Development and validation of deep learning based embryo selection across multiple days of transfer

Abstract

This work describes the development and validation of a fully automated deep learning model, iDAScore v2.0, for the evaluation of human embryos incubated for 2, 3, and 5 or more days. We trained and evaluated the model on an extensive and diverse dataset including 181,428 embryos from 22 IVF clinics across the world. To discriminate the transferred embryos with known outcome, we show areas under the receiver operating curve ranging from 0.621 to 0.707 depending on the day of transfer. Predictive performance increased over time and showed a strong correlation with morphokinetic parameters. The model’s performance is equivalent to the KIDScore D3 model on day 3 embryos while it significantly surpasses the performance of KIDScore D5 v3 on day 5+ embryos. This model provides an analysis of time-lapse sequences without the need for user input, and provides a reliable method for ranking embryos for their likelihood of implantation, at both cleavage and blastocyst stages. This greatly improves embryo grading consistency and saves time compared to traditional embryo evaluation methods.

Assessment of artificial intelligence model and manual morphokinetic annotation system as embryo grading methods for successful live birth prediction: a retrospective monocentric study

“…Retrospective studies elaborated on the distribution of artificial intelligence model in the optimization of selecting the most viable embryo for transfer in terms of fetal heartbeat pregnancy which is a proxy for live birth [ 14 ]; especially in young patients, iDAScore was proposed as an optimal prediction model after single vitrified blastocyst transfer [ 35 ]. A recent multi-centre retrospective cohort study showed that iDAScore significantly surpassed the performance of KIDScore on day 5 embryos, with AUC determination proving that outperformance (AUC (KIDScore D5) = 0.645 and AUC (iDAScore v1) = 0.672) [ 36 ].…”

Embryo Transfer is the last Frontier for Deep Machine Learning & Artificial Intelligence in Medically Assisted Reproduction (MAR)

“…Although time-lapse incubators and preimplantation genetic testing for aneuploidy have been introduced to help increase the chances of live birth, the outcomes remain less than ideal. Utilization of artificial intelligence (AI) has become increasingly popular in the medical field and is increasingly being leveraged in the embryology laboratory to help improve IVF outcomes [50][51][52][53][54][55][56][57][58][59][60][61][62][63][64][65] . And assume we have the perfect AI + ML algorithm for prediction of the correct embryo that will implant and give rise to a live birth, you will still need a skilled gynecologist who will safely and successfully transfer this embryo into the AI+ML ranked receptive uterus.…”

A Dataset for Deep Learning based Cleavage-stage Blastocyst Prediction with Time-lapse Images

“…Jorgen [8] explored the use of deep learning for predicting IVF outcomes, demonstrating that 3D CNNs could be trained to predict embryo implantation from static images. It used multicentre data and known implantation results.…”