Abstract
Domain Generalization is a challenging problem in deep learning especially in medical image analysis because of the huge diversity between different datasets. Existing papers in the literature tend to optimize performance on single target domains, without regards to model generalizability on other domains or distributions. High discrepancy in the number of images and major domain shifts, can therefore cause single-source trained models to under-perform during testing. In this paper, we address the problem of domain generalization in Diabetic Retinopathy (DR) classification. The baseline for comparison is set as joint training on different datasets, followed by testing on each dataset individually. We therefore introduce a method that encourages seeking a flatter minima during training while imposing a regularization. This reduces gradient variance from different domains and therefore yields satisfactory results on out-of-domain DR classification. We show that adopting DR-appropriate augmentations enhances model performance and in-domain generalizability. By performing our evaluation on 4 open-source DR datasets, we show that the proposed domain generalization method outperforms separate and joint training strategies as well as well-established methods. Source Code is available at https://github.com/BioMedIA-MBZUAI/DRGen.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
APTOS: APTOS 2019 Blindness Detection, June 2018. https://kaggle.com/c/aptos2019-blindness-detection
Arjovsky, M., Bottou, L., Gulrajani, I., Lopez-Paz, D.: Invariant Risk Minimization. arXiv:1907.02893 [cs, stat], July 2019. version: 1
Asad, A.H., Azar, A.T., El-Bendary, N., Hassaanien, A.E.: Ant colony based feature selection heuristics for retinal vessel segmentation. arXiv:1403.1735 [cs], March 2014
Cha, J., Cho, H., Lee, K., Park, S., Lee, Y., Park, S.: Domain generalization needs stochastic weight averaging for robustness on domain shifts. CoRR arXiv:2102.08604 (2021)
Decencière, E., et al.: Feedback on a publicly distributed image database: the messidor database. Image Anal. Stereol. 33(3), 231–234 (2014). https://doi.org/10.5566/ias.1155, https://www.ias-iss.org/ojs/IAS/article/view/1155
Fang, C., Xu, Y., Rockmore, D.N.: Unbiased metric learning: on the utilization of multiple datasets and web images for softening bias. In: Proceedings of the 2013 IEEE International Conference on Computer Vision, ICCV 2013, pp. 1657–1664. IEEE Computer Society, USA (2013). https://doi.org/10.1109/ICCV.2013.208
Gulrajani, I., Lopez-Paz, D.: In search of lost domain generalization. CoRR arXiv:2007.01434 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016. https://doi.org/10.1109/CVPR.2016.90. ISSN: 1063-6919
Kempen, J.H., et al.: The prevalence of diabetic retinopathy among adults in the United States. Arch. Ophthalmol. (Chicago, Ill.: 1960) 122(4), 552–563 (2004). https://doi.org/10.1001/archopht.122.4.552, https://europepmc.org/article/med/15078674
Kaggle: Diabetic Retinopathy Detection - EYEPACS Dataset. https://kaggle.com/c/diabetic-retinopathy-detection
Kauppi, T., et al.: DIARETDB 0: Evaluation Database and Methodology for Diabetic Retinopathy Algorithms (2007). https://www.paper/DIARETDB-0-%3A-Evaluation-Database-and-Methodology-Kauppi-Kalesnykiene/bd7d2380e76fb9dfd367d669e311d4913f67f7d2
Kauppi, T., et al.: DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Proceedings of the British Machine Vision Conference, vol. 2007, January 2007. https://doi.org/10.5244/C.21.15
Larxel: Ocular Disease Recognition, April 2020. https://kaggle.com/andrewmvd/ocular-disease-recognition-odir5k, https://odir2019.grand-challenge.org/
Li, C., Qi, Q., Ding, X., Huang, Y., Liang, D., Yu, Y.: Domain generalization on medical imaging classification using episodic training with task augmentation. CoRR arXiv:2106.06908 (2021)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5543–5551 (2017)
Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Learning to generalize: meta-learning for domain generalization. arXiv:1710.03463 [cs], October 2017
Li, H., Wang, Y., Wan, R., Wang, S., Li, T., Kot, A.C.: Domain generalization for medical imaging classification with linear-dependency regularization. CoRR arXiv:2009.12829 (2020)
Li, T., Gao, Y., Wang, K., Guo, S., Liu, H., Kang, H.: Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf. Sci. 501, 511–522 (2019). https://doi.org/10.1016/j.ins.2019.06.011, https://linkinghub.elsevier.com/retrieve/pii/S0020025519305377
Liu, Q., Chen, C., Qin, J., Dou, Q., Heng, P.: FedDG: federated domain generalization on medical image segmentation via episodic learning in continuous frequency space. CoRR arXiv:2103.06030 (2021)
Maffre, G.G., et al.: Messidor. https://www.adcis.net/en/third-party/messidor/
Pachade, S., et al.: Retinal Fundus Multi-Disease Image Dataset (RFMiD): a dataset for multi-disease detection research. Data 6(2), 14 (2021). https://doi.org/10.3390/data6020014, https://www.mdpi.com/2306-5729/6/2/14
Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. CoRR arXiv:1812.01754 (2018)
Porwal, P., et al.: Indian Diabetic Retinopathy Image Dataset (IDRiD): a database for diabetic retinopathy screening research. Data 3(3), 25 (2018). https://doi.org/10.3390/data3030025, https://www.mdpi.com/2306-5729/3/3/25
Ramé, A., Dancette, C., Cord, M.: Fishr: invariant gradient variances for out-of-distribution generalization. CoRR arXiv:2109.02934 (2021)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization in vision: a survey. arXiv:2103.02503 [cs], March 2021. version: 1
Zhou, K., Yang, Y., Qiao, Y., Xiang, T.: MixStyle neural networks for domain generalization and adaptation. arXiv:2107.02053 [cs], July 2021
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
Atwany, M., Yaqub, M. (2022). DRGen: Domain Generalization in Diabetic Retinopathy Classification. 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 13432. Springer, Cham. https://doi.org/10.1007/978-3-031-16434-7_61
Download citation
DOI: https://doi.org/10.1007/978-3-031-16434-7_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16433-0
Online ISBN: 978-3-031-16434-7
eBook Packages: Computer ScienceComputer Science (R0)