Abstract
Medical image classification is challenging for the lack of labeling examples due to time-consuming and expensive annotations, and the imbalance of classes caused by the scarcity of positive diseased individuals. Self-supervised pre-training with supervised fine-tuning is of great significance in image recognition, but it has received limited attention in medical image classification. In this paper, we propose a novel mechanism for medical image classification as an imbalanced learning strategy based on the popular self-supervised frameworks. In short, this mechanism gives up label information and conducts self-supervised pre-training (SSP) in the first stage of long-tail learning. After this stage, we use the Balanced-MixUp to train the final model. We experiment with long-tail datasets of skin cancer and retinal fundus. Experimental results demonstrate that this mechanism outperforms conventional imbalanced learning techniques and loss functions dealing with data imbalance.
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
Yang, Y., Xu, Z.: Rethinking the value of labels for improving class-imbalanced learning. arXiv, arXiv:2006.07529. NeurIPS 2020 (2020)
Azizi, S., et al.: Big self-supervised models advance medical image classification. arXiv, arXiv:2101.05224 (2021)
Galdran, A., Carneiro, G., González Ballester, M.A.: Balanced-MixUp for highly imbalanced medical image classification. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 323–333. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87240-3_31
Pouyanfar, S., et al.: Dynamic sampling in convolutional neural networks for imbalanced data classification. In: 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 112–117 (2018)
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21, 1263–1284 (2009)
Chawla, N., Bowyer, K., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Zhang, H., Cissé, M., Dauphin, Y., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv, arXiv:1710.09412. ICLR 2018 (2018)
Chou, H., Chang, S., Pan, J., Wei, W., Juan, D.: Remix: rebalanced mixup. arXiv, arXiv:2007.03943 (2020)
Huang, C., Li, Y., Loy, C.C., Tang, X.: Deep imbalanced learning for face recognition and attribute prediction. IEEE Trans. Pattern Anal. Mach. Intell. 42, 2781–2794 (2020)
Cui, Y., Jia, M., Lin, T.-Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9268–9277 (2019)
Cao, K., Wei, C., Gaidon, A., Aréchiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. arXiv, arXiv:1906.07413. NeurIPS 2019 (2019)
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2532–2541 (2019)
Yin, X., Yu, X., Sohn, K., Liu, X., Chandraker, M.: Feature transfer learning for face recognition with under-represented data. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5697–5706 (2019)
Zhang, X., Fang, Z., Wen, Y., Li, Z., Qiao, Y.: Range loss for deep face recognition with long-tailed training data. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5419–5428 (2017)
Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5375–5384 (2016)
Shu, J., et al.: Meta-Weight-Net: learning an explicit mapping for sample weighting. In: NeurIPS (2019)
Jamal, M., Brown, M.A., Yang, M., Wang, L., Gong, B.: Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7607–7616 (2020)
Zhou, B., Cui, Q., Wei, X., Chen, Z.: BBN: bilateral-branch network with cumulative learning for long-tailed visual recognition. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9716–9725 (2020)
Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., Kalantidis, Y.: Decoupling representation and classifier for long-tailed recognition. arXiv, arXiv:1910.09217 (2020)
Hjelm, R.D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Trischler, A., Bengio, Y.: Learning deep representations by mutual information estimation and maximization. arXiv, arXiv:1808.06670 (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. arXiv, arXiv:2002.05709 (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726–9735 (2020)
Spitzer, H., Kiwitz, K., Amunts, K., Harmeling, S., Dickscheid, T.: Improving cytoarchitectonic segmentation of human brain areas with self-supervised siamese networks. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 663–671. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_76
Zhuang, X., Li, Y., Hu, Y., Ma, K., Yang, Y., Zheng, Y.: Self-supervised feature learning for 3D medical images by playing a Rubik’s Cube. arXiv, arXiv:1910.02241 (2019)
Sowrirajan, H., Yang, J., Ng, A., Rajpurkar, P.: MoCo pretraining improves representation and transferability of chest X-ray models. arXiv, arXiv:2010.05352 (2021)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv, abs/1803.07728. ICLR (2018)
Acknowledgement
This work is supported by the Key Field Special Project of Guangdong Provincial Department of Education with No. 2021ZDZX1029.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, W., Li, K. (2022). Self-supervised Learning for Medical Image Classification Using Imbalanced Training Data. In: Li, K., Liu, Y., Wang, W. (eds) Exploration of Novel Intelligent Optimization Algorithms. ISICA 2021. Communications in Computer and Information Science, vol 1590. Springer, Singapore. https://doi.org/10.1007/978-981-19-4109-2_23
Download citation
DOI: https://doi.org/10.1007/978-981-19-4109-2_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4108-5
Online ISBN: 978-981-19-4109-2
eBook Packages: Computer ScienceComputer Science (R0)