Noninvasive time-lapse 3D subcellular analysis of embryo development for machine learning-enabled prediction of blastocyst formation
Accurate embryo quality assessment is central to improving outcomes in in vitro fertilization (IVF), yet current practice relies mainly on subjective two-dimensional (2D) morphology. Here we present a label-free framework for quantitative three-dimensional (3D) embryo phenotyping using low-coherence holotomography (HT). Time-lapse HT enabled volumetric imaging of mouse embryos from the 2-cell stage to the blastocyst without affecting developmental competence, capturing subcellular features at high resolution. Quantitative analysis revealed that matured embryos exhibited higher blastomere counts, greater spatial variability, and tighter nuclear packing, whereas arrested embryos showed enlarged blastomeres, elevated cytoplasmic heterogeneity, and fewer, larger nuclei. Machine learning models trained on these features achieved robust prediction of blastocyst formation (AUC up to 0.958). Together, these findings demonstrate that HT provides objective and interpretable 3D biomarkers that could augment and transform embryo selection in IVF.