L2M Validate / Qc Winter 2026 / AI CoPilot for Descriptive Embryo quality Grading

This project aims to develop an AI-assisted decision-support system for embryo quality assessment in in-vitro fertilization (IVF) laboratories. Current evaluation methods, such as the Gardner grading system, rely on subjective visual assessment, leading to high inter- and intra-observer variability that affects clinical decisions and training consistency.

The proposed system will combine computer vision and natural language processing (NLP) to automatically analyze embryo images, suggest standardized Gardner-style grades, and generate clear morphological descriptions in clinical terminology. Unlike existing black box AI tools, this co-pilot emphasizes interpretability and transparency, showing which visual features influence its assessments.

Developed as a human-in-the-loop tool, the system supports embryologists rather than replacing them, improving consistency, documentation, and training across IVF labs. The project also aligns with Canadas priorities in AI-driven healthcare innovation, bridging the gap between academic research and commercial application in reproductive medicine.

Faculty Supervisor:

Abdoulaye Baniré Diallo

Student:

Partner:

V1 Studio

Discipline:

Computer science

Sector:

Education

University:

Université du Québec à Montréal

Program: