无需染色即可实现卵子胚胎的亚细胞级3D成像，突破传统光学限制。

Non-invasive morphological assessment is the cornerstone of oocyte and embryo selection in assisted reproductive technology, yet clinical practice remains limited by two-dimensional, qualitative microscopy. While three-dimensional (3D) fluorescence imaging provides cellular insights, its inherent phototoxicity precludes routine clinical use. Conversely, existing label-free modalities fail to resolve subcellular structures in thick specimens due to two distinct physical barriers: large-scale refractive index heterogeneities, such as the cumulus cells surrounding oocytes, that induce severe aberrations; and short-scale fluctuations, primarily from cytoplasmic lipids, that generate a multiple scattering ``fog''. Here, we report an ultra-fast Reflection Matrix Imaging (RMI) platform designed to overcome these depth and resolution limits. By capturing the back-scattered electromagnetic field for a set of plane-wave illuminations at multiple wavelengths, we record a multi-spectral reflection matrix. From this matrix, we leverage digital adaptive focusing algorithms to computationally compensate for sample-induced aberrations while realigning forward multiple scattering trajectories with the single-scattering contribution. This approach enables label-free 3D visualization of oocytes and blastocysts with an unprecedented subcellular resolution of 300 nm throughout the entire specimen volume. We demonstrate the reliable identification of germinal vesicles and nuclear status in stages previously inaccessible to conventional optics, including imaging through dense cumulus cells. Our method provides a powerful, non-invasive tool for objective grading across all pre-implantation stages, potentially transforming decision-making in clinical IVF.