Early prediction of the transferability of bovine embryos from videomicroscopy

TL;DR

This paper presents a multi-scale 3D CNN model called SFR that predicts bovine embryo transferability from time-lapse videos within four days, addressing data scarcity and class ambiguity challenges.

Contribution

The study introduces a novel multi-path 3D CNN architecture with focal loss for early embryo transferability prediction from videomicroscopy.

Findings

SFR outperforms other methods in accuracy

Effective handling of appearance and motion features

Addresses class ambiguity and limited data issues

Abstract

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.