Related Experiment Video
Updated: Jul 17, 2025
00:09
Semiconductor Sequencing for Preimplantation Genetic Testing for Aneuploidy
Published on: August 25, 2019
9.5K
Knowledge-embedded spatio-temporal analysis for euploidy embryos identification in couples with chromosomal
Fangying Chen1,2, Xiang Xie3, Du Cai4,5,6
1Reproductive Medicine Center, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, Guangdong 510080, China.
Chinese Medical Journal
|August 28, 2023
Summary
This study introduces an AI model, AMCFNet, to assess embryo euploidy status in couples with chromosomal rearrangements. The model integrates time-lapse embryo videos and clinical data, showing promise for improving preimplantation genetic testing outcomes.
Area of Science:
- Reproductive Medicine
- Artificial Intelligence in Healthcare
- Genetics
Background:
- Assisted reproductive treatment aims to achieve healthy neonates via euploid blastocyst transfer.
- Current algorithms assess embryo ploidy for normal chromosomes, but AI application for chromosomal rearrangements is unexplored.
Purpose of the Study:
- To develop and evaluate an artificial intelligence model for assessing blastocyst euploidy status in couples with chromosomal rearrangements.
Main Methods:
- Collected time-lapse videos and clinical data from in vitro cultured embryos undergoing preimplantation genetic testing.
- Developed AMSNet for blastocyst formation prediction and AMCFNet, integrating clinical data, for euploidy assessment.
- Tested AMCFNet efficacy on embryos from couples with parental chromosomal rearrangements.
Main Results:
- AMSNet achieved >70% accuracy in predicting blastocyst formation by day 2, increasing to 80% by day 4.
- AMCFNet, using 7 focal points and 4 clinical features, demonstrated an AUC of 0.729 for euploidy assessment in embryos with chromosomal rearrangements.
Conclusions:
- The AMCFNet model effectively assesses euploidy status in blastocysts from couples with chromosomal rearrangements.
- This AI approach integrates embryo imaging and clinical data for improved genetic testing.
