Time-Lapse Video-Based Embryo Grading via Complementary Spatial-Temporal Pattern Mining

TL;DR

This paper introduces a novel AI framework that utilizes full-length time-lapse videos to assess embryo quality holistically, aiming to improve IVF success rates by mimicking embryologists' evaluation process.

Contribution

It proposes the first video-based embryo grading paradigm using a comprehensive dataset and a dual-branch model that captures both structural and developmental features.

Findings

Outperforms existing methods in embryo grading accuracy

Effectively integrates static and dynamic embryo features

Provides a new benchmark dataset for embryo assessment

Abstract

Artificial intelligence has recently shown promise in automated embryo selection for In-Vitro Fertilization (IVF). However, current approaches either address partial embryo evaluation lacking holistic quality assessment or target clinical outcomes inevitably confounded by extra-embryonic factors, both limiting clinical utility. To bridge this gap, we propose a new task called Video-Based Embryo Grading - the first paradigm that directly utilizes full-length time-lapse monitoring (TLM) videos to predict embryologists' overall quality assessments. To support this task, we curate a real-world clinical dataset comprising over 2,500 TLM videos, each annotated with a grading label indicating the overall quality of embryos. Grounded in clinical decision-making principles, we propose a Complementary Spatial-Temporal Pattern Mining (CoSTeM) framework that conceptually replicates embryologists' evaluation process. The CoSTeM comprises two branches: (1) a morphological branch using a Mixture of Cross-Attentive Experts layer and a Temporal Selection Block to select discriminative local structural features, and (2) a morphokinetic branch employing a Temporal Transformer to model global developmental trajectories, synergistically integrating static and dynamic determinants for grading embryos. Extensive experimental results demonstrate the superiority of our design. This work provides a valuable methodological framework for AI-assisted embryo selection. The dataset and source code will be publicly available upon acceptance.