81–88 (2003)
Kaissis, G.A., Makowski, M.R., et al.: Secure, privacy-preserving and federated machine learning in medical imaging. Nat. Mach. Intell. 2(6), 305–311 (2020)
Lee, J.Y., Jeong, J., et al.: Real-time detection of colon polyps during colonoscopy using deep learning: systematic validation with four independent datasets. Sci. Rep. 10(1), 8379 (2020)
Lee, J., Kim, E., et al.: Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4071–4080 (2021)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Machine Learning Proceedings 1994, pp. 148–156. Elsevier (1994)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Madry, A., Makelov, A., et al.: Towards deep learning models resistant to adversarial attacks. ar**v preprint ar**v:1706.06083 (2017)
Nguyen, V.L., Shaker, M.H., et al.: How to measure uncertainty in uncertainty sampling for active learning. Mach. Learn. 111(1), 89–122 (2022)
Parmar, B., Talati, B.: Automated melanoma types and stages classification for dermoscopy images. In: 2019 Innovations in Power and Advanced Computing Technologies, vol. 1, pp. 1–7. IEEE (2019)
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
Rusak, E., et al.: A simple way to make neural networks robust against diverse image corruptions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 53–69. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_4
Saleh, F.S., Aliakbarian, M.S., et al.: Effective use of synthetic data for urban scene semantic segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 84–100 (2018)
Sanderson, E., Matuszewski, B.J.: FCN-transformer feature fusion for polyp segmentation. In: Yang, G., Aviles-Rivero, A., Roberts, M., Schönlieb, C.B. (eds.) MIUA 2022. LNCS, vol. 13413, pp. 892–907. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-12053-4_65
Silva, J., Histace, A., et al.: Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 9, 283–293 (2014)
Simard, P.Y., Steinkraus, D., et al.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition, vol. 3 (2003)
Srivastava, A., Jha, D., et al.: MSRF-Net: a multi-scale residual fusion network for biomedical image segmentation. IEEE J. Biomed. Health Inform. 26(5), 2252–2263 (2021)
Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28
Wang, J., Huang, Q., et al.: Stepwise feature fusion: Local guides global. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13433, pp. 110–120. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16437-8_11
Yang, J., Zhang, Y., Liang, Y., Zhang, Y., He, L., He, Z.: TumorCP: a simple but effective object-level data augmentation for tumor segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 579–588. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_55
Yun, S., Han, D., et al.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032 (2019)
Zhao, X., Vemulapalli, R., et al.: Contrastive learning for label efficient semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10623–10633 (2021)
Zhong, Z., Zheng, L., et al.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13001–13008 (2020)
Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: a nested U-net architecture for medical image segmentation. In: Stoyanov, D., et al. (eds.) DLMIA/ML-CDS -2018. LNCS, vol. 11045, pp. 3–11. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00889-5_1
Ziller, A., Usynin, D., et al.: Medical imaging deep learning with differential privacy. Sci. Rep. 11(1), 1–8 (2021)
Acknowledgement
This research was supported by IITP-2022-0-00290 (50%), IITP-2019-0-01906 (AI Graduate Program at POSTECH, 10%), IITP-2022-2020-0-01461 (ITRC, 10%) and NRF-2022R1A2C2092336 (30%) funded by the Korean government (MSIT).
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 Switzerland AG
About this paper
Cite this paper
Cho, H., Han, Y., Kim, W.H. (2023). Anti-adversarial Consistency Regularization for Data Augmentation: Applications to Robust 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 14223. Springer, Cham. https://doi.org/10.1007/978-3-031-43901-8_53
Download citation
DOI: https://doi.org/10.1007/978-3-031-43901-8_53
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)
