scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Improving embryo selection using a computer-automated time-lapse image analysis test plus day 3 morphology: results from a prospective multicenter trial

TL;DR: Experienced embryologists using Eeva in combination with D3 morphology significantly improved their ability to identify embryos that would reach the usable blastocyst stage, and adjunctive use of morphology plus Eeva also reduced interindividual variability in embryo selection.
About: This article is published in Fertility and Sterility.The article was published on 2013-08-01. It has received 261 citations till now. The article focuses on the topics: Blastocyst Transfer.
Citations
More filters
Journal ArticleDOI
TL;DR: The strategy of culturing and selecting embryos in the integrated EmbryoScope time-lapse monitoring system improves reproductive outcomes.

261 citations

Journal ArticleDOI
04 Apr 2019
TL;DR: An AI-driven approach provides a reproducible way to assess embryo quality and uncovers new, potentially personalized strategies to select embryos.
Abstract: Visual morphology assessment is routinely used for evaluating of embryo quality and selecting human blastocysts for transfer after in vitro fertilization (IVF). However, the assessment produces different results between embryologists and as a result, the success rate of IVF remains low. To overcome uncertainties in embryo quality, multiple embryos are often implanted resulting in undesired multiple pregnancies and complications. Unlike in other imaging fields, human embryology and IVF have not yet leveraged artificial intelligence (AI) for unbiased, automated embryo assessment. We postulated that an AI approach trained on thousands of embryos can reliably predict embryo quality without human intervention. We implemented an AI approach based on deep neural networks (DNNs) to select highest quality embryos using a large collection of human embryo time-lapse images (about 50,000 images) from a high-volume fertility center in the United States. We developed a framework (STORK) based on Google’s Inception model. STORK predicts blastocyst quality with an AUC of >0.98 and generalizes well to images from other clinics outside the US and outperforms individual embryologists. Using clinical data for 2182 embryos, we created a decision tree to integrate embryo quality and patient age to identify scenarios associated with pregnancy likelihood. Our analysis shows that the chance of pregnancy based on individual embryos varies from 13.8% (age ≥41 and poor-quality) to 66.3% (age <37 and good-quality) depending on automated blastocyst quality assessment and patient age. In conclusion, our AI-driven approach provides a reproducible way to assess embryo quality and uncovers new, potentially personalized strategies to select embryos.

224 citations

Journal ArticleDOI
TL;DR: The potential advantages of a TLS include the ability to maintain a stable culture environment, therefore limiting the exposure of embryos to changes in gas composition, temperature and movement, and improving embryo selection for ART treatment by utilising additional information gained through monitoring embryo development.
Abstract: Background Embryo incubation and assessment is a vital step in assisted reproductive technology (ART). Traditionally, embryo assessment has been achieved by removing embryos from a conventional incubator daily for assessment of quality by an embryologist, under a light microscope. Over recent years time-lapse systems (TLSs) have been developed which can take digital images of embryos at frequent time intervals. This allows embryologists, with or without the assistance of computer algorithms, to assess the quality of the embryos without physically removing them from the incubator. The potential advantages of a TLS include the ability to maintain a stable culture environment, therefore limiting the exposure of embryos to changes in gas composition, temperature and movement. Additionally a TLS has the potential advantage of improving embryo selection for ART treatment by utilising additional information gained through monitoring embryo development. Objectives To determine the effect of a TLS compared to conventional embryo incubation and assessment on clinical outcomes in couples undergoing ART. Search methods A comprehensive search of all the major electronic databases, including grey literature, was undertaken in co-ordination with the Trials Search Co-ordinator of the Cochrane Menstrual Disorders and Subfertility Group in July 2014 and repeated in November 2014 to confirm that the review is up to date. Selection criteria Two authors (SA and NA) independently scanned the titles and abstracts of the articles retrieved by the search. Full texts of potentially eligible randomised controlled trials (RCTs) were obtained and examined independently by the authors for their suitability according to the review inclusion criteria. In the case of doubt between the two authors, a third author (LC) was consulted to gain consensus. The selection process is documented with a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) flow chart. Data collection and analysis Data were obtained and extracted by two authors. Disagreement was resolved by consensus. Trial authors were contacted by e-mail to obtain further study information and data. All extracted data were dichotomous outcomes and odds ratios (OR) were calculated on an intention-to-treat basis. Where enough data were available, meta-analysis was undertaken. Main results Three studies involving 994 women were found for inclusion. Data from all three studies were used to address comparison one, TLS with or without cell-tracking algorithms versus conventional incubation. No studies were found to address comparison two, TLS utilising cell-tracking algorithms versus TLS not utilising cell-tracking algorithms. There was only one study which reported live birth (n = 76). The results demonstrated no conclusive evidence of a difference in live birth rate per couple randomly assigned to the TLS and conventional incubation arms of the study (OR 1.1, 95% CI 0.45 to 2.73, 1 RCT, n = 76, moderate quality evidence). All three studies reported miscarriage (n = 994). There was no conclusive evidence of a difference in miscarriage rates per couple randomly assigned to the TLS and conventional incubation arms (OR 0.70, 95% CI 0.47 to 1.04, 3 RCTs, n = 994, I2 = 0%, low quality evidence). Only one study reported stillbirth rates (n = 76). There were equal numbers of stillbirths in both the TLS and conventional incubation arms of the study. Therefore, there was no evidence of a difference in the stillbirth rate per couple randomly assigned to TLS and conventional incubation (OR 1.0, 95% CI 0.13 to 7.49, 1 RCT, moderate quality evidence). All three studies reported clinical pregnancy rates (n = 994). There was no conclusive evidence of a difference in clinical pregnancy rate per couple randomly assigned to the TLS and conventional incubation arms (OR 1.23, 95% CI 0.96 to 1.59, 3 RCTs, n = 994, I2 = 0%, low quality evidence). None of the included studies reported cumulative clinical pregnancy rates. Authors' conclusions There is insufficient evidence of differences in live birth, miscarriage, stillbirth or clinical pregnancy to choose between TLS and conventional incubation. Further data explicitly comparing the incubation environment, the algorithm for embryo selection, or both, are required before recommendations for a change of routine practice can be justified.

184 citations

Journal ArticleDOI
TL;DR: A retrospective analysis demonstrating that the deep learning model has a high level of predictability of the likelihood that an embryo will implant and may improve the effectiveness of previous approaches used for time-lapse imaging in embryo selection.
Abstract: STUDY QUESTION Can a deep learning model predict the probability of pregnancy with fetal heart (FH) from time-lapse videos?

179 citations

Journal ArticleDOI
TL;DR: The algorithm presented here can be used independently of culture conditions and fertilization method and provides predictive power not surpassed by other published algorithms for ranking embryos according to their blastocyst formation potential.
Abstract: STUDY QUESTION Can a generally applicable morphokinetic algorithm suitable for Day 3 transfers of time-lapse monitored embryos originating from different culture conditions and fertilization methods be developed for the purpose of supporting the embryologist's decision on which embryo to transfer back to the patient in assisted reproduction?

163 citations


Cites background or methods from "Improving embryo selection using a ..."

  • ...access cell cycle length and cleavage patterns has resulted in the proposal of predictive algorithms (e.g. Meseguer et al., 2011; Conaghan et al., 2013; VerMilyea et al., 2014; Basile et al., 2015; Milewski et al., 2015; Liu et al., 2016) for different endpoints, including blastocyst formation or implantation....

    [...]

  • ...Meseguer (Meseguer et al., 2011); Basile (Basile et al., 2015); Eeva I, (Conaghan et al., 2013); Eeva II (VerMilyea et al., 2014); Milewski (Milewski et al., 2015); Liu (Liu et al., 2016); Alpha/ESHRE (Alpha Scientists in Reproductive Medicine and ESHRE Special Interest Group of Embryology, 2011)....

    [...]

  • ...…Meseguer et al., 2011, 2012; Azzarello et al., 2012; Cruz et al., 2012; Dal Canto et al., 2012; Rubio et al., 2012, 2014; Chamayou et al., 2013; Conaghan et al., 2013; Freour et al., 2013; Campbell et al., 2013a, 2013b; Aguilar et al., 2014; Liu et al., 2014, 2016; VerMilyea et al. 2014;…...

    [...]

  • ...The algorithms in Conaghan et al. (2013) and VerMilyea et al. (2014) are based on two early time intervals comprising the 4-cell stage....

    [...]

  • ...search for morphokinetic parameters that are characteristic of implantation, blastocyst formation and aneuploidy, and subsequently several reports have been published on this subject (e.g. Lemmen et al., 2008; Wong et al., 2010; Meseguer et al., 2011, 2012; Azzarello et al., 2012; Cruz et al., 2012; Dal Canto et al., 2012; Rubio et al., 2012, 2014; Chamayou et al., 2013; Conaghan et al., 2013; Freour et al., 2013; Campbell et al., 2013a, 2013b; Aguilar et al., 2014; Liu et al., 2014, 2016; VerMilyea et al. 2014; Yalçınkaya et al., 2014; Basile et al., 2015; Cetinkaya et al., 2015; Gardner et al., 2015; Milewski et al., 2015; Yang et al., 2015)....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: The ability to transfer one high-scoring blastocyst should lead to pregnancy rates greater than 60%, without the complication of twins, according to a retrospective review of blastocysts transfer in an IVF clinic.

1,410 citations

Journal ArticleDOI
TL;DR: A multivariable model is proposed based on the findings to classify embryos according to their probability of implantation and it is proposed that the image acquisition and time-lapse analysis system makes it possible to determine exact timing of embryo cleavages in a clinical setting.
Abstract: background: Time-lapse observation presents an opportunity for optimizing embryo selection based on morphological grading as well as providing novel kinetic parameters, which may further improve accurate selection of viable embryos. The objective of this retrospective study was to identify the morphokinetic parameters specific to embryos that were capable of implanting. In order to compare a large number of embryos, with minimal variation in culture conditions, we have used an automatic embryo monitoring system. methods: Using a tri-gas IVF incubator with a built-in camera designed to automatically acquire images at defined time points, we have simultaneously monitored up to 72 individual embryos without removing the embryos from the controlled environment. Images were acquired every 15 min in five different focal planes for at least 64 h for each embryo. We have monitored the development of transferred embryos from 285 couples undergoing their first ICSI cycle. The total number of transferred embryos was 522, of which 247 either failed to implant or fully implanted, with full implantation meaning that all transferred embryos in a treatment implanted. results: A detailed retrospective analysis of cleavage times, blastomere size and multinucleation was made for the 247 transferred embryos with either failed or full implantation. We found that several parameters were significantly correlated with subsequent implantation (e.g. time of first and subsequent cleavages as well as the time between cleavages). The most predictive parameters were: (i) time of division to 5 cells, t5 (48.8–56.6 h after ICSI); (ii) time between division to 3 cells and subsequent division to 4 cells, s2 (≤0.76 h) and (iii) duration of cell cycle two, i.e. time between division to 2 cells and division to 3 cells, cc2 (≤11.9 h). We also observed aberrant behavior such as multinucleation at the 4 cell stage, uneven blastomere size at the 2 cell stage and abrupt cell division to three or more cells, which appeared to largely preclude implantation. conclusions: The image acquisition and time-lapse analysis system makes it possible to determine exact timing of embryo cleavages in a clinical setting. We propose a multivariable model based on our findings to classify embryos according to their probability of implantation. The efficacy of this classification will be evaluated in a prospective randomized study that ultimately will determine if implantation rates can be improved by time-lapse analysis.

738 citations

Journal ArticleDOI
TL;DR: It is found that success in progression to the blastocyst stage can be predicted with >93% sensitivity and specificity by measuring three dynamic, noninvasive imaging parameters by day 2 after fertilization, before embryonic genome activation (EGA).
Abstract: We report studies of preimplantation human embryo development that correlate time-lapse image analysis and gene expression profiling. By examining a large set of zygotes from in vitro fertilization (IVF), we find that success in progression to the blastocyst stage can be predicted with >93% sensitivity and specificity by measuring three dynamic, noninvasive imaging parameters by day 2 after fertilization, before embryonic genome activation (EGA). These parameters can be reliably monitored by automated image analysis, confirming that successful development follows a set of carefully orchestrated and predictable events. Moreover, we show that imaging phenotypes reflect molecular programs of the embryo and of individual blastomeres. Single-cell gene expression analysis reveals that blastomeres develop cell autonomously, with some cells advancing to EGA and others arresting. These studies indicate that success and failure in human embryo development is largely determined before EGA. Our methods and algorithms may provide an approach for early diagnosis of embryo potential in assisted reproduction.

714 citations

Journal ArticleDOI
TL;DR: Time-lapse video cinematography is shown to be an excellent tool for studying fertilization and early embryo development, and it was found that good quality embryos arose from oocytes that had more uniform timing from injection to pronuclear abuttal and tended to have a longer cytoplasmic wave.
Abstract: In this study, we have used time-lapse video cinematography to study fertilization in 50 human oocytes that had undergone intracytoplasmic sperm injection (ICSI). Time-lapse recording commenced shortly after ICSI and proceeded for 17-20 h. Oocytes were cultured in an environmental chamber which was maintained under standard culture conditions. Overall, 38 oocytes (76%) were fertilized normally, and the fertilization rate and embryo quality were not significantly different from 487 sibling oocytes cultured in a conventional incubator. Normal fertilization followed a defined course of events, although the timing of these events varied markedly between oocytes. In 35 of the 38 fertilized oocytes (92%), there were circular waves of granulation within the ooplasm which had a periodicity of 20-53 min. The sperm head decondensed during this granulation phase. The second polar body was then extruded, and this was followed by the central formation of the male pronucleus. The female pronucleus formed in the cytoplasm adjacent to the second polar body at the same time as, or slightly after, the male pronucleus, and was subsequently drawn towards the male pronucleus until the two abutted. Both pronuclei then increased in size, the nucleoli moved around within the pronuclei and some nucleoli coalesced. During pronuclear growth, the organelles contracted from the cortex towards the centre of the oocyte, leaving a clear cortical zone. The oocyte decreased in diameter from 112 to 106 microm (P < 0.0001) during the course of the observation period. The female pronucleus was significantly smaller in diameter than the male pronucleus (24.1 and 22.4 microm respectively, P = 0.008) and contained fewer nucleoli (4.2 and 7.0 respectively, P < 0.0001). After time-lapse recording, oocytes were cultured for 48 h prior to embryo transfer or cryopreservation. Embryo quality was related to fertilization events and periodicity of the cytoplasmic wave, and it was found that good quality embryos arose from oocytes that had more uniform timing from injection to pronuclear abuttal and tended to have a longer cytoplasmic wave. In conclusion, we have shown that time-lapse video cinematography is an excellent tool for studying fertilization and early embryo development, and have demonstrated that human fertilization comprises numerous complex dynamic events.

398 citations

Journal ArticleDOI
TL;DR: The need for investigation of two major questions is highlighted: large-scale case-control studies of ART outcomes, including long-term assessment of the incidence of birth defects and cancer, and investigation of the relationship between epigenetic errors in both offspring and parents.
Abstract: A surprising set of recent observations suggests a link between assisted reproductive technology (ART) and epigenetic errors—that is, errors involving information other than DNA sequence that is heritable during cell division. An apparent association with ART was found in registries of children with Beckwith-Wiedemann syndrome, Angelman syndrome, and retinoblastoma. Here, we review the epidemiology and molecular biology behind these studies and those of relevant model systems, and we highlight the need for investigation of two major questions: (1) large-scale case-control studies of ART outcomes, including long-term assessment of the incidence of birth defects and cancer, and (2) investigation of the relationship between epigenetic errors in both offspring and parents, the specific methods of ART used, and the underlying infertility diagnoses. In addition, the components of proprietary commercial media used in ART procedures must be fully and publicly disclosed, so that factors such as methionine content can be assessed, given the relationship in animal studies between methionine exposure and epigenetic changes.

309 citations