A 3-Dimensional Convolutional Neural Network Model to Estimate the Glaucomatous Visual Field from Optical Coherence Tomography
DOI:
https://doi.org/10.51094/jxiv.170Keywords:
optical coherence tomography, glaucoma, visual field, machine learningAbstract
Purpose: To improve the accuracy of glaucomatous visual field (VF) estimations from optical coherence tomography (OCT) images, we trained a segmentation-free 3-dimensional convolutional neural network (3DCNN) model instead of the conventional 2-dimensional model.
Design: Retrospective, single-clinic all-cases survey.
Method: We investigated 3,416 patients (6,356 eyes) who underwent OCT and Humphrey Field Analyzer (HFA) 24-2 or 10-2 tests, including all types of glaucoma or suspected glaucoma. All patients containing intraocular disease with or without glaucoma and all images with a weak signal strength index, except those with VF defects due to extraocular diseases, were included. The teacher values of the VF thresholds to be learned and of the VF threshold slopes to be learned were calculated from the pointwise linear regression of the VF thresholds. The mean VF values of all measurement points were 26.5 ± 6.91 dB [mean ± standard deviation] for HFA24-2 and 27.8 ± 8.30 for HFA10-2.
Results: The root mean square error per paired data for glaucoma cases were 3.27 ± 2.20 dB for HFA24-2 and 3.02 ± 2.28 dB for HFA10-2. The Pearson's correlation between the VF and the estimated VF in glaucoma cases were r=0.848 for HFA24-2 and r=0.882 for HFA10-2. The Pearson's correlation between the mean deviation (MD) and the estimated MD in glaucoma cases were r=0.903 for HFA24-2 and r=0.923 for HFA10-2. The Pearson's correlation between the VF slopes and the estimated VF slopes in glaucoma cases were r=0.431 for HFA24-2 and r=0.438 for HFA10-2. The Pearson's correlation between the MD slopes and the estimated MD slopes in glaucoma cases were r=0.429 for HFA24-2 and r=0.383 for HFA10-2.
Conclusion: The 3DCNN model achieved high VF estimation accuracy using OCT images.
Downloads *Displays the aggregated results up to the previous day.
References
Weinreb, R. N. et al. Primary open-angle glaucoma. Nature Reviews Disease Primers vol. 2 Preprint at https://doi.org/10.1038/nrdp.2016.67 (2016).
Altangerel, U., Spaeth, G. L. & Rhee, D. J. Visual function, disability, and psychological impact of glaucoma. Curr Opin Ophthalmol vol. 14 (2003).
Hashimoto, Y. et al. Predicting 10-2 Visual Field From Optical Coherence Tomography in Glaucoma Using Deep Learning Corrected With 24-2/30-2 Visual Field. Translational Vision Science and Technology 10, (2021).
Asaoka, R. et al. A Joint Multitask Learning Model for Cross-sectional and Longitudinal Predictions of Visual Field Using OCT. Ophthalmology Science 1, 100055 (2021).
Cirafici, P. et al. Point-wise correlations between 10-2 Humphrey visual field and OCT data in open angle glaucoma. Eye (Basingstoke) 35, 868–876 (2021).
Shin, J., Kim, S., Kim, J. & Park, K. Visual field inference from optical coherence tomography using deep learning algorithms: A comparison between devices. Translational Vision Science and Technology 10, (2021).
Sugiura, H. et al. Estimating glaucomatous visual sensitivity from retinal thickness with pattern-based regularization and visualization. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 783–792 (Association for Computing Machinery, 2018). doi:10.1145/3219819.3219866.
Xu, L. et al. Improving Visual Field Trend Analysis with OCT and Deeply Regularized Latent-Space Linear Regression. Ophthalmology Glaucoma 4, (2021).
Xu, L. et al. PAMI: A Computational Module for Joint Estimation and Progression Prediction of Glaucoma. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 3826–3834 (Association for Computing Machinery, 2021). doi:10.1145/3447548.3467195.
Xu, L. et al. Predicting the Glaucomatous Central 10-Degree Visual Field From Optical Coherence Tomography Using Deep Learning and Tensor Regression. American Journal of Ophthalmology 218, (2020).
Hashimoto, Y. et al. Deep learning model to predict visual field in central 10° from optical coherence tomography measurement in glaucoma. British Journal of Ophthalmology 105, (2021).
Asano, S. et al. Predicting the central 10 degrees visual field in glaucoma by applying a deep learning algorithm to optical coherence tomography images. Scientific Reports 11, (2021).
Anderson DR, P. V. Automated Static Perimetry, 2nd edtion. (Mosby, St. Louis, 1999).
Yu, S. et al. Comparison of SITA Faster 24-2C test times to legacy SITA tests. Investigative Ophthalmology and Visual Science 60, (2019).
L.J., S., R.A., R. & D.P., C. Standard or Fast?-Differences in precision between SITA Standard and SITA Fast testing algorithms and their utility for detecting visual field deterioration. Investigative Ophthalmology and Visual Science 55, (2014).
Saunders, L. J., Russell, R. A. & Crabb, D. P. Measurement precision in a series of visual fields acquired by the standard and fast versions of the swedish interactive thresholding algorithm analysis of large-scale data from clinics. JAMA Ophthalmology 133, (2015).
Nakatani, Y., Higashide, T., Ohkubo, S., Takeda, H. & Sugiyama, K. Effect of cataract and its removal on ganglion cell complex thickness and peripapillary retinal nerve fiber layer thickness measurements by fourier-domain optical coherence tomography. Journal of Glaucoma 22, 447–455 (2013).
Kim, M., Eom, Y., Song, J. S. & Kim, H. M. Effect of Cataract Grade according to Wide-Field Fundus Images on Measurement of Macular Thickness in Cataract Patients. Korean Journal of Ophthalmology 32, (2018).
shijianjian. EfficientNet-PyTorch-3D. github.com. Updated July 20, 2021. Accessed May 10, 2022. https://github.com/shijianjian/EfficientNet-PyTorch-3D (2021).
Tan, M. & Le, Q. v. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv preprint:1905.11946 (2019).
Akashi, A. et al. The ability of SD-OCT to differentiate early glaucoma with high myopia from highly myopic controls and nonhighly myopic controls. Investigative Ophthalmology and Visual Science 56, (2015).
Sezgin Akcay, B. I., Gunay, B. O., Kardes, E., Unlu, C. & Ergin, A. Evaluation of the Ganglion Cell Complex and Retinal Nerve Fiber Layer in Low, Moderate, and High Myopia: A Study by RTVue Spectral Domain Optical Coherence Tomography. Seminars in Ophthalmology 32, (2017).
Murata, H., Araie, M. & Asaoka, R. A new approach to measure visual field progression in glaucoma patients using variational bayes linear regression. Invest Ophthalmol Vis Sci 55, (2014).
Downloads
Posted
Submitted: 2022-09-20 04:54:45 UTC
Published: 2022-09-27 00:12:15 UTC — Updated on 2022-10-03 08:59:30 UTC
Versions
Reason(s) for revision
I have added an explanation of the speed of progression of the visual field in the discussion section, as it was not fully explained.License
Copyright (c) 2022
Makoto Koyama
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
