Abstract
An accurate and early prediction of a patient’s glaucoma progression can give ophthalmologists insight on how to mitigate the ramifications of the disease before they experience irreversible visual field loss or blindness. Our paper introduces an auxiliary-domain learning framework that trains a convolutional neural network to predict glaucoma progression (main task) and utilizes auxiliary tasks during training, including prediction of the patient age, mean deviation, and optical coherence tomography (OCT) data to improve its accuracy on the main task. The modalities of optic disc photographs and OCT data are often not utilized jointly due to costly machinery. However, we exploit informative features in the OCT, age, and mean deviation data as our learning objective to alleviate the need to acquire the data in clinical deployment. We compared baseline models with no auxiliary outputs to the ones built using auxiliary tasks, and observed a 6.5% increase in Area Under the Receiver Operating Characteristic Curve (AUC-ROC) in the final auxiliary-domain model (91.3 ± 2.6%) compared to the baseline (84.8 ± 4.9%). This study demonstrates the utility of auxiliary tasks when training ophthalmological models by leveraging important patient data that is difficult to acquire during training, even when it is not available as part of the model’s deployment in routine clinical care.
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
Quigley, H.A., Broman, A.T.: The number of people with glaucoma worldwide in 2010 and 2020 (2006)
Allison, K., Patel, D., Alabi, O.: Epidemiology of glaucoma: the past, present, and predictions for the future (2020)
Ting, D.S., et al.: Deep learning in ophthalmology: the technical and clinical considerations. Prog. Retin. Eye Res. 72, 100759 (2019)
Abràmoff, M.D., et al.: Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning. Invest. Ophthalmol. Visual Sci. 57, 5200–5206 (2016)
Shibata, N., et al.: Development of a deep residual learning algorithm to screen for glaucoma from fundus photography. Sci. Rep. 8, 14665 (2018)
Christopher, M., et al.: Deep learning approaches predict glaucomatous visual field damage from oct optic nerve head EN face images and retinal nerve fiber layer thickness maps. Ophthalmology 127, 346–356 (2020)
Dixit, A., Yohannan, J., Boland, M.V.: Assessing glaucoma progression using machine learning trained on longitudinal visual field and clinical data. Ophthalmology 128, 1016–1026 (2021)
Hemelings, R., Elen, B., Barbosa-Breda, J., Blaschko, M.B., De Boever, P., Stalmans, I.: Deep learning on fundus images detects glaucoma beyond the optic disc. Sci. Rep. 11, 20313 (2021)
Sun, Y., Zhu, L., Wang, G., Zhao, F.: Multi-input convolutional neural network for flower grading. J. Electr. Comput. Eng. 2017, 9240407 (2017)
Koch, G., Zemel, R., Salakhutdinov, R., et al.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop, vol. 2, Lille (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Caruana, R.: Multitask learning: a knowledge-based source of inductive bias1. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 41–48. Citeseer (1993)
Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels. CoRR abs/1805.07836 (2018)
Nouri-Mahdavi, K., Mohammadzadeh, V., Rabiolo, A., Edalati, K., Caprioli, J., Yousefi, S.: Prediction of visual field progression from oct structural measures in moderate to advanced glaucoma. Am. J. Ophthalmol. 226, 172–181 (2021)
Sarica, A., Cerasa, A., Quattrone, A.: Random forest algorithm for the classification of neuroimaging data in Alzheimer’s disease: a systematic review. Front. Aging Neurosci. 9, 329 (2017)
Lo, C.S., Wang, C.M.: Support vector machine for breast MR image classification. Comput. Math. Appl. 64, 1153–1162 (2012)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. Appl. 13, 18–28 (1998)
Rish, I., et al.: An empirical study of the Naive Bayes classifier. In: IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, vol. 3, pp. 41–46 (2001)
Kapishnikov, A., Bolukbasi, T., Viégas, F., Terry, M.: Xrai: better attributions through regions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4948–4957 (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. CoRR abs/1505.04597 (2015)
Jin, K., et al.: Fives: a fundus image dataset for artificial intelligence based vessel segmentation. Sci. Data 9, 475 (2022)
Orlando, J.I., et al.: Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med. Image Anal. 59, 101570 (2020)
Mohammed, R., Rawashdeh, J., Abdullah, M.: Machine learning with oversampling and undersampling techniques: overview study and experimental results. In: 11th International Conference on Information and Communication Systems (ICICS). IEEE 2020, pp. 243–248 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, S. et al. (2023). Auxiliary-Domain Learning for a Functional Prediction of Glaucoma Progression. In: Antony, B., Chen, H., Fang, H., Fu, H., Lee, C.S., Zheng, Y. (eds) Ophthalmic Medical Image Analysis. OMIA 2023. Lecture Notes in Computer Science, vol 14096. Springer, Cham. https://doi.org/10.1007/978-3-031-44013-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-44013-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44012-0
Online ISBN: 978-3-031-44013-7
eBook Packages: Computer ScienceComputer Science (R0)
