In-vitro fertilization (IVF), as the most common fertility treatment, has never reached its maximum potentials. Systematic selection of embryos with the highest implementation potentials is a necessary step toward enhancing the effectiveness of IVF. The embryologist evaluates embryo viability by manual microscopic assessment of its components. With the success of deep learning in the medical diagnosis domain, semantic segmentation has the potential to detect crucial components of human embryos for computerized analysis. Manual assessment of embryos components is a crucial task that involves careful observation by embryologists, and this process can be automated using artificial intelligence (AI)-based algorithms. In this project, students are to work with an existing or propose a trained model with algorithm to accurately detect embryo components for analysis using by embryologists.

The project framework should be the following:

1) Data Preparation (Embryo Image Pre-processing)

2) AI/Machine Learning Model (Coded in Python)

3) Simulation and Test (GUI to upload images and report analysis)

Suggestions and technical material will be provided to students through meetings and discussions in coming up with the proper model and code structure.