Data Augmentation of Sperm Images Using Generative Adversarial Networks (WGAN-GP)
https://doi.org/10.26594/register.v12i1.5954
Keywords:
Augmentation, Sperm Image, Reproductive Health, WGAN-GP, InovationAbstract
This study analyzes the use of WGAN-GP for data augmentation in the analysis of sperm morphology. WGAN-GP has been the focus in this study for generating sperm microscopy images, which in turn aims to mitigate the problem of data scarcity in medical imaging. A heterogeneous dataset with mixed object categories was initially employed, leading to an FID score of 134, which in turn reflected a high incidence of mode collapse. For this reason, the dataset was divided into subcategories of Normal, Abnormal, and Non-Sperm identifications, with the scores of the subcategories being 59.19, 74.92, and 83.56, respectively, and showing better balanced model stability. This study's primary contribution is the use of WGAN-GP for the first time for sperm image data augmentation and the generation of more realistic synthetic images. Furthermore, this study illustrates the first understanding of the intricacies of data distribution's complexity and its effect on the model's performance, indicating the possibility of improvement using class-based techniques and sophisticated architectures for the generator. The innovation of this study is the application of WGAN-GP to sperm morphology datasets, improving image quality and the stability of the results, coupled with extensive model performance analysis and providing a further understanding of the field of medical image data augmentation.
Downloads
References
[1] World Health Organization, WHO Laboratory Manual for the Examination and Processing of Human Semen, 6th ed. Geneva, Switzerland: WHO, 2021.
[2] Mayo Clinic, “Sperm morphology: What does it mean?” Mayo Clinic, Mar. 2025.
[3] C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” J. Big Data, vol. 6, no. 1, p. 60, 2019.
[4] I. G. S. Mas Diyasa, I. K. E. Purnama, and H. M. Purnomo, “A new method to improve movement tracking of human sperms,” IAENG Int. J. Comput. Sci., vol. 45, no. 4, pp. 1–9, 2019.
[5] M. Frid-Adar et al., “GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification,” arXiv preprint, arXiv:1803.01229, Mar. 2018.
[6] I. G. S. Mas Diyasa, W. S. J. Saputra, A. A. N. Gunawan, D. Herawati, S. Munir, and S. Humairah, “Abnormality determination of spermatozoa motility using Gaussian mixture model and matching-based algorithm,” J. Robot. Control, vol. 5, no. 1, pp. 103–116, Jan. 2024.
[7] Wikipedia, “Generative adversarial network,” Jun. 2024.
[8] M. M. Saad, R. O’Reilly, and M. H. Rehmani, “A survey on training challenges in generative adversarial networks for biomedical image analysis,” arXiv preprint, arXiv:2201.07646, Jan. 2022.
[9] U. Sirisha, C. K. Kumar, S. C. Narahari, and P. N. Srinivasu, “An iterative PRISMA review of GAN models for image processing, medical diagnosis, and network security,” Comput. Mater. Continua, vol. 82, no. 2, pp. 1757–1810, 2025.
[10] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” in Proc. 34th Int. Conf. Mach. Learn. (ICML), 2017.
[11] I. G. S. Mas Diyasa et al., “Improving classification accuracy of breast ultrasound images using Wasserstein GAN for synthetic data augmentation,” J. Robot. Control, vol. 6, no. 4, pp. 1962–1971, Jul. 2025.
[12] M. Frid-Adar, E. Klang, M. Amitai, J. Goldberger, and H. Greenspan, “GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification,” IEEE Trans. Med. Imaging, vol. 38, no. 3, pp. 736–746, 2018.
[13] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved training of Wasserstein GANs,” in Advances in Neural Information Processing Systems, vol. 30, 2017.
[14] P. Huang, X. Liu, and Y. Huang, “Data augmentation for medical MR image using generative adversarial networks,” arXiv preprint, arXiv:2111.14297, 2021.
[15] A. Abduazimov and G. Jo, “Morpho-GAN: Unsupervised learning of data with high morphology using generative adversarial networks,” in Proc. Korean Comput. Inf. Soc. Winter Conf., vol. 28, no. 1, 2020.
[16] X. Du, X. Ding, M. Xi, Y. Lv, S. Qiu, and Q. Liu, “A data augmentation method for motor imagery EEG signals based on DCGAN-GP network,” Brain Sci., vol. 14, no. 4, p. 375, 2024.
[17] P. Rana et al., “Data augmentation with improved regularisation and sampling for imbalanced blood cells classification using Wasserstein divergence GAN, mixup, and nonlinear mixup,” 2022.
[18] H. Ilhan, “Sperm morphology image data set (SMIDS),” Mendeley Data, ver. 1, 2022, doi: 10.17632/6xvdhc9fyb.1.
[19] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Upper Saddle River, NJ, USA: Prentice Hall, 2018.
[20] A. K. Jain, Fundamentals of Digital Image Processing. Englewood Cliffs, NJ, USA: Prentice-Hall, 1989.
[21] W. K. Pratt, Digital Image Processing: PIKS Inside, 3rd ed. New York, NY, USA: Wiley, 2001.
[22] J. C. Russ, The Image Processing Handbook, 6th ed. Boca Raton, FL, USA: CRC Press, 2011.
[23] T. M. Nguyen, T. H. Le, and H. G. Lim, “A comparative study on data preprocessing in deep learning-based medical image analysis,” Appl. Sci., vol. 13, no. 14, p. 8103, Jul. 2023.
[24] A. Kirillov et al., “Segment Anything,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 10399–10409.
[25] Z. Chen, Y. Zhang, Y. Zhang, and X. Liu, “GAN-based image generation: A survey and taxonomy,” IEEE Trans. Neural Netw. Learn. Syst., pp. 1–22, 2024, doi: 10.1109/TNNLS.2024.3387820.
[26] J. O. Öfele, “On the effective design of generative adversarial networks,” Ph.D. dissertation, Dept. Comput. Sci., Technical Univ. Munich, Munich, Germany, 2023.
[27] A. S. Lundervold and A. L. T. A. T. H. Anonsen, “An overview of deep learning in medical imaging,” in Deep Learning in Medical Imaging and Multimodal Learning for Clinical Decision Support. Cham, Switzerland: Springer, 2023, pp. 1–23.
[28] D. Samal, P. Agrawal, V. Madaan, and V. Goyal, “Efficient deepfake detection using convolutional neural network,” in Proc. Int. Conf. Intelligent Control, Computing and Communications (IC3), 2025, doi: 10.1109/IC363308.2025.10957581.
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 I Gede Susrama Mas Diyasa, Hajjar Ayu Cahyani Kuswardhani , Mohammad Idhom, Prismahardi Aji Riyantoko, Deshinta Arrova Dewi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Please find the rights and licenses in Register: Jurnal Ilmiah Teknologi Sistem Informasi. By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.
1. License
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author(s)' Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User/Public Rights
Register's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, Register permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and Register on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
Copyright and other proprietary rights relating to the article, such as patent rights,
The right to use the substance of the article in own future works, including lectures and books,
The right to reproduce the article for own purposes,
The right to self-archive the article (please read out deposit policy),
The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Register: Jurnal Ilmiah Teknologi Sistem Informasi).
5. Co-Authorship
If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. Register will not be held liable for anything that may arise due to the author(s) internal dispute. Register will only communicate with the corresponding author.
6. Royalties
Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that Register entitles the author(s) to no royalties or other fees.
7. Miscellaneous
Register will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. Register's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.
