Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction

TL;DR

This paper introduces a large, annotated embryo video dataset and a public benchmark for morphokinetic prediction, enabling the development and evaluation of deep learning models in IVF.

Contribution

It provides the first comprehensive public dataset and benchmark for embryo development phase prediction using deep learning, with detailed annotations of 16 phases.

Findings

Deep learning models outperform traditional algorithmic methods.

ResNet, LSTM, and ResNet-3D achieve high accuracy on the benchmark.

The dataset includes 704 videos with 337,000 images, covering detailed developmental phases.

Abstract

An important limitation to the development of Artificial Intelligence (AI)-based solutions for In Vitro Fertilization (IVF) is the absence of a public reference benchmark to train and evaluate deep learning (DL) models. In this work, we describe a fully annotated dataset of 704 videos of developing embryos, for a total of 337k images. We applied ResNet, LSTM, and ResNet-3D architectures to our dataset and demonstrate that they overperform algorithmic approaches to automatically annotate stage development phases. Altogether, we propose the first public benchmark that will allow the community to evaluate morphokinetic models. This is the first step towards deep learning-powered IVF. Of note, we propose highly detailed annotations with 16 different development phases, including early cell division phases, but also late cell divisions, phases after morulation, and very early phases, which have never been used before. We postulate that this original approach will help improve the overall performance of deep learning approaches on time-lapse videos of embryo development, ultimately benefiting infertile patients with improved clinical success rates (Code and data are available at https://gitlab.univ-nantes.fr/E144069X/bench_mk_pred.git).