Fig. 1: Overview of FedEmbryo workflow, architecture, development and evaluation.
From: Federated task-adaptive learning for personalized selection of human IVF-derived embryos
a Schematic of the FedEmbryo. FedEmbryo is a federated task-adaptive learning (FTAL), which focuses on the client processing multiple tasks simultaneously. We incorporate four private clients collaboratively training the model without any data sharing. For each communication round, every client transmits their local model and the corresponding loss ratio to the server. The server then aggregates these local models and redistributes the updated model to clients. b In FedEmbryo, we introduce the hierarchical dynamic weighting adaptation (HDWA) mechanism to dynamically balance the weight coefficient at both client and task levels. The server (Upper) assigns the aggregated weight based on the loss ratio λt, derived from previous \(t-1\) to \(t-2\) communication rounds. Unlike traditional approaches, where client weight remains fixed, the HDWA mechanism dynamically balances the weight based on client performance in each training round. At the client level (Bottom), the framework manages complex clinical practices, such as morphology assessment (Bottom Left) and prediction of live-birth outcomes (Bottom Right). We utilize the HDWA mechanism to balance the weights to various tasks—such as pronuclear features, symmetry, cell count, fragmentation rate, and blastocyst formation—based on the loss ratios from the two previous local epochs. We integrate images and clinical factors as multimodal input to improve the prediction of live-birth outcomes. c Datasets description (N is the number of patients).
