Euploidy Rate According to Kidscore Software (Embryoscope Plus®) Evaluation Tool

Abstract

optical signature of each type of microscope, and the presence of foreign objects, such as a holding micropipette present in the image. If a certain optical signature or foreign artifact appeared more in the positive training class compared to the negative training class, the CNN models were found to learn these biases and give a higher score to those images regardless of the embryo morphology. With these insights, a new dataset was prepared that balanced the ratios of positive-to-negative samples for each type of microscope and for each group containing foreign objects. This provided a non-inflated total AUC of 0.72 and significantly raised the lowest per-site AUC from 0.51 to 0.61.CONCLUSIONS: There has been significant recent interest in using deep learning for analyzing images of embryos at the blastocyst stage. The blackbox nature of deep learning models such as CNNs makes it difficult to recognize when potential sources of bias have been introduced during the training process. We performed a series of experiments that identified and reduced two sources of bias, and improved per-clinic performance of the CNN. Future work will continue to search for other sources of bias and address them accordingly.IMPACT STATEMENT: Naive approaches to preparing training data for deep learning models for embryo ranking can create bias in the models. Our work illustrates the need for careful preparation of training data and monitoring of different metrics to identify and reduce potential sources of bias.