(ANSA) – ROME, APRIL 29 – Artificial intelligence (AI) opens up new scenarios for medically assisted procreation (MAP).
Thanks to artificial neural networks it is in fact possible to identify embryos which, although showing good morphology, have a low probability of implantation. This is what emerges from the study “Analysis of the morphological dynamics of blatocysts” conducted by Marcos Meseguer, scientific supervisor and embologist of the Pma IVI Valencia centers and presented at the 10th Ivirma international congress on reproductive medicine, which took place in recent days in Rum raisin.
In particular, 511 blatocysts (embryos 5-6 days after fertilization) were devitrified, a procedure that precedes implantation in the uterus.
“We are working on an Ai algorithm that studies the behavior of the embryo from devitrification to transfer, which lasts about 4 hours – Meseguer comments – therefore, the Ai shows us that an embryo that starts its expansion early and performs this process rapidly , acquiring a surface area greater than 0.14 square millimeters, can implant up to 30% more than a slower-expanding embryo during those first 4 hours of life.” More than 60% of the re-expanded blastocysts, adds the expert, “were successfully implanted, compared to 6% of those that did not re-expand after devitrification”. (HANDLE).
breaking latest news © Copyright ANSA
