The selection of high-quality embryo is one of the most critical factors for the successful pregnancy rates.
The latest findings in embryology selection techniques led to Artificial Intelligence assistance to help increase the rates furthermore.
The best-quality embryo selection for transfer in IVF plays major role in achieving high pregnancy rates. Profound grading by trained embryologist and other advanced techniques, such as time-lapse imaging, predicts the ability for the endpoint of clinical pregnancy.
Years of research and related findings in improving embryo grading while its development prior the transfer has brought an important "player" into the process. Artificial Intelligence (AI). And as practice and results shows - embryo selection process and implantation prediction together with pregnancy outcomes have reached new level with the assistance of AI.
Yes, it might sound too futuristic using AI to analyse embryos in a standardised way, but it is already becoming a common practice in top IVF clinics processes.
And how does it actually work?
Standard embryo evaluation is performed in a protocolled grading, gathering data and registering development features on a daily basis. Using the time-lapse systems provides much more data and alleviate inconsistencies and time needed to evaluate a cohort of embryos.
AI methods use advanced computer 3D vision and graphically depicts pixel-to-pixel changes from one time-lapse image to the next to find the likely timing of a kinetic change of the embryo.
AI uses deep learning assessment models for prediction of embryo viability using static images captured by optical light microscopy during embryo cultivation phase. This deep learning system dispose of great potential if algorithms are based on qualitative training datasets.
Based on the time-lapse sequences of more than a hundred thousand developing embryos, sophisticated learning system assesses each embryo for likelihood of implantation, ensuring objective and consistent results.
What the embryo grading with AI looks like
Artificial intelligence performs a comprehensive assessment of the growth of the embryos over the cultivation days and analyses the data to whether a fetal heart has developed to identify the embryo with the greatest likelihood of developing. The embryo with the highest score, and therefore the highest potential for leading to a viable fetus, can then be selected for transfer.
AI reviews a massive amount of data, far more than any human could ever process, including hundreds of images from each embryo . The growth patterns from these images are then related to whether each embryo developed into an ongoing pregnancy.
Development in using machine learning, large numbers of annotated embryos with clinical outcome data, were used to establish so called KIDScore - KID" is short for Known Implantation Data. These are mathematical algorithms to support ranking of embryos monitored by time-lapse and correlating embryo development patterns to their implantation potential.
KIDScore decision support tools are designed for use during the embryologists' decision process of prioritising embryos before transfer.
With the development of the deep learning model the system has strengthen its algorithms as more data has become available. The AI-based model was trained using static two or three-dimensional optical light microscope images with known clinical pregnancy outcome. Predictive accuracy was determined by evaluating sensitivity, specificity and overall weighted accuracy, and was visualized using histograms of the distributions of predictions.
As IVF clinics are faced with increasing patient demand, often requiring more and increasingly complex procedures, there is a clear need to automate as many processes as possible to ensure the best treatment quality while optimising clinic resources. Use of artificial intelligence-based systems are already used by top IVF clinics and show great potential for streamlining treatment decisions.
As always when applying new technologies, it is important that they are validated, proven and used as supportive tools not as a replacement for humans.
More to read on our blog: Closer look at cryoshipping containers: cryoshipping containers.