
An AI system recently created by Weill Cornell Medicine researchers is capable of determining how likely a 5-day-old in vitro fertilized embryo is to result in successful pregnancy. This is achieved through analysis of time lapse images of early-stage embryos, and has the potential to greatly increase the number of successful in vitro fertilization pregnancies.
In their study, published this week in NPJ Digital Medicine, the team used 12,000 images of human embryos taken 110 hours after fertilization to train the AI algorithm to differentiate between viable and unhealthy embryos. These embryos were first assigned a grade by an embryologist based on its appearance. The researchers then performed a statistical analysis relating this grade to the embryo’s chance of resulting in a successful pregnancy.
The embryos were considered to have good quality if this chance was 58 percent or higher, and below 35 percent was deemed to be poor quality. The study found that the AI platform, known as Stork, was able to correctly classify new images with 97 percent accuracy.
READ MORE: Michigan Researchers use 3D Printing to Aid Arthritis Patients at Low Costs
“By introducing new technology into the field of IVF we can automate and standardize a process that was very dependent on subjective human judgement,” said Dr. Zev Rosenwaks, director and physician-in-chief of the Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine at NewYork-Presbyterian/Weill Cornell Medical Center and Weill Cornell Medicine. “This pioneering work gives us a window into how this field might look in the future.” Rosenwaks is also the Revlon Distinguished Professor of Reproductive Medicine in Obstetrics and Gynecology at Weill Cornell Medicine.
It is estimated that infertility affects roughly 8 percent of women in a chlid-bearing age range. In virto fertilization has given many of these women a chance to give birth, but the average success rate of these procedures in the U.S. is only 45 percent. This AI algorithm offers an accurate and convenient means of analyzing the embryo prior to implantation, and will hopefully increase the percentage of successful pregnancies resulting from in vitro fertilization.
The process of selecting healthy embryos is currently a challenging task, with experienced embryologists sharing little agreement on how to predict and embryo’s viability.
“We wanted to develop an objective method that can be used to standardize and optimize the selection process to increase the success rates of IVF,” stated Dr. Nikica Zaninovic, co-senior author and director of the Embryology Lab in the Center for Reproductive Medicine.
READ MORE: FDA Cleared AI Systems for Diagnosing Breast Cancer and Brain Bleeding
Stork efficiently determines which embryos are of good quality, however research has suggested that only 80 percent of pregnancy success is tethered to embryo quality. Factors such as maternal age play an important role in successful implantation of the embryo as well.
The system is currently an investigative tool, but the researchers have plans to incorporate additional parameters to improve the algorithm.
Infertility affects about 8% of women of child-bearing age. While #IVF has helped millions give birth, the average success rate in the US is approximately 45%.#WCM researchers have begun using AI in hopes of drastically improving success rates.
Link: https://t.co/n3SHBIPTve pic.twitter.com/qv8lxqoYSj
— Weill Cornell Medicine (@WeillCornell) April 4, 2019
Source: Weill Cornell Medicine