Over a million developers have joined DZone.

Using AI in the IVF Process

DZone's Guide to

Using AI in the IVF Process

The Prague Fertility Centre is using artificial intelligence to recognize and sort embryos during the IVF process to make pregnancies smoother and healthier.

· AI Zone ·
Free Resource

Bias comes in a variety of forms, all of them potentially damaging to the efficacy of your ML algorithm. Read how Alegion's Chief Data Scientist discusses the source of most headlines about AI failures here.

AI has been increasingly deployed in various stages of the pregnancy process, from reminding women to take the contraceptive pill, to tracking and monitoring ovulation cycles. The Prague Fertility Centre aims to take things a step further.

They're using AI as part of the IVF process via a fertility treatment that they refer to as CATI (cognitive automation of time-lapse images). They believe it's the first automated technology that uses AI to recognize and sort embryos.

Embryos are sorted according to specific criteria known as morphokinetic. It's a crucial step in the IVF process, as alongside aneuploidy screening (PGS), it helps to prevent the misdiagnosis of mosaic embryos. The team believes that their system can improve the chances of success by 30-40%. In other words, for a 40-year-old woman, whose chances of pregnancy might be ordinarily 20%, it would give them a success probability of around 50-60%, which is akin to that of a much younger woman.

"Preimplantation genetic screening (PGS) is a screening tool that is being used to help further improve embryo selection and is successful. However, there is a drawback with this method in that false negative/positive results can occur in mosaic embryos, leading to the rejection of viable embryos," the researchers say. "CATI removes this disadvantage by detecting abnormal cleavage patterns and providing valuable information on the dynamics of the embryo morphologic changes so that only viable embryos are used. The automatic statistic analysis enables the evaluation of multiple embryo markers at the same time to remove human error and only select those that are relevant to embryo implantation ability."

By applying both PGS and CATI, the team believes they can hugely increase the likelihood of a healthy live birth. What's more, they believe that the process can significantly enhance the probability of success in all women with at least one parameter of their reproductive abilities affected, whether this is due to age, multiple miscarriages, or repeated failure of implantation.

Your machine learning project needs enormous amounts of training data to get to a production-ready confidence level. Get a checklist approach to assembling the combination of technology, workforce and project management skills you’ll need to prepare your own training data.

ai ,healthcare ,image recognition

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}