Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading

2025-11-22

AI Summary

Morphological assessment of Day-5 blastocysts in IVF suffers from high subjectivity, poor inter-rater consistency, and is further hindered by scarcity of high-quality labeled data, severe class imbalance, and stringent privacy constraints—impeding robust AI model development. To address these challenges, we propose DIA, a novel framework based on latent-space diffusion modeling, enabling the first controlled, high-fidelity generation of human blastocyst images conditioned on both Gardner grading and Z-axis focal depth. Comprehensive evaluation—including Fréchet Inception Distance (FID), memorization detection, embryologist Turing testing, and downstream classification tasks—demonstrates that synthesized images are indistinguishable from real ones by domain experts. When used for data augmentation, DIA-enhanced training boosts classification accuracy significantly, with up to 40% of real samples replaceable without performance degradation. This establishes a clinically viable paradigm for generating reliable synthetic data to advance AI-driven embryonic assessment.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: AI for Accessibility
• Intelligent Robots: Embodied AI

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The success of in vitro fertilization (IVF) at many clinics relies on the accurate morphological assessment of day 5 blastocysts, a process that is often subjective and inconsistent. While artificial intelligence can help standardize this evaluation, models require large, diverse, and balanced datasets, which are often unavailable due to data scarcity, natural class imbalance, and privacy constraints. Existing generative embryo models can mitigate these issues but face several limitations, such as poor image quality, small training datasets, non-robust evaluation, and lack of clinically relevant image generation for effective data augmentation. Here, we present the Diffusion Based Imaging Model for Artificial Blastocysts (DIA) framework, a set of latent diffusion models trained to generate high-fidelity, novel day 5 blastocyst images. Our models provide granular control by conditioning on Gardner-based morphological categories and z-axis focal depth. We rigorously evaluated the models using FID, a memorization metric, an embryologist Turing test, and three downstream classification tasks. Our results show that DIA models generate realistic images that embryologists could not reliably distinguish from real images. Most importantly, we demonstrated clear clinical value. Augmenting an imbalanced dataset with synthetic images significantly improved classification accuracy (p < 0.05). Also, adding synthetic images to an already large, balanced dataset yielded statistically significant performance gains, and synthetic data could replace up to 40% of real data in some cases without a statistically significant loss in accuracy. DIA provides a robust solution for mitigating data scarcity and class imbalance in embryo datasets. By generating novel, high-fidelity, and controllable synthetic images, our models can improve the performance, fairness, and standardization of AI embryo assessment tools.

Problem

• Address subjective blastocyst grading in IVF through AI standardization
• Overcome data scarcity and class imbalance in embryo datasets
• Generate high-fidelity synthetic blastocyst images for clinical augmentation

Innovation

• Latent diffusion models generate high-fidelity blastocyst images
• Conditioning on morphological categories and focal depth
• Synthetic images improve classification accuracy and replace real data