As IVF clinics face greater workloads, the desire to automate some of the laboratory processes is increasing. With the introduction of time-lapse technology many clinics now have full sequence images of embryo development, linked together with clinical outcome. This provides an ideal platform for developing Artificial Intelligence methods which are able to automatically analyse and evaluate embryo implantation potential. To be useful in a clinical setting, the AI must be robust, perform equally well regardless of clinic, observer or patient and able to automatically analyse the full cohort of patient embryos. Although AI examines features which may not be obvious to a human observer, it would be intuitive to expect that scores align with current knowledge of embryo quality.
In this recorded webinar, Jørgen Berntsen, Data Science Manager at Vitrolife, present performance of a fully automated AI-based embryo evaluation algorithm. We will also look at how the AI scores correlate with currently accepted embryo evaluation parameters.
Presenter - Jørgen Berntsen
Jørgen Berntsen received a M.Sc. in biology and a B.Sc. in computer science from Aarhus University. He participated in the development of the first EmbryoScope time-lapse system and has published 27 reviewed articles and more than 10 patent applications. Currently he is working at Vitrolife with AI for embryo selection.