Medical / AgriTech · USA
Bovine Embryo Health Assessment — Multi-Model
An AI embryo-assessment platform for grade, stage, pregnancy, and sex prediction: a 30-second time-lapse clip goes in, and a production-ready health assessment comes out.
The challenge
Low expert agreement
Emgenisys research found that embryologists agreed on embryo stage only 59% on average; even highly experienced embryologists with 10+ years reached just 74.6% agreement.
Tiny, drifting subjects
Embryos are small and low-contrast; identity must survive the full-length video.
A production bar, not a demo
Every model had to clear deep evaluation analytics before approval.
The approach
Detection & tracking backbone
Driven to 99% across full-length videos — every prediction starts from a stable, correctly identified subject.
Spatial & temporal pattern recognition
The system analyzes morphology, motion, and change across the clip, combining frame-level visual cues with temporal patterns that are difficult to judge consistently by eye.
Goal-specific model design
Each model is designed around its primary goal — grade, stage, pregnancy, or sex — so the training objective, labels, and evaluation logic match the decision the model must support.
Calibration-aware evaluation & MLOps
Custom evaluation analytics, MLflow experiments, and CI/CD checks helped turn research models into approved production components.
Outcomes
Detection & tracking
Embryo identity held across full-length videos.
Approved for production
Grade, stage, sex, and pregnancy prediction.
Clip to assessment
From raw video to a complete embryo readout.