Automated Deep Learning Model for Sperm Head Segmentation, Pose Correction, and Classification
Source abstract
Abstract
Male infertility remains a significant global health concern, with abnormal sperm head morphology recognized as a key factor impacting fertility. Traditional analysis of sperm morphology through manual microscopy is labor-intensive and susceptible to variability among observers. In this study, we introduce a deep learning framework designed to automate sperm head classification, integrating EdgeSAM for precise segmentation with a Sperm Head Pose Correction Network to standardize orientation and position. The classification network employs flip feature fusion and deformable convolutions to capture symmetrical characteristics, which enhances classification accuracy across morphological variations. Our model achieves a test accuracy of 97.5% on the HuSHem and Chenwy datasets, outperforming existing methods and demonstrating greater robustness to rotational and translational transformations. This approach offers a streamlined, automated solution for sperm morphology analysis, providing a reliable tool to support clinical fertility diagnostics and research applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sperm and Testicular Function · Reproductive Biology and Fertility · Ovarian function and disorders
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou 215163, China
School of Electronic and Information Engineering, Soochow University, Donghuan Road No. 50, Suzhou 215031, China
Funding
The High-tech industrialization special project in cooperation between Jilin Province and the Chinese Academy of Sciences
References (29)
Show source-provided references
1. Agarwal, A., Mulgund, A., Hamada, A., and Chyatte, M.R. (2015). A Unique View on Male Infertility around the Globe. Reprod. Biol. Endocrinol., 13.10.1186/s12958-015-0032-1 ↗
2. Physiology of the Reproductive System10.2174/9789815051667122050003 ↗
3. World Health Organization (WHO) (2021). Laboratory Manual for the Examination and Processing of Human Semen.
4. Automatic Classification of Human Sperm Head Morphology10.1016/j.compbiomed.2017.03.029 ↗
5. A Dictionary Learning Approach for Human Sperm Heads Classification10.1016/j.compbiomed.2017.10.009 ↗
6. Sperm Morphologic Features as a Prognostic Factor in in Vitro Fertilization10.1016/S0015-0282(16)49891-2 ↗
7. Effect of Sperm Morphology on Pregnancy Success via Intrauterine Insemination: A Systematic Review and Meta-Analysis10.1016/j.juro.2017.11.045 ↗
8. Variability in the Morphologic Assessment of Human Sperm: Use of the Strict Criteria Recommended by the World Health Organization in 201010.1016/j.fertnstert.2013.12.047 ↗
9. A Comparison of Morphometric Characteristics of Sperm from Fertile Bos Taurus and Bos Indicus Bulls in Brazil10.1016/j.anireprosci.2004.04.019 ↗
10. Gold-Standard for Computer-Assisted Morphological Sperm Analysis10.1016/j.compbiomed.2017.03.004 ↗
11. Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
12. Riordon, J., McCallum, C., and Sinton, D. (2019). Deep Learning for the Classification of Human Sperm. Comput. Biol. Med., 111.10.1016/j.compbiomed.2019.103342 ↗
13. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. arXiv.10.1109/CVPR.2016.308 ↗
14. A Fully Automated Hybrid Human Sperm Detection and Classification System Based on Mobile-Net and the Performance Comparison with Conventional Methods10.1007/s11517-019-02101-y ↗
15. Yüzkat, M., Ilhan, H.O., and Aydin, N. (2021). Multi-Model CNN Fusion for Sperm Morphology Analysis. Comput. Biol. Med., 137.10.1016/j.compbiomed.2021.104790 ↗
16. Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017, January 4–9). Dynamic Routing Between Capsules. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
17. New Conditional Generative Adversarial Capsule Network for Imbalanced Classification of Human Sperm Head Images10.1007/s00521-023-08742-3 ↗
18. Sapkota, N., Zhang, Y., Li, S., Liang, P., Zhao, Z., Zhang, J., Zha, X., Zhou, Y., Cao, Y., and Chen, D.Z. (2024, January 27–30). Shmc-Net: A Mask-Guided Feature Fusion Network for Sperm Head Morphology Classification. Proceedings of the 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece.10.1109/ISBI56570.2024.10635339 ↗
19. Ensembled Deep Learning for the Classification of Human Sperm Head Morphology10.1002/aisy.202200111 ↗
20. Mahali, M.I., Leu, J.-S., Darmawan, J.T., Avian, C., Bachroin, N., Prakosa, S.W., Faisal, M., and Putro, N.A.S. (2023). A Dual Architecture Fusion and AutoEncoder for Automatic Morphological Classification of Human Sperm. Sensors, 23.10.3390/s23146613 ↗
21. Azulay, A., and Weiss, Y. (2019). Why Do Deep Convolutional Networks Generalize so Poorly to Small Image Transformations?. arXiv.
22. Making Convolutional Networks Shift-Invariant Again
23. Liu, R., Wang, M., Wang, M., Yin, J., Yuan, Y., and Liu, J. (2021). Automatic Microscopy Analysis with Transfer Learning for Classification of Human Sperm. Appl. Sci., 11.10.3390/app11125369 ↗
24. Zhou, C., Li, X., Loy, C.C., and Dai, B. (2024). EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM. arXiv.
25. Huang, J., Sivakumar, V., Mnatsakanyan, M., and Pang, G. (2018). Improving Rotated Text Detection with Rotation Region Proposal Networks. arXiv.
26. Chen, W., Song, H., Dai, C., Jiang, A., Shan, G., Liu, H., Zhou, Y., Abdalla, K., Dhanani, S.N., and Fatemeh Moosavi, K. (2024, January 13–17). Automated Sperm Morphology Analysis Based on Instance-Aware Part Segmentation. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan.10.1109/ICRA57147.2024.10611339 ↗
27. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv.
28. Feng, Z., Guo, S., Tan, X., Xu, K., Wang, M., and Ma, L. (2022). Rethinking Efficient Lane Detection via Curve Modeling. arXiv.10.1109/CVPR52688.2022.01655 ↗
29. Iqbal, I., Mustafa, G., and Ma, J. (2020). Deep Learning-Based Morphological Classification of Human Sperm Heads. Diagnostics, 10.10.3390/diagnostics10050325 ↗