Expert-Annotated Embryo Image Dataset with Natural Language Descriptions for Evidence-Based Patient Communication in IVF

2026-04-16

AI Summary

This study addresses the limited interpretability of existing AI-assisted embryo selection methods, which hinders their clinical integration and transparent communication between clinicians and patients. To bridge this gap, the authors construct the first expert-annotated dataset pairing time-lapse embryo images with natural language descriptions encompassing cell cycle phases, developmental stages, and key morphological features. Leveraging this dataset, they fine-tune a vision–language foundation model to automatically generate scientifically grounded and interpretable embryo assessment reports. By introducing natural language descriptions into AI-based embryo evaluation for the first time, this approach substantially enhances decision transparency and the quality of patient–clinician dialogue, offering a trustworthy intelligent support system for assisted reproductive treatments.

Technology Category

• Computer Vision: Language and Vision
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Intelligent Robots: Embodied AI

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Embryo selection is one of multiple crucial steps in in-vitro fertilization, commonly based on morphological assessment by clinical embryologists. Although artificial intelligence methods have demonstrated their potential to support embryo selection by automated embryo ranking or grading methods, the overall impact of AI-based solutions is still limited. This is mainly due to the required adaptation of automated solutions to custom clinical data, reliance on time lapse incubators and a lack of interpretability to understand AI reasoning. The modern, informed patient is questioning expert decisions, particularly if the treatment is not successful. Thus, evidence-based decision justification in tasks like embryo selection would support transparent decision making and respectful patient communication. To support this aim, we hereby present an expert-annotated dataset consisting of embryo images and corresponding morphological description using natural language. The description contains relevant information on embryonic cell cycle, developmental stage and morphological features. This dataset enables the finetuning of modern foundational vision-language models to learn and improve over time with high accuracy. Predicted embryo descriptions can then be leveraged to automatically extract scientific evidence from literature, facilitating well-informed, evidence-based decision-making and transparent communication with patients. Our proposed dataset supports research in language-based, interpretable, and transparent automated embryo assessment and has the potential to enhance the decision-making process and improve patient outcomes significantly over time.

Problem

• embryo selection
• interpretability
• evidence-based communication
• patient transparency
• morphological assessment

Innovation

• vision-language models
• interpretable AI
• embryo selection
• natural language descriptions
• evidence-based decision making