A deep learning approach to predict differentiation outcomes in hypothalamic-pituitary organoids

Abstract

We use three-dimensional culture systems of human pluripotent stem cells for differentiation into pituitary organoids. Three-dimensional culture is inherently characterized by its ability to induce heterogeneous cell populations, making it difficult to maintain constant differentiation efficiency. That is why the culture process involves empirical aspects. In this study, we use deep-learning technology to create a model that can predict from images of organoids whether differentiation is progressing appropriately. Our models using EfficientNetV2-S or Vision Transformer, employing VENUS-coupled RAX expression, predictively class bright-field images of organoids into three categories with 70% accuracy, superior to expert-observer predictions. Furthermore, the model obtained by ensemble learning with the two algorithms can predict RAX expression in cells without RAX::VENUS, suggesting that our model can be deployed in clinical applications such as transplantation.