L26/O-027 Integrating AI-driven hyperspectral sperm imaging for prioritisation of spermatozoa associated with embryo implantation
Human Reproduction · 01.07.2026 · 41 (Supplement_1)
DOI: 10.1093/humrep/deag083.027 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Reproduction, online erschienen am 08.07.2026. Verfasst von M. Gil Juliá und 12 weiteren Autor:innen.
Abstract (Originalsprache)
Study question Can hyperspectral sperm imaging (HS) combined with machine-learning (ML) assign predictive success to selected spermatozoa according to their likelihood of resulting in embryo implantation? Summary answer HS-derived biochemical signatures enable ML-based scoring of clinically selected spermatozoa, increasing the likelihood of achieving embryo implantation per selected attempt. What is known already Sperm selection in assisted reproduction relies predominantly on subjective assessment of morphology and motility, providing limited predictive value for downstream embryological outcomes. Hyperspectral imaging enables non-invasive acquisition of single-cell biochemical fingerprints. Applied to sperm selection, this approach offers a framework for objective and reproducible prioritisation within clinically viable sperm populations, compatible with ICSI workflows. Our group has previously reported promising results using HS-based algorithms to predict fertilization and embryo development, with model precision exceeding routine laboratory success rates. However, it remains essential to evaluate more informative and predictive reproductive outcomes that better reflect reproductive success, such as embryo implantation. Study design, size, duration Prospective study embedded in routine clinical practice including 93 patients undergoing ICSI with either own or donor, fresh or vitrified oocytes, and autologous fresh ejaculate sperm. All ICSI procedures followed the standard practice; with the only addition being hyperspectral imaging after sperm immobilisation and prior microinjection. Hyperspectral images were acquired from 716 immobilised spermatozoa, of which 699 were used for model development. Data were collected January 2022-August 2024. Participants/materials, setting, methods Hyperspectral images were acquired using a 4200M Microscope system coupled to an IX73 inverted microinjector microscope and TruScope v.1.17 software. Full traceability of gametes and embryos was maintained. Implantation was defined as the presence of gestational sacs after an embryo transfer. Model performance was assessed using precision metrics compared with clinical success rates, calculated per microinjected oocyte. Hyperspectral sperm features and clinical variables were used to train XGBoost models. Main results and the role of chance Hyperspectral images were summarised at the single-spermatozoon level by aggregating spectra across segmented pixels, applying quality filtering, and reducing dimensionality using principal component analysis (PCA). The resulting components, combined with routine clinical variables, were used to train an XGBoost classifier. Data were split at patient level into training (n = 459 images), validation (n = 135), and independent test (n = 105) sets to prevent data leakage. Candidate models were ranked using a precision-weighted F-score (Fβ, β = 0.25), and the top-performing model was selected. On the independent test set, the model achieved a precision of 16.67% (Fβ = 16.50%), per microinjected MII oocyte, compared with the clinic’s baseline success rate of 6.67%. At patient level, predicted probabilities showed substantial intra-patient dispersion, with within-patient score ranges spanning up to 0.53, enabling top-1/top-k sperm ranking. Clinically, these findings suggest that AI-based sperm prioritisation could support final microinjection decisions by integrating hyperspectral-derived biological information and improving prioritisation within embryologist-preselected sperm populations, without altering standard ICSI workflows. Limitations, reasons for caution This study evaluated model performance restricted to embryologist-selected sperm, meaning results are applicable to the selected population rather than the entire ejaculate. Sample size is small and single-centered. Embryo implantation outcomes are influenced by maternal factors, including endometrial receptivity, which were not included; therefore model predictions should be interpreted cautiously. Wider implications of the findings These findings indicate that hyperspectral imaging HS combined with ML has the potential to serve as a decision-support strategy for sperm prioritisation within daily routine ICSI workflows. Conditional enrichment of high-probability candidates motivates prospective studies to evaluate its impact on efficiency and clinical outcomes under adapted selection protocols. Trial registration number No
Zitieren
APA
Juliá, M. G., Pellicer, D. M., Pacheco-Rendón, R., Lahoz, R. T., Santos, J. D. L., Beltrán, D., Gámiz, P., Escrich, L., Viloria, T., Mossetti, L., Santos, M. D. L., Egea, R. R., & Garrido, N. (2026). L26/O-027 Integrating AI-driven hyperspectral sperm imaging for prioritisation of spermatozoa associated with embryo implantation. Human Reproduction, 41(Supplement_1). https://doi.org/10.1093/humrep/deag083.027
Vancouver
Juliá MG, Pellicer DM, Pacheco-Rendón R, Lahoz RT, Santos JDL, Beltrán D, et al. L26/O-027 Integrating AI-driven hyperspectral sperm imaging for prioritisation of spermatozoa associated with embryo implantation. Human Reproduction. 2026;41(Supplement_1). doi:10.1093/humrep/deag083.027
BibTeX
@article{Juli2026,
author = {Juliá, M. Gil and Pellicer, D. Muñoz and Pacheco-Rendón, R.M. and Lahoz, R. Trinidad and Santos, J.M. De los and Beltrán, D. and Gámiz, P. and Escrich, L. and Viloria, T. and Mossetti, L. and Santos, M.J. De los and Egea, R. Rivera and Garrido, N.},
title = {L26/O-027 Integrating AI-driven hyperspectral sperm imaging for prioritisation of spermatozoa associated with embryo implantation},
journal = {Human Reproduction},
year = {2026},
volume = {41},
number = {Supplement_1},
doi = {10.1093/humrep/deag083.027}
}
EUVIMED