Abstract
It is well known that in medical image analysis, only a small number of high-quality labeled images can be often obtained from a large number of medical images due to the requirement of expert knowledge and intensive labor work. Therefore, we propose a novel semi-supervised adversarial learning framework (SSALF) for diabetic retinopathy (DR) screening of color fundus images. Specifically, our proposed framework consists of two subnetworks, an extended network and a discriminator. The extended network is obtained by extending a common classification network with a generator used for unsupervised image reconstruction. Thus, the extended network can utilize some labeled and lots of unlabeled fundus images. Then the discriminator is attached to the generator of the extended network to judge whether a reconstructed image is real or fake, introducing adversarial learning into the whole framework. Our framework achieves promising utility and generalization on the datasets of EyePACS and Messidor in a semi-supervised setting: we use some labeled and lots of unlabeled fundus images to train our framework. And we also investigate the effects of image reconstruction and adversarial learning on our framework by implementing ablation experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abràmoff, M.D., et al.: Automated early detection of diabetic retinopathy. Ophthalmology 117(6), 1147–1154 (2010)
Chongxuan, L., Xu, T., Zhu, J., Zhang, B.: Triple generative adversarial nets. In: NIPS, pp. 4088–4098 (2017)
Goodfellow, I., et al.: Generative adversarial nets. In: NIPS. pp. 2672–2680 (2014)
Gulshan, V., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402–2410 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hu, B., et al.: Unsupervised learning for cell-level visual representation in histopathology images with generative adversarial networks. IEEE J. Biomed. Health Inform. 23(3), 1316–1328 (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)
Lecouat, B., et al.: Semi-supervised deep learning for abnormality classification in retinal images. In: Machine Learning for Health (ML4H) Workshop at NeurIPS (2018)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR, pp. 4681–4690 (2017)
Madani, A., Moradi, M., Karargyris, A., Syeda-Mahmood, T.: Semi-supervised learning with generative adversarial networks for chest x-ray classification with ability of data domain adaptation. In: ISBI 2018, pp. 1038–1042. IEEE (2018)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: NIPS, pp. 3546–3554 (2015)
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
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANS. In: NIPS, pp. 2234–2242 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1–9 (2015)
Vo, H.H., Verma, A.: New deep neural nets for fine-grained diabetic retinopathy recognition on hybrid color space. In: 2016 IEEE International Symposium on Multimedia (ISM), pp. 209–215. IEEE (2016)
Yang, L., Zhang, Y., Chen, J., Zhang, S., Chen, D.Z.: Suggestive Annotation: a deep active learning framework for biomedical image segmentation. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 399–407. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_46
Zhao, J., Mathieu, M., Goroshin, R., Lecun, Y.: Stacked what-where auto-encoders. arXiv preprint arXiv:1506.02351 (2015)
Acknowledgements
This work was supported in part by the Programme of Introducing Talents of Discipline to University: B13043, and the National Key Research and Development Program of China under grant 2017YFA0700800.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, S., Xin, J., Wu, J., Shi, P. (2019). Semi-supervised Adversarial Learning for Diabetic Retinopathy Screening. In: Fu, H., Garvin, M., MacGillivray, T., Xu, Y., Zheng, Y. (eds) Ophthalmic Medical Image Analysis. OMIA 2019. Lecture Notes in Computer Science(), vol 11855. Springer, Cham. https://doi.org/10.1007/978-3-030-32956-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-32956-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32955-6
Online ISBN: 978-3-030-32956-3
eBook Packages: Computer ScienceComputer Science (R0)