Early prediction of the transferability of bovine embryos from videomicroscopy
This work addresses the problem of early embryo selection for livestock breeding, but it is incremental as it applies existing deep learning techniques to a specific biological domain.
The paper tackled the problem of predicting bovine embryo transferability from videomicroscopy within four days, using a 3D convolutional neural network with three pathways to address challenges like poor discrimination and small data, achieving favorable accuracy compared to other methods.
Videomicroscopy is a promising tool combined with machine learning for studying the early development of in vitro fertilized bovine embryos and assessing its transferability as soon as possible. We aim to predict the embryo transferability within four days at most, taking 2D time-lapse microscopy videos as input. We formulate this problem as a supervised binary classification problem for the classes transferable and not transferable. The challenges are three-fold: 1) poorly discriminating appearance and motion, 2) class ambiguity, 3) small amount of annotated data. We propose a 3D convolutional neural network involving three pathways, which makes it multi-scale in time and able to handle appearance and motion in different ways. For training, we retain the focal loss. Our model, named SFR, compares favorably to other methods. Experiments demonstrate its effectiveness and accuracy for our challenging biological task.