A team from the Institute of Bioengineering of Catalonia (IBEC) in “Bioengineering in Reproductive Health” has developed a new technology that can visualise the metabolism of embryos obtained by in vitro fertilisation using diagnostic imaging and artificial intelligence, and allows the identification of which of them is more likely to implant correctly in the uterus and reach term. This technique is more precise and reliable than traditional methods and reduces the time to achieve pregnancy.
The innovative method, called ‘METAPHOR’, creates 3D images that reveal the colours of the embryo in a non-invasive manner. This is made possible by certain natural fluorescent compounds in the embryo’s metabolism, which are crucial for processes such as cellular respiration and nutrient consumption. In this way, METAPHOR makes it possible to precisely observe the health status of the embryo.
“This new technology will help increase the probability of success in assisted reproduction processes, reducing the so-called “time to pregnancy” and the economic and psychological strain on patients,” says Samuel Ojosnegros, principal investigator at IBEC and leader of the study.
Artificial intelligence to preserve fertility
The study has been published in the scientific journal PNAS and shows that in studies with mice the success rate in selecting viable embryos was doubled, compared to embryologists using traditional microscopy. In addition, METAPHOR is also very effective in analyzing the metabolism of oocytes, selecting those most suitable for in vitro fertilization. When comparing oocytes from young and older females, the system was able to distinguish with 96% accuracy between young and non-young ones, and predict with more than 80% accuracy which would develop into viable embryos, figures unprecedented in this field.
“We are able to assess the loss of oocyte quality associated with the loss of fertility with age. We look for what are known as “molecular signatures”, characteristics of the cells associated with this loss of fertility, such as the distribution of mitochondria. From this information we are able to predict which oocytes can develop and which cannot. This would represent a major advance in the management of donations and fertility preservation,” explains Anna Seriola, senior researcher in the Ojosnegros group and author of the study.
“We are able to predict which oocytes can develop and which cannot. This would represent a major advance in the management of donations and fertility preservation.”
The technology behind METAPHOR uses artificial intelligence to analyse metabolic images obtained through hyperspectral microscopy. “Using hyperspectral microscopy, we capture hundreds of images containing complex information on many mixed metabolites from embryos and oocytes. To analyse them, we have trained an artificial intelligence tool capable of analysing and classifying these images in a matter of minutes,” says Albert Parra, researcher in the Ojosnegros group and first author of the study.
Thanks to its power and safety, this new method is positioned as a revolutionary tool for evaluating oocytes and embryos according to their physiology. Currently, researchers are adapting this technology to evaluate human embryos and have created a spin-off that will bring the technology to assisted reproduction clinics in the coming years.
Source: Institute for Bioengineering of Catalonia (IBEC)
