Leveraging Artificial Intelligence Technology for IVF Embryo Selection | Press room

An artificial intelligence algorithm can non-invasively determine, with about 70 percent accuracy, whether an in vitro fertilized embryo has a normal or abnormal number of chromosomes, according to a new study from Weill Cornell Medicine researchers.

Having an abnormal number of chromosomes, a condition called aneuploidy, is one of the main reasons that embryos derived from in vitro fertilization (IVF) fail to implant or result in a healthy pregnancy. One of the current methods of detecting aneuploidy involves biopsy-like sampling and genetic testing of cells from an embryo, an approach that adds cost to the IVF process and is invasive to the embryo. The new algorithm, STORK-A, described in a paper published December 19 in Lancet Digital Health, may help predict aneuploidy without the drawbacks of biopsy. It works by analyzing microscopic images of the embryo and incorporates information about maternal age and the IVF clinic score on the appearance of the embryo.

“Our hope is that ultimately we can predict aneuploidy in a completely non-invasive way, using artificial intelligence and computer vision techniques,” said the study’s lead author. Dr Iman Hajirasoulihaassociate professor of computational genomics and of physiology and biophysics at Weill Cornell Medicine and member of the England Institute of Precision Medicine.

The study’s first author is Josue Barnes, a doctoral student at the Weill Cornell Graduate School of Medical Sciences who studies at the Hajirasouliha Laboratory. dr. Nikica Zaninovicassociate professor of embryology in clinical obstetrics and gynecology and director of the Laboratory of Embryology at the Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine at Weill Cornell Medicine and NewYork-Presbyterian/Weill Cornell Medical Center led the embryology work for the study.

According to the US Centers for Disease Control and Prevention, more than 300,000 IVF cycles were performed in the United States in 2020, resulting in around 80,000 live births. IVF experts are always looking for ways to increase that success rate, to achieve more successful pregnancies with fewer embryo transfers, which means developing better methods to identify viable embryos.

Fertility clinic staff currently use microscopy to evaluate embryos for large-scale abnormalities that correlate with poor viability. To obtain information about the chromosomes, the clinic staff may also use a biopsy method called preimplantation genetic testing for aneuploidy (PGT-A), predominantly in women older than 37 years.

To develop a computational approach to embryo evaluation that took advantage of the Embryology Laboratory’s pioneering use of time-lapse photography, researchers at the Center for Reproductive Medicine partnered with colleagues at the Englander Institute.

in a 2019 to study, the teams developed an artificial intelligence (AI) algorithm, STORK, which could assess embryo quality as well as the IVF clinic staff. For the new study, they developed STORK-A as a potential replacement for PGT-A, or as a more selective way of deciding which embryos should be tested for PGT-A.

The new STORK-A algorithm uses microscopic images of embryos taken five days after fertilization, the clinic staff’s score on embryo quality, maternal age, and other information typically collected as part of the IVF process. Because it uses AI, the algorithm automatically “learns” to correlate certain features of the data, often too subtle to the human eye, with the possibility of aneuploidy. The team trained STORK-A on a dataset of 10,378 blastocysts for which the ploidy status was already known.

From their performance, they assessed the algorithm’s accuracy in predicting aneuploid “euploid” embryos versus normal chromosomes at nearly 70 percent (69.3%). In predicting aneuploidy involving more than one chromosome (complex aneuploidy) versus euploidy, STORK-A was 77.6% accurate. They subsequently tested the algorithm on independent data sets, including one from an IVF clinic in Spain, and found comparable precision results, demonstrating the generalizability of STORK-A.

The study provides a proof of concept for an approach that is currently experimental. Standardizing the use of STORK-A in clinics would require clinical trials comparing it to PGT-A, and Food and Drug Administration approval, every year in the future. But the new algorithm represents progress on the path to making IVF embryo selection less risky, less subjective, less expensive, and more accurate.

“This is another great example of how AI can potentially transform medicine. The algorithm converts tens of thousands of embryo images into AI models that can ultimately be used to help improve IVF efficacy and further democratize access by lowering costs,” said co-author. Dr AS Element Oliverdirector of the England Institute of Precision Medicine and professor of physiology and biophysics and of computational genomics in computational biomedicine at Weill Cornell Medicine.

“Ultimately, we believe that by using this technology we can reduce the number of embryos to be biopsied, reduce costs and provide a very good tool to consult with the patient when they need to make a decision about whether or not to do PGT-A. . said Dr. Zaninovic.

The team now plans to build on this success with algorithms trained on videos of embryo development.

“By using video classification, we can take advantage of temporal and spatial information about embryo development, and hopefully that will enable the detection of developmental trends that distinguish aneuploidy from euploidy with even greater precision,” Barnes said. .

“This technology is being optimized in the hope that at some point its accuracy will approach that of genetic testing, which is the gold standard and is more than 90 percent accurate,” said the co-author. Dr Zev Rosenwaks, director and chief physician of the Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine at NewYork-Presbyterian/Weill Cornell Medical Center and Weill Cornell Medicine, and Revlon Distinguished Professor of Reproductive Medicine in Obstetrics and Gynecology at Weill Cornell Medicine. “But we realize that this goal is aspirational.”

Many Weill Cornell Medicine physicians and scientists maintain relationships and collaborate with outside organizations to foster scientific innovation and provide expert guidance. The institution makes these disclosures public to ensure transparency. For this information, consult the profiles of Dr Iman Hajirasouliha, dr. Nikica Zaninovic, Dr AS Element Oliver Y Dr Zev Rosenwaks.