Time-lapse imaging algorithms rank human preimplantation embryos according to the probability of live birth

Fishel, Simon; Campbell, Alison; Montgomery, Sue; Smith, R. L.; Nice, Lynne; Duffy, Samantha; Jenner, Lucy; Berrisford, Kathryn; Kellam, Louise; Smith, R.; Foad, Fiona; Beccles, Ashley

doi:10.1016/j.rbmo.2018.05.016

Cited by 48 publications

(31 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Fortunately, many clinics now have time‐lapse incubators to evaluate embryos without disturbing them in which embryos are briefly exposed to red light to avoid stress derived from direct exposure to light (Maas, Galkina, Thornton, Penzias, & Sakkas, ; Ottosen, HindkjærHindkjaer, & Ingerslev, ). Furthermore, a recent report states that time‐lapse imaging morphokinetic‐based algorithms on blastocysts can predict live births (Fishel et al, ). Gentle pipetting during embryo or gamete manipulation is also recommended to avoid mechanical stress.…”

Section: Embryo Responses To Art‐induced Stress In Humansmentioning

confidence: 99%

Embryo responses to stress induced by assisted reproductive technologies

Ramos‐Ibeas

Heras

Gómez-Redondo

et al. 2019

Molecular Reproduction Devel

View full text Add to dashboard Cite

Assisted reproductive technology (ART) has led to the birth of millions of babies. In cattle, thousands of embryos are produced annually. However, since the introduction and widespread use of ART, negative effects on embryos and offspring are starting to emerge. Knowledge so far, mostly provided by animal models, indicates that suboptimal conditions during ART can affect embryo viability and quality, and may induce embryonic stress responses. These stress responses take the form of severe gene expression alterations or modifications in critical epigenetic marks established during early developmental stages that can persist after birth. Unfortunately, while developmental plasticity allows the embryo to survive these stressful conditions, such insult may lead to adult health problems and to long-term effects on offspring that could be transmitted to subsequent generations. In this review, we describe how in mice, livestock, and humans, besides affecting the development of the embryo itself, ART stressors may also have significant repercussions on offspring health and physiology. Finally, we argue the case that better control of stressors during ART will help improve embryo quality and offspring health. K E Y W O R D S assisted reproductive technologies, bovine, embryo, human, mouse, stress

show abstract

Section: Embryo Responses To Art‐induced Stress In Humansmentioning

confidence: 99%

Embryo responses to stress induced by assisted reproductive technologies

Ramos‐Ibeas

Heras

Gómez-Redondo

et al. 2019

Molecular Reproduction Devel

View full text Add to dashboard Cite

show abstract

“…Previous approaches to morphokinetic analysis (Meseguer et al , 2012; Conaghan et al , 2013; Basile et al , 2014; Milewski et al , 2016; Fishel et al , 2018; Liu et al , 2018) have been based on algorithms that have studied known events in embryological development, such as rapid early cleavage and blastulation, and applied scores to these known events. Deep learning takes an entirely different approach, where time-lapse videos are objectively reviewed with no assumptions at all being made about the significance, or otherwise, of different events in early embryo development.…”

Section: Discussionmentioning

confidence: 99%

“…This latter point is of great physiological interest, as it appears tied to both metabolic activity and embryonic ploidy (Desai et al ., 2018). In an attempt to glean more predictive potential from time-lapse images, several algorithms have been created (Motato et al , 2016; Petersen et al , 2016; Fishel et al , 2018), which take into account the annotated time at which key morphological events occur. Data to date have suggested that this approach may have value in embryo selection, and its efficacy has been studied in randomized trials.…”

Section: Introductionmentioning

confidence: 99%

Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer

Dang¹,

Cooke²,

Illingworth³

et al. 2019

Human Reproduction

232

170

View full text Add to dashboard Cite

STUDY QUESTION Can a deep learning model predict the probability of pregnancy with fetal heart (FH) from time-lapse videos? SUMMARY ANSWER We created a deep learning model named IVY, which was an objective and fully automated system that predicts the probability of FH pregnancy directly from raw time-lapse videos without the need for any manual morphokinetic annotation or blastocyst morphology assessment. WHAT IS KNOWN ALREADY The contribution of time-lapse imaging in effective embryo selection is promising. Existing algorithms for the analysis of time-lapse imaging are based on morphology and morphokinetic parameters that require subjective human annotation and thus have intrinsic inter-reader and intra-reader variability. Deep learning offers promise for the automation and standardization of embryo selection. STUDY DESIGN, SIZE, DURATION A retrospective analysis of time-lapse videos and clinical outcomes of 10 638 embryos from eight different IVF clinics, across four different countries, between January 2014 and December 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS The deep learning model was trained using time-lapse videos with known FH pregnancy outcome to perform a binary classification task of predicting the probability of pregnancy with FH given time-lapse video sequence. The predictive power of the model was measured using the average area under the curve (AUC) of the receiver operating characteristic curve over 5-fold stratified cross-validation. MAIN RESULTS AND THE ROLE OF CHANCE The deep learning model was able to predict FH pregnancy from time-lapse videos with an AUC of 0.93 [95% CI 0.92–0.94] in 5-fold stratified cross-validation. A hold-out validation test across eight laboratories showed that the AUC was reproducible, ranging from 0.95 to 0.90 across different laboratories with different culture and laboratory processes. LIMITATIONS, REASONS FOR CAUTION This study is a retrospective analysis demonstrating that the deep learning model has a high level of predictability of the likelihood that an embryo will implant. The clinical impacts of these findings are still uncertain. Further studies, including prospective randomized controlled trials, are required to evaluate the clinical significance of this deep learning model. The time-lapse videos collected for training and validation are Day 5 embryos; hence, additional adjustment would need to be made for the model to be used in the context of Day 3 transfer. WIDER IMPLICATIONS OF THE FINDINGS The high predictive value for embryo implantation obtained by the deep learning model may improve the effectiveness of previous approaches used for time-lapse imaging in embryo selection. This may improve the prioritization of the most viable embryo for a single embryo transfer. The deep learning model may also prove to be usef...

show abstract

“…The evaluation and use of TLI in the study system, the timing allowance for ICSI, annotation protocols and the strict training and adherence criteria for quality control have all been detailed previously (Fishel et al, 2017(Fishel et al, , 2018. The algorithm did not include morphological criteria or cleavage dysmorphism, and although extensively validated, the effectiveness of an in-house derived algorithm may not produce similar results in other settings (Freour et al, 2015;Liu et al, 2016;Storr et al, 2018), as previously discussed (Fishel et al, 2018).…”

Section: Evaluation Of Time-lapse Images Annotation Protocols and Qumentioning

confidence: 99%

Evolution of embryo selection for IVF from subjective morphology assessment to objective time-lapse algorithms improves chance of live birth

Fishel

Campbell²,

Foad

et al. 2020

Reproductive BioMedicine Online

Self Cite

View full text Add to dashboard Cite

Time-lapse imaging algorithms rank human preimplantation embryos according to the probability of live birth

Cited by 48 publications

References 51 publications

Embryo responses to stress induced by assisted reproductive technologies

Embryo responses to stress induced by assisted reproductive technologies

Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer

Evolution of embryo selection for IVF from subjective morphology assessment to objective time-lapse algorithms improves chance of live birth

Contact Info

Product

Resources

About