IDENTIFYING POTENTIAL SOURCES OF BIAS IN DEEP LEARNING MODELS FOR EMBRYO ASSESSMENT

To identify and reduce potential sources of bias when training deep learning models for analyzing images of human embryos. Historical, de-identified images of blastocyst-stage embryos were collected from 11 IVF clinics in the United States between 2015-2020. Each laboratory captured a single image using their existing inverted microscope, stereo zoom microscope, or time-lapse microscope. Approximately 8,000 images were matched to positive...