Генерування аберометричних даних шляхом застосування генеративно-змагальної нейронної мережі

Maksym Oleksandrovych Yaroshenko

doi:10.20535/2523-4455.mea.286366

Vol. 28 · Issue 3 · 2023 Dec 27, 2023 Electronic Systems and Signals

Human Eye Aberrometry Data Generation Using Generative Adversarial Neural Network

Maksym Oleksandrovych Yaroshenko Corresponding Національний технічний університет України "Київський політехнічний інститут імені Ігоря Сікорського" Ukraine

Pages286366.1-286366.8 PublishedDec 27, 2023

PDF (Ukrainian)

VOL 28 · ISS 3 · 2023 To the 125th Anniversary of Igor Sikorsky Kyiv Polytechnic Institute View issue

Abstract

It’s obvious that for development and improvement of methods and apparatus for diagnosis and treatment of optical flaws of human eye at the modelling stage, it’s necessary to have sets of real measurements. However, data requests to clinics are accompanied by substantial amount of bureaucracy procedures and, at the same time, acquired dataset may be too small, which can be critical, for example, for training of neural networks. According to the analysis of existing publications, publicly available datasets of aberrometry data (sets of eye’s refractive flaws) are rare and consist of relatively low number of measurements. But, due to current development state of neural networks, it is possible to generate data based on real measurements. The most common solutions are methods based on the usage of the Generative Adversarial Networks (GAN). This tendency is also relevant for the modern ophthalmology, but no publications aimed at aberrometry data synthesis were found. For this reason, objective of this work is development of solution for generation of sets of human eye’s refractive errors using neural networks. Proposed solution includes generator and critic networks trained according to the Wasserstein GAN with Gradient Penalty (WGAN GP) algorithm. In order to improve training, the method of data augmentation called Data Augmentation Optimized for GAN (DAG) was used, moreover, the possibility of augmentation of aberrometry data in two forms was implemented — for both Zernike coefficient vectors and wavefront pixel images. According to the result’s evaluation, generated data has the distribution close to the real sample (Fréchet distance equals 0.7) and, at the same time, it is neither a copy of real measurements (92% creativity rate) nor duplication of a few aberration sets (diversity metric equals 3.64 which is close to the optimal 3.83). The direction of further improvement includes enhancement of existing architectures of generator and critic, search or creation of bigger training dataset and refinement of data augmentation technics.

Keywords

#Ophthalmology #Generative adversarial networks #Data augmentation

References

S. M. Khan et al., “A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability,” Lancet Digit Health, vol. 3, no. 1, pp. e51–e66, Jan. 2021, DOI: https;//doi.org/10.1016/S2589-7500(20)30240-5
A. You, J. K. Kim, I. H. Ryu, and T. K. Yoo, “Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey,” Eye and Vision, vol. 9, no. 1, p. 6, Dec. 2022, DOI: https;//doi.org/10.1186/s40662-022-00277-3
I. J. Goodfellow et al., “Generative Adversarial Networks,” Jun. 2014, URL: https://arxiv.org/abs/1406.2661
J. Jarosz, P. Mecê, J.-M. Conan, C. Petit, M. Paques, and S. Meimon, “High temporal resolution aberrometry in a 50-eye population and implications for adaptive optics error budget,” Biomed Opt Express, vol. 8, no. 4, p. 2088, Apr. 2017, DOI: https;//doi.org/10.1364/BOE.8.002088
I. Chyzh, G. Tymchyk, and T. Shisha, Aberometriya optychnoyi systemy oka lyudyny: Monohrafiya [Aberrometry of the optical system of the human eye: Monograph]. Kyiv, Ukraine: National Technical University of Ukraine “Kyiv Polytechnic Institute,” 2013.
V. Lakshminarayanan and A. Fleck, “Zernike polynomials: a guide,” J Mod Opt, vol. 58, no. 7, pp. 545–561, Apr. 2011, DOI: https://doi.org/10.1080/09500340.2011.554896
M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” Jan. 2017, URL: https://arxiv.org/abs/1701.07875
I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved Training of Wasserstein GANs,” Mar. 2017, URL: https://arxiv.org/abs/1704.00028
N.-T. Tran, V.-H. Tran, N.-B. Nguyen, T.-K. Nguyen, and N.-M. Cheung, “On Data Augmentation for GAN Training,” IEEE Transactions on Image Processing, vol. 30, pp. 1882–1897, 2021, DOI: https://doi.org/10.1109/TIP.2021.3049346
M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” Jun. 2017, URL: https://arxiv.org/abs/1706.08500
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, DOI: https;//doi.org/10.1109/5.726791
T. Chen, X. Zhai, M. Ritter, M. Lucic, and N. Houlsby, “Self-Supervised GANs via Auxiliary Rotation Loss,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 12146–12155, DOI: https://doi.org/10.1109/CVPR.2019.01243
“CIFAR-10 and CIFAR-100 datasets.” [Online]. Available: https://www.cs.toronto.edu/~kriz/cifar.html . [Accessed: 16-Jul-2023].
S. Guan and M. Loew, “Evaluation of Generative Adversarial Network Performance Based on Direct Analysis of Generated Images,” in 2019 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 2019, pp. 1–5, DOI: https://doi.org/10.1109/AIPR47015.2019.9174595
C. Szegedy et al., “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1–9, DOI: https://doi.org/10.1109/CVPR.2015.7298594
D. C. Dowson and B. V. Landau, “The Fréchet distance between multivariate normal distributions,” J Multivar Anal, vol. 12, no. 3, pp. 450–455, Sep. 1982, DOI: https;//doi.org/10.1016/0047-259X(82)90077-X
Z. Wang, E. P. Simoncelli, and A. C. Bovik, “Multiscale structural similarity for image quality assessment,” in The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, pp. 1398–1402, DOI: https;//doi.org/10.1109/ACSSC.2003.1292216
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Dec. 2014, URL: https://arxiv.org/abs/1412.6980
“Kaggle: Your Machine Learning and Data Science Community.” [Online]. Available: https://www.kaggle.com/ . [Accessed: 04-Aug-2023]
“TensorFlow.” [Online]. Available: https://www.tensorflow.org/ . [Accessed: 04-Aug-2023]
“SciPy.” [Online]. Available: https://scipy.org/ . [Accessed: 04-Aug-2023]
“Matplotlib — Visualization with Python.” [Online]. Available: https://matplotlib.org/ . [Accessed: 04-Aug-2023]
H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, “Self-Attention Generative Adversarial Networks,” May 2018, URL: https://arxiv.org/abs/1805.08318

Previous in issue A Model of a Free-Space Optical Communication Line with a Smart Reflector Next in issue Using Information about Experimental Conditions to Predict Properties of Metamaterials

§ 06 — Related

Similar Articles

Anton Volodymyrovych Mnevets, Nataliia Heorhiivna Ivanushkina, Siamеse Neural Network’s Models for Cardiac Arrhythmia Classification in the Conditions of Shortage of Training Ecg Signals , Microsystems, Electronics and Acoustics: Vol. 30 No. 2 (2025)
Volodymyr Semenovych Lazebnyi, Chengliang Yin, Estimation of probabilistic processes in wireless networks of 802.11 standard , Microsystems, Electronics and Acoustics: Vol. 22 No. 5 (2017)
Anastasiia Volodymyrivna Pareniuk, PhD Dmytro Volodymyrovych Pareniuk, PhD, Researcher Kateryna L. Rudenka, Practical Method of Estimating Safe Sounds for a Person with PTSD , Microsystems, Electronics and Acoustics: Vol. 31 No. 2 (2026)
Maksym Serhiiovych Fil, Dnys Yurevych Lebeddev, Leonid Mykolaiovych Pavlov, Increase the Resistance of Digital Television to Interference , Microsystems, Electronics and Acoustics: Vol. 24 No. 5 (2019)
Dmytro A. Shevchuk, PhD, Assoc. Prof. Nataliia Heorhiivna Ivanushkina, A A Complex Method for Non-invasive Fetal Electrocardiogram Signal Extraction and Cardiac Arrhythmia Classification , Microsystems, Electronics and Acoustics: Vol. 31 No. 2 (2026)
Ivan Andriiovych Vakulenko, PhD, Assoc. Prof. Dmytro Anatoliiovych Mykolaiets, PhD, Assoc. Prof. Kateryna Serhiivna Klen, Simulation Modeling of a Filter-Compensating Converter for a Three-Phase Three-Wire Network , Microsystems, Electronics and Acoustics: Vol. 31 No. 2 (2026)
Tymofii Andriiovych Khodniev, Oleksandr Ihorovych Antoniuk, Anton Yuriiovych Varfolomieiev, Oleksandr Mykolaiovych Lysenko, By-Layer Decomposition Model for Evaluating the Integral Communication Path Utilization Efficiency with Account for Errors , Microsystems, Electronics and Acoustics: Vol. 23 No. 6 (2018)
Dmytro V. Pareniuk, Sergey A. Naida, The Study of the Possibility of Usage of the Sokolov’s Criteria for Assessing the Results of Directed Influence on the Auditory System of a Biological Object , Microsystems, Electronics and Acoustics: Vol. 24 No. 3 (2019)
Myhailo Yuhymovych Artemenko, Larysa Mykolaivna Batrak, Serhii Yosyfovych Polishchuk, Apparent Power and Efficiency of Three-Phase Four-Wire System , Microsystems, Electronics and Acoustics: Vol. 23 No. 3 (2018)
Yana Vjyatsheslavivna Kabushka, Anton Serhiiovych Zotko, Ivan Viktorovich Kandrachuk, Oleksii Volodymyrovych Korzhyk, Range of Detection of Small Air Objects by the Grounding Noise Receivers System , Microsystems, Electronics and Acoustics: Vol. 23 No. 5 (2018)

1-10 of 30 Next

You may also start an advanced similarity search for this article.

[1] S. M. Khan et al., “A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability,” Lancet Digit Health, vol. 3, no. 1, pp. e51–e66, Jan. 2021, DOI: https;//doi.org/10.1016/S2589-7500(20)30240-5

[2] A. You, J. K. Kim, I. H. Ryu, and T. K. Yoo, “Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey,” Eye and Vision, vol. 9, no. 1, p. 6, Dec. 2022, DOI: https;//doi.org/10.1186/s40662-022-00277-3

[3] I. J. Goodfellow et al., “Generative Adversarial Networks,” Jun. 2014, URL: https://arxiv.org/abs/1406.2661

[4] J. Jarosz, P. Mecê, J.-M. Conan, C. Petit, M. Paques, and S. Meimon, “High temporal resolution aberrometry in a 50-eye population and implications for adaptive optics error budget,” Biomed Opt Express, vol. 8, no. 4, p. 2088, Apr. 2017, DOI: https;//doi.org/10.1364/BOE.8.002088

[5] I. Chyzh, G. Tymchyk, and T. Shisha, Aberometriya optychnoyi systemy oka lyudyny: Monohrafiya [Aberrometry of the optical system of the human eye: Monograph]. Kyiv, Ukraine: National Technical University of Ukraine “Kyiv Polytechnic Institute,” 2013.

[6] V. Lakshminarayanan and A. Fleck, “Zernike polynomials: a guide,” J Mod Opt, vol. 58, no. 7, pp. 545–561, Apr. 2011, DOI: https://doi.org/10.1080/09500340.2011.554896

[7] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” Jan. 2017, URL: https://arxiv.org/abs/1701.07875

[8] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved Training of Wasserstein GANs,” Mar. 2017, URL: https://arxiv.org/abs/1704.00028

[9] N.-T. Tran, V.-H. Tran, N.-B. Nguyen, T.-K. Nguyen, and N.-M. Cheung, “On Data Augmentation for GAN Training,” IEEE Transactions on Image Processing, vol. 30, pp. 1882–1897, 2021, DOI: https://doi.org/10.1109/TIP.2021.3049346

[10] M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” Jun. 2017, URL: https://arxiv.org/abs/1706.08500

[11] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, DOI: https;//doi.org/10.1109/5.726791

[12] T. Chen, X. Zhai, M. Ritter, M. Lucic, and N. Houlsby, “Self-Supervised GANs via Auxiliary Rotation Loss,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 12146–12155, DOI: https://doi.org/10.1109/CVPR.2019.01243

[13] “CIFAR-10 and CIFAR-100 datasets.” [Online]. Available: https://www.cs.toronto.edu/~kriz/cifar.html . [Accessed: 16-Jul-2023].

[14] S. Guan and M. Loew, “Evaluation of Generative Adversarial Network Performance Based on Direct Analysis of Generated Images,” in 2019 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 2019, pp. 1–5, DOI: https://doi.org/10.1109/AIPR47015.2019.9174595

[15] C. Szegedy et al., “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1–9, DOI: https://doi.org/10.1109/CVPR.2015.7298594

[16] D. C. Dowson and B. V. Landau, “The Fréchet distance between multivariate normal distributions,” J Multivar Anal, vol. 12, no. 3, pp. 450–455, Sep. 1982, DOI: https;//doi.org/10.1016/0047-259X(82)90077-X

[17] Z. Wang, E. P. Simoncelli, and A. C. Bovik, “Multiscale structural similarity for image quality assessment,” in The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, pp. 1398–1402, DOI: https;//doi.org/10.1109/ACSSC.2003.1292216

[18] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Dec. 2014, URL: https://arxiv.org/abs/1412.6980

[19] “Kaggle: Your Machine Learning and Data Science Community.” [Online]. Available: https://www.kaggle.com/ . [Accessed: 04-Aug-2023]

[20] “TensorFlow.” [Online]. Available: https://www.tensorflow.org/ . [Accessed: 04-Aug-2023]

[21] “SciPy.” [Online]. Available: https://scipy.org/ . [Accessed: 04-Aug-2023]

[22] “Matplotlib — Visualization with Python.” [Online]. Available: https://matplotlib.org/ . [Accessed: 04-Aug-2023]

[23] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, “Self-Attention Generative Adversarial Networks,” May 2018, URL: https://arxiv.org/abs/1805.08318

Human Eye Aberrometry Data Generation Using Generative Adversarial Neural Network

Abstract

Keywords

References

Similar articles in this journal

Quasistatic Identification of The Shading Structure of Solar Panels by The Method of Cardinal Number Vectors

A A Complex Method for Non-invasive Fetal Electrocardiogram Signal Extraction and Cardiac Arrhythmia Classification

Simulation Modeling of a Filter-Compensating Converter for a Three-Phase Three-Wire Network

Most read articles by the same author(s)

Similar Articles