Novel and conventional embryo parameters as input data for artificial neural networks: an artificial intelligence model applied for prediction of the implantation potential

Bori, Lorena; Payá, Elena; Alegre, Lucía; Viloria, Thamara; Remohı́, José; Naranjo, Valery; Meseguer, M.

doi:10.1016/j.fertnstert.2020.08.023

Cited by 64 publications

(31 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At the morula stage, partial compaction with excluded or extruded cells seems to have an adverse effect on blastulation, blastocyst morphology, and live births [ 59 ]. At the blastocyst stage, trophectoderm cell cycle length and blastocyst expanded diameter were described as independent variables that could discriminate implanted from non-implanted embryos [ 60 ].…”

Section: Discussionmentioning

confidence: 99%

Change in the Strategy of Embryo Selection with Time-Lapse System Implementation—Impact on Clinical Pregnancy Rates

Boucret

Tramon

Saulnier

et al. 2021

JCM

View full text Add to dashboard Cite

Time-lapse systems (TLS) and associated algorithms are interesting tools to improve embryo selection. This study aimed to evaluate how TLS and KIDScore™ algorithm changed our practices of embryo selection, as compared to a conventional morphological evaluation, and improved clinical pregnancy rates (CPR). In the study group (year 2020, n = 303 transfers), embryos were cultured in an EmbryoScope+ time-lapse incubator. A first team observed embryos conventionally once a day, while a second team selected the embryos for transfer based on time-lapse recordings. In the control group (year 2019, n = 279 transfers), embryos were selected using the conventional method, and CPR were recorded. In 2020, disagreement between TLS and the conventional method occurred in 32.1% of transfers, more often for early embryos (34.7%) than for blastocysts (20.5%). Irregular morphokinetic events (direct or reverse cleavage, multinucleation, abnormal pronuclei) were detected in 54.9% of the discordant embryos. When it was available, KIDScore™ was decreased for 73.2% of the deselected embryos. Discordant blastocysts mainly corresponded with a decrease in KIDScore™ (90.9%), whereas discordant Day 3 embryos resulted from a decreased KIDScore™ and/or an irregular morphokinetic event. CPR was significantly improved in the TLS group (2020), as compared to the conventional group (2019) (32.3% vs. 21.9%, p = 0.005), even after multivariate analysis. In conclusion, TLS is useful to highlight some embryo development abnormalities and identify embryos with the highest potential for pregnancy.

show abstract

Section: Discussionmentioning

confidence: 99%

Change in the Strategy of Embryo Selection with Time-Lapse System Implementation—Impact on Clinical Pregnancy Rates

Boucret

Tramon

Saulnier

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

“…First, training models for embryo ranking should focus exclusively on embryo intrinsic features. These may include engineered features that measure specific embryo properties such as the appearance of pronuclei and fading timing (tPNa, tPNf), the number of pronuclei, pronuclei shape, symmetry [21, 22, 23] blastocyst expanded diameter and trophectoderm cell cycle length [24], temporal events [25, 26] and/or training deep neural networks on the raw images [13] while avoiding embryo-extrinsic clinical factors that are shared by the other sibling embryos within the cohort. Second, the ambiguity in the KID-N labels makes implantation prediction a sub-optimal optimization problem both in model training as well as in model evaluation.…”

Section: Discussionmentioning

confidence: 99%

Solving the “right” problems for effective machine learning driven in vitro fertilization

Erlich

Ben‐Meir

Har-Vardi

et al. 2021

Preprint

View full text Add to dashboard Cite

Automated live embryo imaging has transformed in-vitro fertilization (IVF) into a data-intensive field. Unlike clinicians who rank embryos from the same IVF cycle cohort based on the embryos visual quality and determine how many embryos to transfer based on clinical factors, machine learning solutions usually combine these steps by optimizing for implantation prediction and using the same model for ranking the embryos within a cohort. Here we establish that this strategy can lead to sub-optimal selection of embryos. We reveal that despite enhancing implantation prediction, inclusion of clinical properties hampers ranking. Moreover, we find that ambiguous labels of failed implantations, due to either low quality embryos or poor clinical factors, confound both the optimal ranking and even implantation prediction. To overcome these limitations, we propose conceptual and practical steps to enhance machine-learning driven IVF solutions. These consist of separating the optimizing of implantation from ranking by focusing on visual properties for ranking, and reducing label ambiguity.

show abstract

“…Bori and co-workers in a retrospective study including 637 patients who underwent eSBT, described how the use of an artificial neural network model can be applied in predicting implantation potential. The unique feature of this study was the description of novel morphokinetic features as well as utilizing commonly accepted markers and yielded an AUC value of 0.77 [Bori et al, 2020]. Subsequently, the same group published results from a retrospective study where they tested three artificial NN aimed to predict live births from euploid embryos by combining blastocyst morphology extracted from single static image.…”

Section: Artificial Intelligence and Future Perspectivementioning

confidence: 99%

Focus on time-lapse analysis: blastocyst collapse and morphometric assessment as new features of embryo viability

Sciorio

Meseguer²

2021

Reproductive BioMedicine Online

Self Cite

View full text Add to dashboard Cite

Novel and conventional embryo parameters as input data for artificial neural networks: an artificial intelligence model applied for prediction of the implantation potential

Cited by 64 publications

References 63 publications

Change in the Strategy of Embryo Selection with Time-Lapse System Implementation—Impact on Clinical Pregnancy Rates

Change in the Strategy of Embryo Selection with Time-Lapse System Implementation—Impact on Clinical Pregnancy Rates

Solving the “right” problems for effective machine learning driven in vitro fertilization

Focus on time-lapse analysis: blastocyst collapse and morphometric assessment as new features of embryo viability

Contact Info

Product

Resources

About