Reseach Article
Explainable Deep Neural Architectures for Morphological Classification of Human Sperm Cells in Automating Reproductive Health Applications
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 108 |
| Year of Publication: 2026 |
| Authors: Rincy T.A. |
10.5120/ijca535437d59d2f
|
Rincy T.A. . Explainable Deep Neural Architectures for Morphological Classification of Human Sperm Cells in Automating Reproductive Health Applications. International Journal of Computer Applications. 187, 108 ( May 2026), 31-38. DOI=10.5120/ijca535437d59d2f
Abstract
Accurate morphological classification of human sperm cells is critical in diagnosing male infertility and automating assisted reproductive technologies (ART). Deep learning-based solutions have demonstrated remarkable performance in this domain. However, the opaque nature of these models poses challenges in clinical acceptance. This study presents an Explainable AI (XAI) framework for the analysis of sperm morphology in reproductive health, using CNN architectures to classify and interpret morphological features of sperm cells. The study employs Grad-CAM (Gradient-weighted Class Activation Mapping) to provide visual explanations for the model's decision-making process, enabling enhanced interpretability of deep learning models in the biomedical domain. The framework focuses on key sperm morphological components, including the head, vacuole, tail, and acrosome, assessing the performance of VGG16, ResNet34 and DenseNet-121 across these categories. Through a comparative evaluation, this study demonstrates the performance of various CNN architectures and the effectiveness of Grad-CAM in highlighting important regions within sperm images, thus providing transparency into the classification process and ensuring model trustworthiness.
References
- Segal, T.R., and Giudice, L.C., 2019. Before the beginning: environmental exposures and reproductive and obstetrical outcomes. Fertility and Sterility; 112(4), 613-21.
- Zegers‐Hochschild, F., and Dickens, B.M., and Dughman‐Manzur, S., 2013. Human rights to in vitro fertilization. International Journal of Gynecology & Obstetrics; 123(1), 86-89.
- MacLeod, J., and Gold, R.Z., 1951. The male factor in fertility and infertility. IV. Sperm morphology in fertile and infertile marriage. Fertil Steril; 2(5):394–414.
- Menkveld, R., Holleboom, C.A., and Rhemrev, J. P., 2011. Measurement and significance of sperm morphology, Asian J. Androl. 13, 59.
- WHO. 2021. Laboratory manual for the examination and processing of human semen. 6th ed. Geneva: World Health Organization.
- Yim, J., Ju, J., Jung, H., and Kim, J., 2015. Image classification using convolutional neural networks with a multi-stage feature. Proceedings of the 3rd International Conference on Robot Intelligence Technology and Applications, November, Beijing, China, Springer. 587–594.
- LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., and Jackel, L. D., 1989. Backpropagation applied to handwritten zip code recognition. Neural Computation. 1, no. 4, 541–551.
- LeCun, Y., Jackel, L. D., Bottou, L., Cortes, C., Denker, J. S., Drucker, H., Guyon, I., Muller, U. A., Sackinger, E., Simard, P., and Vapnik, V., 1995. Learning algorithms for classification: a comparison on handwritten digit recognition. Neural networks: The statistical mechanics perspective. 261.
- Violeta Chang, Laurent Heutte, Caroline Petitjean, Steffen Härtel, and Nancy Hitschfeld, 2017. Automatic classification of human sperm head morphology. Computers in Biology and Medicine, Vol 84, 205-216, ISSN 0010-4825.
- Chang, V., Garcia, A., Hitschfeld, N., and Härtel, S. 2017. Gold-standard for computer-assisted morphological sperm analysis. Comput. Biol. Med. 83, 143–150.
- Goodfellow, I., Bengio, Y., and Courville, Y. 2016. Deep Learning. online: https://mitpress.mit.edu/9780262035613/
- Thirumalaraju, P., Bormann, C.L., Kanakasabapathy, M., Doshi, F., Souter, I., Dimitriadis, I., and Shafiee, H. 2018. Automated sperm morpshology testing using artificial intelligence. Fertil. Steril. 110, e432.
- TP Kanakasabapathy, M.K., Bormann, C.L., Kandula, H., Sai Pavan, S.K., Yarravarapu, D., and Shafiee, H. 2019. Human sperm morphology analysis using smartphone microscopy and deep learning. Fertil. Steril. 112, e41.
- Ilhan, H.O., Serbes, G., and Aydin, N. 2020. Automated sperm morphology analysis approach using a directional masking technique. Comput. Biol. Med. 122, 103845.
- Javadi, S., and Mirroshandel, S.A., 2019. A novel deep learning method for automatic assessment of human sperm images. Comput. Biol. Med. 109, 182–194.
- Riordon, J., McCallum, C., and Sinton, D. 2019. Deep learning for the classification of human sperm. Comput Biol Med. doi: 10.1016/j.compbiomed.2019.103342. Epub: 2019 Jun 25. PMID: 31279166.
- Ilhan, H.O., Yuzkat, M., and Aydin, N. 2021. Sperm Motility Analysis by using Recursive Kalman Filters with the smartphone based data acquisition and reporting approach. Expert Syst. Appl. 186, 115774.
- Ilhan, H.O., Serbes, G., and Aydin, N. 2020. Automated sperm morphology analysis approach using a directional masking technique. Comput. Biol. Med. 122, 103845.
- Abbasi, A., Miahi, E., and Mirroshandel, S.A. 2021. Effect of deep transfer and multi-task learning on sperm abnormality detection. Comput. Biol. Med. 128, 104121.
- Prabaharan, L., and Saravanan, N. 2025. A three stage framework for abnormality detection in sperm cell images using CNN, Biomedical Signal Processing and Control, Vol 99, ISSN 1746-8094.
- Ghasemian, F., Javadi, S., and Mirroshandel, S. A., 2020. MHSMA: The Modified Human Sperm Morphology Analysis Dataset. Mendeley Data, V2. doi:10.17632/hjygss6sw2.2
- Ghasemian, F., Mirroshandel, S.A., Monji-Azad, S., Azarnia, M., and Zahiri, Z. 2015. An efficient method for automatic morphological abnormality detection from human sperm images. Comput. Methods Progr. Biomed. 122, 409–420.
- Simonyan, K., and Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint. https://arxiv.org/abs/1409.1556.
- He, K., Zhang, X., Ren, S., and Sun, J. 2016. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.
- Wu, S., Zhong, S., and Liu, Y. 2018. Deep residual learning for image steganalysis. Multimedia Tools and Applications. 77, no. 9, 10437–10453, https://doi.org/10.1007/ s11042-017-4440-4
- Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. 2017. Densely Connected Convolutional Networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 2261-2269, doi: 10.1109/CVPR.2017.243.
- Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. 2017. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 618–626, doi: 10.1109/ICCV.2017.74.
Index Terms
Keywords