Assisted Reproductive Technology Dataset of Embryo Time-lapse Images and Clinical Data
Zhylko, D.; Del Gallego, R.; Pardo, S.; Mahmoud, R.; Hsieh, Y. T.; Selim, S.; Nogueira, D.; El-Khatib, I.; Lawrenz, B.; Fatemi, H. M.; Shamout, F. E.
Show abstract
In this report, we present Version 1.0 of the Assisted Reproductive Technology (ART) Dataset, a multi-modal fertility dataset from treatments performed at the ART Fertility Clinic in Abu Dhabi, United Arab Emirates, between 2015 and 2022. The data consists of Electronic Health Records (EHR) and embryo development image sequences captured with the Vitrolife EmbryoScope time-lapse system, providing detailed treatment, morphology, and pregnancy outcome information. The final processed dataset consists of a total of 14,776 embryos from 1,810 patients across 2,500 treatments. This dataset will be used in the development of machine learning models for automated analysis of embryo development and viability, to assist clinical decision-making. This report provides a summary of the statistics of the dataset, as well as the extraction and pre-processing pipelines of the time-lapse images and EHR data. The dataset is private, so we publish this report for transparency on data pre-processing pipelines to share the methodology with similar studies that may arise.
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.