This is not the first time we have discussed the use of Artificial Intelligence in reproductive medicine. Through several studies, IVI has contributed to the development of this ground-breaking tool in embryo selection. Within the framework of the 38th Congress of the European Society of Human Reproduction and Embryology (ESHRE), we would now like to present a new breakthrough.
Artificial Intelligence: Promising results
The uses of artificial intelligence, current and future, are immense. It is a technology that is here to stay and not only in reproductive medicine, but also in many other fields, such as social, political, economic and even scientific. Artificial Intelligence has a special place in all of them, a privileged place given the dizzying pace at which its applications are growing.
Having said that, we would like to talk to you about the study presented at the current edition of the ESHRE Congress: “Artificial Intelligence (AI) based triage for preimplantation genetic testing (PGT); an AI model that detects novel features in the embryo associated with ploidy”.
Dr. Marcos Meseguer, leader of the study and embryologist and scientific supervisor of IVI Valencia, explains: “This is a pioneering study, since, for the first time in the world, we have developed and combined 5 independent modules that analyse embryo characteristics using computer vision, thus achieving an accuracy of 90% in the prediction of chromosomally normal embryos. Being able to evaluate embryo implantation potential in this way allows us to improve the efficiency of a fundamental process in assisted reproduction, such as embryo culture and selection”.
Results similar to those obtained by conventional biopsies
We are talking about an unprecedented percentage of accuracy, close to that obtained by conventional invasive embryo study. Thanks to the application of Artificial Intelligence, the embryo can be studied by means of complex algorithms, thus avoiding the need to manipulate it and extract cells from it. In addition, the capacity to select viable embryos for subsequent transfer is high.
“The germ of this study responds to an unquestionable reality: Embryonic development does not occur in the same way in euploid –chromosomally normal– and aneuploid –chromosomally abnormal– embryos. At this point, could Artificial Intelligence predict ploidy? The 5 modules that we have been able to analyse and combine show us that yes, it would be possible and reliable”, added Dr. Meseguer.
2,500 embryos were analysed for this study, making it the most important scientifically analysed case study in the world. The result is a non-invasive, universal, innovative technique in the field of embryology, which is also standardised and automatic. This is a clear improvement on all current methods of embryo selection.
The 5 modules studied
- Morphokinetic parameters. This module focuses on the timing of the most important events in embryo development. In other words, it refers to when the embryo divides into cells until it reaches the blastocyst stage.
Dr. Meseguer highlighted: “By simply analysing these parameters in the 2,500 embryos studied, we have been able to verify that, taking an euploid embryo as a reference, if another embryo arrives later than this one at an event, its probability of being aneuploid increases considerably”.
- Embryo morphology. By studying this parameter in an automated way, it has been observed that embryos with good morphology have a higher probability of being chromosomally normal. The morphology itself has a 68% predictive capacity for aneuploidy.
- Cell activity. It is in this module that the diameter of a cell is measured and all the embryo’s cell diameters (from 2 to 8 cells) at a specific moment of its development are added up.
“This automatically calculates values that are then analysed for 160 images, resulting in chromosomally abnormal or aneuploid embryos with a longer diameter length. This is because they take longer to split, the splitting produces many movements and thus increases the measurement”, said Dr. Meseguer.
- Mitochondrial activity. The aim is to associate the pixels, which are the smallest analysable size of an image, with the size of a mitochondrion. After counting the embryo’s pixels, the changes in quantity and distribution are analysed, thus making a comparison between aneuploid and euploid embryos. Aneuploid embryos have a different number of pixels than euploid embryos. It is this module that helps predict aneuploidy, with 77% accuracy.
- Warping/shrinkage. Approximately 20% of embryos show what is known as shrinkage. After automatically analysing this event, we see that in aneuploid embryos it occurs more often.
Dr. Meseguer concluded: “In short, computer vision allows us to emulate our eyes’ capabilities on computers. In other words, it aims to acquire, process, analyse and understand images of the real world in order to produce numerical or symbolic information that can be processed by a computer. And this ultimately allows us to check that embryos behave differently during their development according to their chromosomal content and thus optimise the process of embryo study and the selection of normal and viable embryos for transfer”.
As a result, the combination of these 5 modules together with the algorithm developed by IVI Valencia and the Israeli company AiVF results in an accuracy of 90% in the selection of chromosomally normal embryos, which has a direct impact on an increase in gestation rates. In addition, this would provide a reliable and objective prediction through a fast and, above all, economical technique.
Comments are closed here.