Non-invasive pre-implantation genetic testing's reliability for aneuploidy using Cell-free DNA in embryo culture media.

OBJECTIVE: The presence of embryonic cell-free DNA (cfDNA) in spent embryo culture media (SECM) may offer valuable advantages for non-invasive testing of embryo ploidy or genetic characteristics compared to trophectoderm (TE) biopsy. This study aimed to assess the diagnostic potential of SECM cfDNA as a non-invasive sample for chromosomal copy number testing in blastocysts within the clinical setting of in-vitro fertilization. METHOD: This prospective observational study collected 28 SECM cfDNA samples matched with TE biopsy samples from 21 infertile couples who underwent IVF-PGT-A cycles. SECM samples were obtained from blastocysts that were cultured for approximately 5/6 days in an uninterrupted time-lapse incubator. Both sets of samples were collected during the biopsy procedure. The Variseq Illumina platform was utilized for ploidy measurement. The study evaluated the informativity and interpretability of SECM cfDNA, concordance of general ploidy status, and sex chromosome agreement between the two sample types. RESULTS: SECM cfDNA had a high informativity rate (100 %) after double amplification procedure, with a result interpretability of 93 %. Two out of the 28 SECM cfDNA samples were uninterpretable and regarded as overall noise samples. The diagnostic potential of SECM cfDNA, when compared to TE biopsy the standard reference, was relatively low at 50 %. Maternal DNA contamination remains the major obstacle that hinders the widespread clinical adoption of SECM cfDNA in the routine practice of pre-implantation genetic testing for aneuploidy within IVF settings. CONCLUSION: A significant modification must be implemented in the IVF laboratory to minimize DNA contamination and this necessitates suggesting adjustments to oocyte denudation, embryo culture media preparation, and sample collection procedures.

Embryo ploidy status classification through computer-assisted morphology assessment.

BACKGROUND: Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy. OBJECTIVE: Computer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment. STUDY DESIGN: Image processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm. RESULTS: An efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84. CONCLUSION: This research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model.