Abstract
Robust self-training (RST) can augment the adversarial robustness of image classification models without significantly sacrificing models’ generalizability. However, RST and other state-of-the-art defense approaches failed to preserve the generalizability and reproduce their good adversarial robustness on small medical image sets. In this work, we propose the Multi-instance RST with drop-max layer, namely MIRST-DM, which involves a sequence of iteratively generated adversarial instances during training to learn smoother decision boundaries on small datasets. The proposed drop-max layer eliminates unstable features and helps learn representations that are robust to image perturbations. The proposed approach was validated using a small breast ultrasound dataset with 1,190 images. The results demonstrate that the proposed approach achieves state-of-the-art adversarial robustness against three prevalent attacks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Drucker, H., Cun, Y.L.: Double backpropagation increasing generalization performance. In: IJCNN-91-Seattle International Joint Conference on Neural Networks, vol. 2, pp. 145–150 (1991). https://doi.org/10.1109/IJCNN.1991.155328
Qin, C., et al.: Adversarial robustness through local linearization. Adv. Neural. Inf. Process. Syst. 32, 13847–13856 (2019)
Zhang, H., Yu, Y., Jiao, J., Xing, E., El Ghaoui, L., Jordan, M.: Theoretically principled trade-off between robustness and accuracy. In: International Conference on Machine Learning, pp. 7472–7482. PMLR (2019)
Carmon, Y., Raghunathan, A., Schmidt, L., Duchi, J.C., Liang, P.S.: Unlabeled data improves adversarial robustness. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Raghunathan, A., Xie, S.M., Yang, F., Duchi, J., Liang, P.: Understanding and mitigating the tradeoff between robustness and accuracy. In: Proceedings of the 37th International Conference on Machine Learning, pp. 7909–7919. PMLR (2020)
Al-Dhabyani, W., Gomaa, M., Khaled, H., Fahmy, A.: Dataset of breast ultrasound images. Data Brief 28, 104863 (2020). https://doi.org/10.1016/j.dib.2019.104863
Xian, M., et al.: BUSIS: a benchmark for breast ultrasound image segmentation. arXiv preprint arXiv:1801.03182 [cs] (2021)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: Presented at the International Conference on Learning Representations, 15 Feb 2018 (2018)
Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39–57 (2017). https://doi.org/10.1109/SP.2017.49
Lehman, C.D., Lee, C.I., Loving, V.A., Portillo, M.S., Peacock, S., DeMartini, W.B.: Accuracy and value of breast ultrasound for primary imaging evaluation of symptomatic women 30–39 years of age. Am. J. Roentgenol. 199, 1169–1177 (2012). https://doi.org/10.2214/AJR.12.8842
Okello, J., Kisembo, H., Bugeza, S., Galukande, M.: Breast cancer detection using sonography in women with mammographically dense breasts. BMC Med. Imaging 14, 41 (2014). https://doi.org/10.1186/s12880-014-0041-0
Burkett, B.J., Hanemann, C.W.: A review of supplemental screening ultrasound for breast cancer: certain populations of women with dense breast tissue may benefit. Acad. Radiol. 23, 1604–1609 (2016). https://doi.org/10.1016/j.acra.2016.05.017
Shia, W.-C., Chen, D.-R.: Classification of malignant tumors in breast ultrasound using a pretrained deep residual network model and support vector machine. Comput. Med. Imaging Graph. 87, 101829 (2021). https://doi.org/10.1016/j.compmedimag.2020.101829
Xie, J., et al.: A novel approach with dual-sampling convolutional neural network for ultrasound image classification of breast tumors. Phys. Med. Biol. 65 (2020)
Zhuang, Z., Yang, Z., Zhuang, S., Joseph Raj, A.N., Yuan, Y., Nersisson, R.: Multi-features-based automated breast tumor diagnosis using ultrasound image and support vector machine. Comput. Intell. Neurosci. 2021, e9980326 (2021). https://doi.org/10.1155/2021/9980326
Zhang, G., Zhao, K., Hong, Y., Qiu, X., Zhang, K., Wei, B.: SHA-MTL: soft and hard attention multi-task learning for automated breast cancer ultrasound image segmentation and classification. Int. J. Comput. Assist. Radiol. Surg. 16(10), 1719–1725 (2021). https://doi.org/10.1007/s11548-021-02445-7
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Yang, Y.-Y., Rashtchian, C., Zhang, H., Salakhutdinov, R., Chaudhuri, K.: A closer look at accuracy vs. robustness. arXiv preprint arXiv:2003.02460 [cs, stat]. (2020)
Ma, X., et al.: Understanding adversarial attacks on deep learning based medical image analysis systems. Pattern Recogn. 110, 107332 (2021). https://doi.org/10.1016/j.patcog.2020.107332
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, S., Xian, M., Vakanski, A., Ghanem, H. (2022). MIRST-DM: Multi-instance RST with Drop-Max Layer for Robust Classification of Breast Cancer. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. Lecture Notes in Computer Science, vol 13434. Springer, Cham. https://doi.org/10.1007/978-3-031-16440-8_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-16440-8_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16439-2
Online ISBN: 978-3-031-16440-8
eBook Packages: Computer ScienceComputer Science (R0)