STUDY QUESTION Can a deep learning model predict the probability of pregnancy with fetal heart (FH) from time-lapse videos? SUMMARY ANSWER We created a deep learning model named IVY, which was an objective and fully automated system that predicts the probability of FH pregnancy directly from raw time-lapse videos without the need for any manual morphokinetic annotation or blastocyst morphology assessment. WHAT IS KNOWN ALREADY The contribution of time-lapse imaging in effective embryo selection is promising. Existing algorithms for the analysis of time-lapse imaging are based on morphology and morphokinetic parameters that require subjective human annotation and thus have intrinsic inter-reader and intra-reader variability. Deep learning offers promise for the automation and standardization of embryo selection. STUDY DESIGN, SIZE, DURATION A retrospective analysis of time-lapse videos and clinical outcomes of 10 638 embryos from eight different IVF clinics, across four different countries, between January 2014 and December 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS The deep learning model was trained using time-lapse videos with known FH pregnancy outcome to perform a binary classification task of predicting the probability of pregnancy with FH given time-lapse video sequence. The predictive power of the model was measured using the average area under the curve (AUC) of the receiver operating characteristic curve over 5-fold stratified cross-validation. MAIN RESULTS AND THE ROLE OF CHANCE The deep learning model was able to predict FH pregnancy from time-lapse videos with an AUC of 0.93 [95% CI 0.92–0.94] in 5-fold stratified cross-validation. A hold-out validation test across eight laboratories showed that the AUC was reproducible, ranging from 0.95 to 0.90 across different laboratories with different culture and laboratory processes. LIMITATIONS, REASONS FOR CAUTION This study is a retrospective analysis demonstrating that the deep learning model has a high level of predictability of the likelihood that an embryo will implant. The clinical impacts of these findings are still uncertain. Further studies, including prospective randomized controlled trials, are required to evaluate the clinical significance of this deep learning model. The time-lapse videos collected for training and validation are Day 5 embryos; hence, additional adjustment would need to be made for the model to be used in the context of Day 3 transfer. WIDER IMPLICATIONS OF THE FINDINGS The high predictive value for embryo implantation obtained by the deep learning model may improve the effectiveness of previous approaches used for time-lapse imaging in embryo selection. This may improve the prioritization of the most viable embryo for a single embryo transfer. The deep learning model may also prove to be usef...
XeAuF has been detected and characterized using microwave rotational spectroscopy. It was prepared by laser ablation of Au in the presence of Xe and SF(6), and stabilized in a supersonic jet of Ar. The spectrum was measured with a cavity pulsed jet Fourier transform microwave spectrometer, in the frequency range 6-26 GHz. Rotational constants, centrifugal distortion constants, and (131)Xe and (197)Au nuclear quadrupole coupling constants have been evaluated. The molecule is linear, with a short XeAu bond (2.54 A), and is rigid. The (131)Xe nuclear quadrupole coupling constant (NQCC) is large (-135 MHz). The (197)Au NQCC differs radically from that of uncomplexed AuF. The results are supported by those of ab initio calculations which have given an XeAu dissociation energy approximately 100 kJ mol(-1), plus Mulliken and natural bond orbital populations, MOLDEN plots of valence orbitals, and an energy density distribution. All evidence is consistent with XeAu covalent bonding in XeAuF.
Microwave spectra of the complexes KrAuF and KrAgBr have been measured for the first time using a cavity pulsed jet Fourier transform microwave spectrometer. The samples were prepared by laser ablation of the metal from its solid and allowing the resulting plasma to react with an appropriate precursor (Kr, plus SF6 or Br2) contained in the backing gas of the jet (usually Ar). Rotational constants; geometries; centrifugal distortion constants; vibration frequencies; and 197Au, 79Br, and 81Br nuclear quadrupole coupling constants have all been evaluated. The complexes are unusually rigid and have short Kr-Au and Kr-Ag bonds. The 197Au nuclear quadrupole coupling constant differs radically from its value in an AuF monomer. In addition 83Kr hyperfine structure has been measured for KrAuF and the previously reported complex KrAgF. The geometry of the latter has been reevaluated. Large values for the 83Kr nuclear quadrupole coupling constants have been found for both complexes. Both the 197Au and 83Kr hyperfine constants indicate a large reorganization of the electron distribution on complex formation. A thorough assessment of the nature of the noble gas-noble metal bonding in these and related complexes (NgMX; Ng is a noble gas, M is a noble metal, and X is a halogen) has been carried out. The bond lengths are compared with sums of standard atomic and ionic radii. Ab initio calculations have produced dissociation energies along with Mulliken populations and other data on the electron distributions in the complexes. The origins of the rigidity, dissociation energies, and nuclear quadrupole coupling constants are considered. It is concluded that there is strong evidence for weak noble gas-noble metal chemical bonding in the complexes.
Rotational spectra of KrCuF and KrCuCl have been measured in the frequency range 8-18 GHz, using a pulsed jet cavity Fourier transform microwave spectrometer. The molecules were prepared by ablating Cu metal with a pulsed Nd:YAG laser (1064 nm) and allowing the plasma to react with appropriate precursors (Kr plus SF(6) or Cl(2)) contained in the backing gas of the jet (Ar or Kr). Rotational constants, internuclear distances, vibration frequencies, and (83)Kr, Cu, and Cl nuclear quadrupole coupling constants have all been evaluated. The Kr-Cu bonds are short and the complexes are rigid. The (83)Kr coupling constant of KrCuF is large (128.8 MHz). The Cu nuclear quadrupole coupling constants differ radically from those of uncomplexed CuF and CuCl molecules. The results are supported by those of ab initio calculations, which have also yielded Mulliken populations, MOLDEN plots of valence molecular orbitals and Laplace concentrations, and electron localization functions. The results are consistent with those reported earlier for other noble gas-noble metal halide complexes. The results have been used to assess the nature of the bonding in the complexes and have produced good evidence for weak noble gas-noble metal chemical bonding.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.