Multitasking Embedding for Embryo Blastocyst Grading Prediction (MEmEBG)

TL;DR

This paper introduces a multitask embedding-based method using deep learning to automate and standardize the assessment of embryo quality in IVF, focusing on key blastocyst components.

Contribution

The study presents a novel multitask embedding approach leveraging ResNet-18 to improve embryo component identification and grading from limited image data.

Findings

The method accurately identifies TE and ICM regions and grades them.

Experimental results show improved consistency over traditional visual assessments.

The approach demonstrates potential for robust blastocyst quality evaluation.

Abstract

Reliable evaluation of blastocyst quality is critical for the success of in vitro fertilization (IVF) treatments. Current embryo grading practices primarily rely on visual assessment of morphological features, which introduces subjectivity, inter-embryologist variability, and challenges in standardizing quality assurance. In this study, we propose a multitask embedding-based approach for the automated analysis and prediction of key blastocyst components, including the trophectoderm (TE), inner cell mass (ICM), and blastocyst expansion (EXP). The method leverages biological and physical characteristics extracted from images of day-5 human embryos. A pretrained ResNet-18 architecture, enhanced with an embedding layer, is employed to learn discriminative representations from a limited dataset and to automatically identify TE and ICM regions along with their corresponding grades, structures that are visually similar and inherently difficult to distinguish. Experimental results demonstrate the promise of the multitask embedding approach and potential for robust and consistent blastocyst quality assessment.