bioRxiv Science⌕ Search

Biology subjects

kim, g.

Publications and source records attributed to kim, g..

2 recordsLinked to original sources

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.

developmental biology↗

Three-dimensional virtual H&E staining of label-free colon cancer tissue using holotomography and deep learning

In standard histopathology, hematoxylin and eosin (H&E) staining stands as a pivotal tool for cancer tissue analysis. However, this method is limited to two-dimensional (2D) analysis or requires labor-intensive preparation for three-dimensional (3D) inspection of cancer tissues. In this study, we present a method for 3D virtual H&E staining of label-free cancer tissues, employing holotomography and deep learning. Holotomography is used to measure the 3D refractive index (RI) distribution of the label-free cancer slides. A deep learning-based image-to-image translation framework is integrated into the resulting 3D RI distribution, enabling virtual H&E staining in 3D. Our method has been applied to colon cancer tissue slides with thicknesses up to 20 m, with conventional chemical H&E staining providing a direct validation for the method. This framework not only bypasses the conventional staining process but also provides 3D structures of glands, lumens, and individual nuclei. The results demonstrate enhancement in histopathological efficiency and the extension of the standard histopathology into the 3D realm. To validate the repeatability and scalability of the approach, we applied the framework to the gastric cancer slides obtained from different institute and imaging devices.

cancer biology↗