Abstract
Recent application of deep learning in medical image achieves expert-level accuracy. However, the accuracy often degrades greatly on unseen data, for example data from different device designs and population distributions. In this work, we consider a realistic problem of domain generalization in fundus image analysis: when a model is trained on a certain domain but tested on unseen domains. Here, the known domain data is taken from a single fundus camera manufacture, i.e. Canon. The unseen data are the image from different demographic population and with distinct photography styles. Specifically, the unseen images are taken from Topcom, Syseye and Crystalvue cameras. The model performance is evaluated by two objectives: age regression and diabetic retinopathy (DR) classification. We found that the model performance on unseen domain could decrease significantly. For example, the mean absolute error (MAE) of age prediction could increase by 57.7 %. To remedy this problem, we introduce an easy-to-use method, named enhanced domain transformation (EDT), to improve the performance on both seen and unseen data. The goal of EDT is to achieve domain adaptation without using labeling and training on unseen images. We evaluate our method comprehensively on seen and unseen data sets considering the factors of demographic distribution, image style and prediction task. All the results demonstrate that EDT improves the performance on seen and unseen data in the tasks of age prediction and DR classification. Equipped with EDT, the \(\mathrm{R}^2\) (coefficient of determination) of age prediction could be greatly improved from 0.599 to 0.765 (n = 29,577) on Crystalvue images, and AUC (area under curve) of DR classification increases from 0.875 to 0.922 (n = 1,015).
Keywords
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
Jain, A.: Fundamentals of Digital Image Processing. Prentice-Hall, Upper Saddle River (1989)
Chollet, F., et al.: Keras. https://keras.io. Accessed 29 Feb 2020
Christ, P.F., et al.: Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 415–423. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_48
DeHoog, E., Schwiegerling, J.: Optimal parameters for retinal illumination and imaging in fundus cameras. Appl. Opt. 47(36), 6769–6777 (2008)
Efron, B.: Better bootstrap confidence intervals. J. Am. Stat. Assoc. 82(397), 171–185 (1987)
Fu, C., et al.: Three dimensional fluorescence microscopy image synthesis and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2221–2229. IEEE (2018)
Graham, B.: Diabetic retinopathy detection competition report. University of Warwick (2015)
Guibas, J.T., Virdi, T.S., Li, P.S.: Synthetic medical images from dual generative adversarial networks (2017). arXiv preprint arXiv:1709.01872
Huang, X., Liu, M.Y., Belongie, S., Kautz., J.: Multimodal unsupervised image-to-image translation. In: Proceedings of the European Conference on Computer Vision, pp. 172–189 (2018)
Jung, W., Park, S., Jung, K.H., Hwang, S.I.: Prostate cancer segmentation using manifold mixup u-net. In Proceedings of the Medical Imaging with Deep Learning (MIDL), pp. 8–10 (2019)
Karimi, D., Dou, H., Warfield, S.K., Gholipour, A.: Deep learning with noisy labels: exploring techniques and remedies in medical image analysis. Med. Image Anal. 65, 101759 (2020)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Li, H., Liu, W., Zhang, H.F.: Investigating the influence of chromatic aberration and optical illumination bandwidth on fundus imaging in rats. J. Biomed. Opt. 20(10), 106010 (2015)
Li, Z., Kamnitsas, K., Glocker, B.: Overfitting of neural nets under class imbalance: analysis and improvements for segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 402–410. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_45
Liskowski, P., Krawiec, K.: Segmenting retinal blood vessels with deep neural networks. IEEE Trans. Med. Imaging 35(11), 2369–2380 (2016)
Maninis, K.-K., Pont-Tuset, J., Arbeláez, P., Van Gool, L.: Deep retinal image understanding. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 140–148. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_17
Panfilov, E., Tiulpin, A., Klein, S., Nieminen, M.T., Saarakkala., S.: Improving robustness of deep learning based knee MRI segmentation: mixup and adversarial domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision Workshops (2019)
Poplin, R., et al.: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2(3), 158 (2018)
Sinthanayothin, C., Boyce, J., Cook, H., Williamson, T.: Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Brit. J. Ophthalmol. 83(8), 902–910 (1999)
Sirinukunwattana, K., et al.: Gland segmentation in colon histology images: the glas challenge contest. Med. Image Anal. 35, 489–502 (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Tajbakhsh, N., et al.: Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med. Image Anal. 63, 101693 (2020)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Yasaka, K., Abe, O.: Deep learning and artificial intelligence in radiology: current applications and future directions. PLoS Med. 15(11), e1002707 (2018)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization (2017). arXiv preprint arXiv:1710.09412
Zhang, L., et. al: When unseen domain generalization is unnecessary? rethinking data augmentation (2019). arXiv preprint arXiv:1906.03347
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Xiong, J. et al. (2020). Improve Unseen Domain Generalization via Enhanced Local Color Transformation. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12262. Springer, Cham. https://doi.org/10.1007/978-3-030-59713-9_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-59713-9_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59712-2
Online ISBN: 978-3-030-59713-9
eBook Packages: Computer ScienceComputer Science (R0)