Automatic Blastomere Recognition from a Single Embryo Image

Abstract

The number of blastomeres of human day 3 embryos is one of the most important criteria for evaluating embryo viability. However, due to the transparency and overlap of blastomeres, it is a challenge to recognize blastomeres automatically using a single embryo image. This study proposes an approach based on least square curve fitting (LSCF) for automatic blastomere recognition from a single image. First, combining edge detection, deletion of multiple connected points, and dilation and erosion, an effective preprocessing method was designed to obtain part of blastomere edges that were singly connected. Next, an automatic recognition method for blastomeres was proposed using least square circle fitting. This algorithm was tested on 381 embryo microscopic images obtained from the eight-cell period, and the results were compared with those provided by experts. Embryos were recognized with a 0 error rate occupancy of 21.59%, and the ratio of embryos in which the false recognition number was less than or equal to 2 was 83.16%. This experiment demonstrated that our method could efficiently and rapidly recognize the number of blastomeres from a single embryo image without the need to reconstruct the three-dimensional model of the blastomeres first; this method is simple and efficient.

Artificial intelligence and machine learning for human reproduction and embryology presented at ASRM and ESHRE 2018

“…Numerous experimental methods have been developed to parse the implantation potential and live birth rate of IVF embryos from images or video, including morphometric analysis by time-lapse imaging [23][24][25][26], mathematical and statistical tools [27,28], and computer-assisted scoring [29,30]. In 2008, the first commercially available time-lapse system (TLS) was sold for use in human in vitro fertilization (IVF) (Primo Vision™, Vitrolife, Göteborg, Sweden) when it was introduced at the European Society of Human Reproduction meeting.…”

Semantic segmentation of human oocyte images using deep neural networks

“…Automatic circle detection has been applied to analyze the images of day three embryos. The method has been applied for automatic detection of blastomers [ 16 ]. Raudonis et al [ 17 ] propose an automated detection human embryo using a Haar feature-based cascade classifier, the radiating lines and the technique of deep learning obtaining accuracy for embryo detection around 90%.…”

Predicting pregnancy rate following multiple embryo transfers using algorithms developed through static image analysis

“…According to the different stages of embryo development, several algorithms are avaialble for embryo quality assessment. For cleavage stage embryos (Gabrielsen et al, 2000;Hesters et al, 2008;Tian et al, 2014), evaluation systems are primarily based on several factors, including fragmentation rate, presence of mononucleated blastomeres, number and size of nuclei, thickness of the zona pellucida and number and symmetry of blastomeres. For blastocyst stage embryos (Balaban et al, 2006b;Gardner et al, 2004;Papanikolaou et al, 2006), the degree of expansion of the blastocyst cavity, the inner cell mass and the number and cohesion of trophectoderm cells are the main considerations.…”