Public articles linked to the same research event.
Research Square In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.
In this retrospective multicenter study, an in-house deep learning segmentation model delineated the zona pellucida, inner cell mass, and trophectoderm and extracted 17 quantitative morphological indicators from 14,072 blastocyst images across seven Korean centers (after exclusions, 10,718 embryos for consensus grade prediction and 1,387 for fetal heart tone prediction), finding that morphology-based predicted grades agreed with consensus grades more closely than individual embryologists for developmental stage and inner cell mass, and that a quantitative morphology-based Random Forest model outperformed a manual consensus grade-based model for fetal heart tone prediction (AUROC 0.648 versus 0.610; DeLong's test p = 0.