AI classification of 4-cell embryos as Planar or Tetrahedral (v2)

  • Research type

    Research Study

  • Full title

    Development of an artificial intelligence model capable of analysing embryo images and classifying their arrangement as planar or tetrahedral

  • IRAS ID

    287428

  • Contact name

    Cristina Hickman

  • Contact email

    cristina@apricity.life

  • Sponsor organisation

    Apricity

  • Duration of Study in the UK

    2 years, 0 months, 1 days

  • Research summary

    In vitro fertilization (IVF) has shown remarkable improvements in recent years, with the advent of artificial intelligence (AI) becoming more widely used in healthcare. One of the key areas within IVF, particularly clinically, is evaluating the embryo at a four-cell stage. Notably, the embryo is still totipotent and cell to cell contacts are critical for the fate of the embryo. Thus, the arrangement of a four-cell embryo, whether tetrahedral or more planar in structure, is likely to have a significant impact on embryo outcome: this is also further evidenced by the current literature (Cauffman et al., 2014; Desai & Gill, 2019; T. Ebner et al., 2012; Thomas Ebner et al., 2017).

    However, the process of labelling embryo arrangement remains a manual one performed by clinical embryologists. The creation of an AI capable of performing this task not only addresses this inefficient use of resources, but it may also improve the inconsistencies within the decision making of the currently user-dependent method. Moreover, being able to assess the cellular arrangement of these 4-cell embryos may allow for novel techniques in 3-dimensional (3D) reconstruction of embryos. This in turn may help more accurately determine the outcome of embryos as well, and improve the efficacy of IVF as a whole.

    The aim of this project is to be able to reliably and accurately determine the cell arrangement of 4-cell embryos through AI, with the ultimate goal of integrating this into 3D embryo reconstruction and embryo outcome machine learning (ML) algorithms.

  • REC name

    West Midlands - Black Country Research Ethics Committee

  • REC reference

    20/WM/0317

  • Date of REC Opinion

    3 Dec 2020

  • REC opinion

    Favourable Opinion