A proof of concept for a deep learning system that can aid embryologists in predicting blastocyst survival after thaw.

Journal: Scientific reports
Published Date: Dec 7, 2022

Abstract

The ability to understand whether embryos survive the thaw process is crucial to transferring competent embryos that can lead to pregnancy. The objective of this study was to develop a proof of concept deep learning model capable of assisting embryologist assessment of survival of thawed blastocysts prior to embryo transfer. A deep learning model was developed using 652 labeled time-lapse videos of freeze-thaw blastocysts. The model was evaluated against and along embryologists on a test set of 99 freeze-thaw blastocysts, using images obtained at 0.5 h increments from 0 to 3 h post-thaw. The model achieved AUCs of 0.869 (95% CI 0.789, 0.934) and 0.807 (95% CI 0.717, 0.886) and the embryologists achieved average AUCs of 0.829 (95% CI 0.747, 0.896) and 0.850 (95% CI 0.773, 0.908) at 2 h and 3 h, respectively. Combining embryologist predictions with model predictions resulted in a significant increase in AUC of 0.051 (95% CI 0.021, 0.083) at 2 h, and an equivalent increase in AUC of 0.010 (95% CI -0.018, 0.037) at 3 h. This study suggests that a deep learning model can predict in vitro blastocyst survival after thaw in aneuploid embryos. After correlation with clinical outcomes of transferred embryos, this model may help embryologists ascertain which embryos may have failed to survive the thaw process and increase the likelihood of pregnancy by preventing the transfer of non-viable embryos.

Authors

  • P Marsh
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • D Radif
    Department of Computer Science, Stanford University, Stanford, USA.
  • P Rajpurkar
    Department of Computer Science, Stanford University, Stanford, USA.
  • Z Wang
    Guangzhou Accurate and Correct Test Company, Guangzhou 510663, China.
  • E Hariton
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA. hariton.md@gmail.com.
  • S Ribeiro
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • R Simbulan
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • A Kaing
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • W Lin
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • A Rajah
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • F Rabara
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.
  • M Lungren
    Center for Artificial Intelligence in Medicine & Imaging, Stanford University, Stanford, USA.
  • U Demirci
    Canary Center for Cancer Early Detection, Stanford University, Stanford, USA.
  • A Ng
    Department of Computer Science, Stanford University, Stanford, USA.
  • M Rosen
    Center for Reproductive Health, Department of Medicine, University of California, San Francisco, USA.

Keywords

External Resources

Popular Topics
Recent Journals