A foundational model for in vitro fertilization trained on 18 million time-lapse images
Suraj Rajendran, Eeshaan Rehani, William Phu, Qiansheng Zhan, Jonas Malmsten, Marcos Meseguer, Kathleen A. Miller, Zev Rosenwaks, Olivier Elemento, Nikica Zaninović, Iman Hajirasouliha
Abstract
Embryo assessment in in vitro fertilization (IVF) involves multiple tasks—including ploidy prediction, quality scoring, component segmentation, embryo identification, and timing of developmental milestones. Existing methods address these tasks individually, leading to inefficiencies due to high costs and lack of standardization. Here, we introduce FEMI (Foundational IVF Model for Imaging), a foundation model trained on approximately 18 million time-lapse embryo images. We evaluate FEMI on ploidy prediction, blastocyst quality scoring, embryo component segmentation, embryo witnessing, blastulation time prediction, and stage prediction. FEMI attains area under the receiver operating characteristic (AUROC) > 0.75 for ploidy prediction using only image data—significantly outpacing benchmark models. It has higher accuracy than both traditional and deep-learning approaches for overall blastocyst quality and its subcomponents. Moreover, FEMI has strong performance in embryo witnessing, blastulation-time, and stage prediction. Our results demonstrate that FEMI can leverage large-scale, unlabelled data to improve predictive accuracy in several embryology-related tasks in IVF. In vitro fertilisation relies on accurate, non-invasive embryo evaluation to improve success rates. Here, authors present a foundation model trained on 18 million time-lapse images, which outperforms existing benchmarks in ploidy prediction, quality scoring, segmentation, and developmental timing.