Abstract

Artificial intelligence is evolving in the field of embryology, offering exciting possibilities for improved results in Assisted Reproductive Technologies such as In Vitro Fertilization. The morphological quality of blastocysts of day 5 human embryo is a vital factor for determining the success of In Vitro Fertilization Hence making accurate and automated analysis of embryonic structures essential. To achieve an automated assessment of human embryo quality on the basis of morphological image features, it is crucial to precisely segment the regions of the embryo. In this research, a comprehensive analysis of U-Net and its variants for the semantic segmentation of human embryo day 5 blastocyst images is performed. Based on this insights gained from the comparative analysis, a novel Ensemble segmentation model is proposed to exploit the complementary strengths of multiple models. The proposed ensemble approach demonstrates robust performance, achieving an overall segmentation accuracy of 98%, with an F1-score of 0.95081 and a Jaccard index of 0.90625, indicating high spatial agreement between predicted and ground-truth segmentations. The framework effectively addresses key challenges inherent to blastocyst imaging, including low-contrast boundaries, heterogeneous cellular organization, and limited annotated data. By enabling precise and reproducible segmentation of critical embryonic regions, the proposed method provides a reliable foundation for automated embryo quality assessment and grading systems. This work also contributes to the integration of biologically inspired computational models into clinical embryology and supports the broader adoption of AI-driven decision support tools in reproductive medicine.

Keywords

In Vitro Fertilization (IVF), Image Analysis, Artificial Intelligence, Deep Learning Neural Networks, Human Embryos, Day-5 Blastocysts,

Downloads

Download data is not yet available.

References

  1. World Health Organization. (2025) WHO Fact Sheet, Infertility.
  2. https://www.who.int/news-room/fact-sheets/detail/infertility
  3. N. Purkayastha, H. Sharma, Prevalence and Potential Determinants of Primary Infertility in India: Evidence from Indian Demographic Health Survey. Clinical Epidemiology and Global Health, 9, (2021) 162-170. https://doi.org/10.1016/j.cegh.2020.08.008
  4. Ministry of Health and Family Welfare, Government of India. (2021) National Family Health Survey (NFHS-5), 2019–21: India Fact Sheet. International Institute for Population Sciences (IIPS), Mumbai, India.
  5. C.L. Bormann, M.K. Kanakasabapathy, P. Thirumalaraju, R. Gupta, R. Pooniwala, H. Kandula, E. Hariton, I. Souter, I. Dimitriadis, L.B. Ramirez, C.L. Curchoe, J. Swain, L.M. Boehnlein, H. Shafiee, Performance of a Deep Learning-Based Neural Network in the Selection of Human Blastocysts for Implantation. Elife, 9, (2020) e55301. https://doi.org/10.7554/eLife.55301
  6. L.L. Veeck, R.G. Gosden, (1999). An atlas of human gametes and conceptuses: An Illustrated Reference for Assisted Reproductive Technology, Parthenon Publishing Group, New York
  7. A. Pandian, A. Bhattacharya, E. Ozturk, S. Templeton, (2013) Number of Embryos for Transfer Following IVF or ICSI. Cochrane Database of Systematic Reviews. https://doi.org/10.1002/14651858.CD003416.pub4
  8. D.K. Gardner, M. Lane, J. Stevens, T. Schlenker, W.B. Schoolcraft, Blastocyst Score affects implantation and pregnancy outcome: towards a Single Blastocyst Transfer. Fertility and Sterility, 73(6), (2000) 1155–1158. https://doi.org/10.1016/S0015-0282(00)00518-5
  9. P. Khosravi, E. Kazemi, Q. Zhan, J.E. Malmsten, M. Toschi, P. Zisimopoulos, A. Sigaras, S. Lavery, L.A. Cooper, C. Hickman, M. Meseguer, Deep Learning Enables Robust Assessment and Selection of Human Blastocysts after in Vitro Fertilization. NPJ Digital Medicine, 2(1), (2019) 21. https://doi.org/10.1038/s41746-019-0096-y
  10. E.J. Topol, High-Performance Medicine: the Convergence of human and Artificial Intelligence. Nature Medicine, 25, (2019) 44–56. https://doi.org/10.1038/s41591-018-0300-7
  11. G. Litjens, T. Kooi, B.E. Bejnordi, A.A.A. Setio, F. Ciompi, M. Ghafoorian, J.A.W.M. van der Laak, B. van Ginneken, C.I. Sánchez, A survey on Deep Learning in Medical Image Analysis. Medical Image Analysis, 42, (2017) 60–88. https://doi.org/10.1016/j.media.2017.07.005
  12. O. Ronneberger, P. Fischer, T. Brox, U-Net: convolutional networks for biomedical image segmentation, in: N. Navab, J. Hornegger, W. Wells, A. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science, Springer, Cham, 9351, (2015) 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
  13. S.E. Roshan, J. Tanha, M. Zarrin, A.F. Babaei, H. Nikkhah, Z. Jafari, A Deep Ensemble Medical Image Segmentation. Computers in Biology and Medicine, 172, (2024) 108305. https://doi.org/10.1016/j.compbiomed.2024.108305
  14. P. Saeedi, D. Yee, J. Au, J. Havelock, Automatic Identification of Human Blastocyst Components Via Texture. IEEE Transactions on Biomedical Engineering, IEEE, 64(12), (2017) 2968–2978. https://doi.org/10.1109/TBME.2017.2664817
  15. T.G. Dietterich, Ensemble Methods in Machine learning, in: Multiple Classifier Systems, MCS 2000, Lecture Notes in Computer Science, Springer, Berlin, Heidelberg, 1857, (2000) 1-15. https://doi.org/10.1007/3-540-45014-9_1
  16. R. Barkavi, G. Yamuna, C. Jayaram, (2023) Artificial Intelligence: Revolution in Assisted Reproductive Technology, in: S. Kumar, S. Hiranwal, S. Purohit, M. Prasad (Eds.), Proceedings of International Conference on Communication and Computational Technologies, ICCCT 2023, Algorithms for Intelligent Systems, Springer, Singapore. https://doi.org/10.1007/978-981-99-3485-0_76
  17. A.A. Taha, A. Hanbury, Metrics for Evaluating 3D Medical Image Segmentation: Analysis, Selection, and Tool. BMC Medical Imaging, 15(1), (2015) 29. https://doi.org/10.1186/s12880-015-0068-x
  18. M.R. Islam, M.M. Rahman, M.S. Ali, A.A.N. Nafi, M.S. Alam, T.K. Godder, M.S. Miah, M.K. Islam, Enhancing Breast Cancer Segmentation and Classification: An Ensemble Deep Convolutional Neural Network and U-Net Approach on Ultrasound Images, Machine Learning with Applications, 16, (2024) 100555.. https://doi.org/10.1016/j.mlwa.2024.100555
  19. P. Thirumalaraju, M.K. Kanakasabapathy, C.L. Bormann, R. Gupta, R. Pooniwala, H. Kandula, I. Souter, I. Dimitriadis, H. Shafiee, Evaluation of Deep Convolutional Neural Networks in Classifying Human Embryo Images based on their Morphological Quality. Heliyon, 7(2), (2021) e06298. https://doi.org/10.1016/j.heliyon.2021.e06298
  20. A. Targosz, P. Przystałka, R. Wiaderkiewicz, G. Mrugacz, Semantic Segmentation of Human Oocyte Images using Deep Neural Networks. BioMedical Engineering OnLine, 20(1), (2021) 40.https://doi.org/10.1186/s12938-021-00864-w
  21. A. Khan, S. Gould, M. Salzmann, (2016) Segmentation of Developing Human Embryo in Time-Lapse Microscopy. IEEE 13th International Symposium on Biomedical Imaging (ISBI), IEEE, Prague, Czech Republic. https://doi.org/10.1109/ISBI.2016.7493417
  22. B. Dhiyanesh, M. Vijayalakshmi, P. Saranya, D. Viji, EnsembleEdgeFusion: Advancing Semantic Segmentation in Microvascular Decompression Imaging with Innovative Ensemble Techniques, Scientific Reports, 15(1), (2025) 17892.https://doi.org/10.1038/s41598-025-02470-5
  23. F.I. Diakogiannis, F. Waldner, P. Caccetta, C. Wu, ResUNet-a: A Deep Learning Framework for Semantic Segmentation of Remotely Sensed Data. ISPRS Journal of Photogrammetry and Remote Sensing, 162, (2020) 94–114.https://doi.org/10.1016/j.isprsjprs.2020.01.013
  24. H. Huang, L. Lin, R. Tong, H. Hu, Q. Zhang, Y. Iwamoto, X. Han, Y.W. Chen, J. Wu, (2020) UNet 3+: a Full-Scale Connected UNet for Medical Image Segmentation. In: ICASSP 2020 – 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, Barcelona, Spain. https://doi.org/10.1109/ICASSP40776.2020.9053405
  25. K. Kamnitsas, C. Ledig, V.F. Newcombe, J.P. Simpson, A.D. Kane, D.K. Menon, D. Rueckert, B. Glocker, Efficient Multi-Scale 3D CNN with fully Connected CRF for Accurate Brain Lesion Segmentation. Medical Image Analysis, 36, (2017) 61–78. https://doi.org/10.1016/j.media.2016.10.004
  26. D. Saadati, O.N. Manzari, S. Mirzakuchaki, (2023) Dilated-UNet: a Fast and Accurate Medical Image Segmentation Approach using a Dilated Transformer and U-Net architecture, arXiv preprint arXiv:2304.11450. https://doi.org/10.48550/arXiv.2304.11450
  27. H. Nematzadeh, J. García-Nieto, I. Navas-Delgado, J.F. Aldana-Montes, Ensemble-Based Genetic Algorithm Explainer with Automized Image Segmentation: a Case Study on Melanoma Detection Dataset. Computers in Biology and Medicine, 155, (2023) 106613. https://doi.org/10.1016/j.compbiomed.2023.106613
  28. R.M. Rad, P. Saeedi, J. Au, J. Havelock, Trophectoderm Segmentation in Human Embryo Images via Inceptioned U-Net. Medical Image Analysis, 62, (2020) 101612. https://doi.org/10.1016/j.media.2019.101612
  29. N. Uysal, T.K. Yozgatlı, E.N. Yıldızcan, E. Kar, M. Gezer , E. Baştu, Comparison of U-Net based Models for Human Embryo Segmentation. Journal of Information Technologies, 15(1), (2022) 35–44. https://doi.org/10.17671/gazibtd.949430
  30. M. Arsalan, A. Haider, S.-W. Cho, Y.-H. Kim, K.R. Park, Human Blastocyst Components Detection using Multiscale Aggregation Semantic Segmentation Network for Embryonic analysis. Biomedicines, 10(7), (2022) 1717. https://doi.org/10.3390/biomedicines10071717
  31. S. Wang, C. Zhou, D. Zhang, L. Chen, H. Sun, A Deep Learning Framework Design for Automatic Blastocyst Evaluation with Multifocal Images. IEEE Access, IEEE, 9, (2021) 18927–18934. https://doi.org/10.1109/ACCESS.2021.3053098
  32. J.M. Gorriz, F. Segovia, J. Ramirez, A. Ortiz, J. Suckling, Is K-fold Cross Validation the Best Model Selection Method for Machine Learning?, arXiv preprint, (2024). https://doi.org/10.48550/arXiv.2401.16407
  33. R. Azad, M. Heidari, K. Yilmaz, M. Hüttemann, S. Karimijafarbigloo, Y. Wu, A. Schmeink, D. Merhof, (2024) Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook. arXiv:2312.05391. https://doi.org/10.48550/arXiv.2312.05391
  34. D.P. Kingma, J. Ba, (2014) Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR), Banff, 14-16.