EmbryoDiff: A Conditional Diffusion Framework with Multi-Focal Feature Fusion for Fine-Grained Embryo Developmental Stage Recognition

TL;DR

EmbryoDiff introduces a diffusion-based framework utilizing multi-focal feature fusion and semantic-boundary cues to improve fine-grained embryo developmental stage recognition, achieving state-of-the-art accuracy with minimal denoising steps.

Contribution

The paper presents a novel two-stage diffusion model with multi-focal feature fusion and hybrid semantic-boundary conditioning for embryo stage classification, addressing limitations of existing methods.

Findings

Achieves 82.8% and 81.3% accuracy on benchmark datasets.

Outperforms existing methods with a single denoising step.

Effectively alleviates feature ambiguity due to cell occlusions.

Abstract

Identification of fine-grained embryo developmental stages during In Vitro Fertilization (IVF) is crucial for assessing embryo viability. Although recent deep learning methods have achieved promising accuracy, existing discriminative models fail to utilize the distributional prior of embryonic development to improve accuracy. Moreover, their reliance on single-focal information leads to incomplete embryonic representations, making them susceptible to feature ambiguity under cell occlusions. To address these limitations, we propose EmbryoDiff, a two-stage diffusion-based framework that formulates the task as a conditional sequence denoising process. Specifically, we first train and freeze a frame-level encoder to extract robust multi-focal features. In the second stage, we introduce a Multi-Focal Feature Fusion Strategy that aggregates information across focal planes to construct a 3D-aware morphological representation, effectively alleviating ambiguities arising from cell occlusions. Building on this fused representation, we derive complementary semantic and boundary cues and design a Hybrid Semantic-Boundary Condition Block to inject them into the diffusion-based denoising process, enabling accurate embryonic stage classification. Extensive experiments on two benchmark datasets show that our method achieves state-of-the-art results. Notably, with only a single denoising step, our model obtains the best average test performance, reaching 82.8% and 81.3% accuracy on the two datasets, respectively.