Artificial Intelligence Is Useful for Embryo Selection in IVF

Lay summary The success of IVF has remained stagnant for a decade. The focus of a great deal of research is to improve on the current ~30% success rate of IVF. Artificial intelligence (AI), or machines that mimic human intelligence, has been gaining traction for its potential to improve outcomes in medicine, such as cancer diagnosis from medical images. In this commentary, we discuss whether AI has the potential to improve fertility outcomes in the IVF clinic. Based on existing research, we examine the potential of adopting AI within multiple facets of an IVF cycle, including egg/sperm and embryo selection, as well as formulation of an IVF treatment regimen. We discuss both the potential benefits and concerns of the patient and clinician in adopting AI in the clinic. We outline hurdles that need to be overcome prior to implementation. We conclude that AI has an important future in improving IVF success.

Download Full-text

Embryo selection with artificial intelligence: how to evaluate and compare methods?

Journal of Assisted Reproduction and Genetics ◽

10.1007/s10815-021-02254-6 ◽

2021 ◽

Author(s):

Mikkel Fly Kragh ◽

Henrik Karstoft

Keyword(s):

Artificial Intelligence ◽

Performance Metrics ◽

Selection Procedure ◽

Relevant Information ◽

Embryo Selection ◽

Vitro Fertilization ◽

Ranking Performance ◽

Retrospective Cohort Studies ◽

Microscopy Images

AbstractEmbryo selection within in vitro fertilization (IVF) is the process of evaluating qualities of fertilized oocytes (embryos) and selecting the best embryo(s) available within a patient cohort for subsequent transfer or cryopreservation. In recent years, artificial intelligence (AI) has been used extensively to improve and automate the embryo ranking and selection procedure by extracting relevant information from embryo microscopy images. The AI models are evaluated based on their ability to identify the embryo(s) with the highest chance(s) of achieving a successful pregnancy. Whether such evaluations should be based on ranking performance or pregnancy prediction, however, seems to divide studies. As such, a variety of performance metrics are reported, and comparisons between studies are often made on different outcomes and data foundations. Moreover, superiority of AI methods over manual human evaluation is often claimed based on retrospective data, without any mentions of potential bias. In this paper, we provide a technical view on some of the major topics that divide how current AI models are trained, evaluated and compared. We explain and discuss the most common evaluation metrics and relate them to the two separate evaluation objectives, ranking and prediction. We also discuss when and how to compare AI models across studies and explain in detail how a selection bias is inevitable when comparing AI models against current embryo selection practice in retrospective cohort studies.

Download Full-text

P–141 Artificial intelligence system for the automation of the blastocyst morphology evaluation in GERI Time-lapse Incubator

Human Reproduction ◽

10.1093/humrep/deab130.140 ◽

2021 ◽

Vol 36 (Supplement_1) ◽

Author(s):

E Pay. Bosch ◽

L Bori ◽

A Beltran ◽

V Naranjo ◽

M Meseguer

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Evaluation Process ◽

Time Lapse ◽

Embryo Selection ◽

Learning Approach ◽

Initial Attempt ◽

High Quality ◽

Blind Test ◽

Medium Quality

Abstract Study question Can an Artificial Intelligence (AI) system (hand-crafted vs. deep learning techniques) based on single embryo image analysis from a GERI time-lapse incubator (TL) evaluate the blastocyst morphology? Summary answer Our hand-crafted method trained with blastocyst images from Geri-TL evaluated and classified parameters regarding to embryo quality with a global precision of 63.7% in blind-test. What is known already Recent studies have shown that AI can improve automatic grading and embryo selection. The approaches that have been carried out are very different, but all they conclude that there is a great potential (Rad2019, Manoj2020, Thirumalaraju2020). As we know, conventional embryo evaluation is performed manually based on the morphology of the blastocyst, therefore, it should be possible to replicate this process. In this study, we implemented different methods to analyse the behaviour and performance of an AI doing embryology tasks. Study design, size, duration Our study consisted of a retrospective analysis for the automatization of embryo evaluation with different approaches. We developed our models based on 715 images extracted from GERI TL Videos (Genea, Australia) from a single IVF center. Database was divided into 3 classes depending on the quality of the embryo according to ASEBIR morphology criteria (high; medium and low-quality). All the images were divided into 70% for training, 15% for validating and 15% for testing. Participants/materials, setting, methods We developed an automated AI algorithm to extract and classify features from images at 111,5 hpi of embryos cultured in GERI TL. Hand-crafted features from texture information are extracted to feed the classification algorithm. A statistical analysis is carried out to select the more discriminative variables. Parallelly, a deep neural network was built to compare performance of automatic and hand-crafted features. Additionally, we trained a model to detect embryo in the well. Main results and the role of chance High-quality, medium-quality and low-quality sensitivity were 73%, 56% and 72% for hand-crafted method and 76%, 53% and 22% for deep learning approach, respectively. High-quality, medium-quality and low-quality precision were 66%, 56% and 76% for hand-crafted method and 40%, 60% and 55% for deep learning approach, respectively. The global accuracy associated with each method was 64% and 50%. Also, we noticed that results were higher when we applied our embryo masks that avoid irrelevant information. In this initial attempt, our results showed that it is possible to replicate the embryo evaluation process. Limitations, reasons for caution The low results obtained in our deep learning model due to the absence of an extent dataset did not allow to obtain a model applicable to the clinic. However, the preliminary study let us to conclude the high potential of the approach. Wider implications of the findings: Our results showed a potential automatization of the embryo evaluation process in Geri TL where the available software for embryo selection does not provide such option. Our findings leaded to an increase in objectification, a reduction of the workload of the embryologist and the research of new unknown morphological variables. Trial registration number Not applicable

Download Full-text

O-088 Performance of a commercial artificial intelligence software for embryo selection (Embryoscope/KIDScore™) on predicting biopsied and non-biopsied blastocyst clinical pregnancy according to score subgroups

Human Reproduction ◽

10.1093/humrep/deab125.018 ◽

2021 ◽

Vol 36 (Supplement_1) ◽

Author(s):

R Erberelli ◽

C K Jacobs ◽

M Nicolielo ◽

E L Motta ◽

J R Alegretti ◽

...

Keyword(s):

Artificial Intelligence ◽

Maternal Age ◽

Time Lapse ◽

Clinical Pregnancy ◽

Embryo Selection ◽

Chi Square ◽

Biochemical Pregnancy ◽

Registration Number ◽

Gestational Sac ◽

N 93

Abstract Study question How informative is the score grade of KIDScore version 3 for day 5 blastocyst for clinical pregnancy in biopsied and non-biopsied embryos? Summary answer Potential clinical pregnancy is predicable according to score grades (above 7.0), regardless the use of PGT-A, in blastocysts on day 5. What is known already Time-lapse technology has promoted, along with the use of artificial intelligence (A.I.), a new spectrum of tools to improve embryo selection. Several software and algorithms have been launched in ART field in the last years, with the perspective of providing a substantial boost in IVF outcomes. KIDScore is one of these new tools, developed based on morphology and morphokinetics of embryo development with known clinical outcome and validated with transfer of blastocyst on day 3 or 5. Yet, it is highly recommended an in-house validation of any A.I. tool before it started to be apply in clinical decisions. Study design, size, duration Retrospective cohort study in a single private IVF center. Positive or negative clinical pregnancy (fetal heartbeat and gestational sac presence/absence) record of patient’s autologous and donated cycles using fresh and frozen oocytes, with or without PGT-A embryos transfers using the Embryocope® Plus incubator, that underwent single embryo transfers (total sET, n = 415; euploid = 228, non-biopsied = 187) of blastocysts developed on day 5 were included. Biochemical pregnancy and miscarriage were excluded of this analysis. Participants/materials, setting, methods Negative and positive clinical pregnancy KIDScoreTMDay 5’s were stratified in three subgroups, according to V3 score intervals: subgroup 1: range between 1.0-3.9 (n = 29), subgroup 2: 4.0-6.9 (n = 154) and subgroup 3: 7.0-9.9 (n = 232). sET of euploid embryos (n = 228) were also analyzed in the described subgroups (subgroup 1: n = 17; subgroup 2: n = 93 and subgroup 3: n = 118, respectively). For the analysis, Mann-Whitney, Chi-square and Fisher tests were used for statistical analysis, values of p < 0.05 were considered significant. Main results and the role of chance Maternal age between overall positive and negative pregnancies were similar (38,48±3,86 versus 38,75±3,83,p = 0,3573). When comparing score subgroups, overall positive clinical pregnancy rates were significant different [subgroup 1: 20.7% (6/29); subgroup 2: 43.5% (67/154); subgroup 3: 63.8% (148/232),p < 0.0001]. When analyzing subgroup 1 versus subgroup 2 there was also a difference in positive clinical pregnancy (p = 0.023) and subgroup 3 also showed a higher rate in clinical pregnancy when compared to subgroup 1 and 2 together (scores from 1.0 to 6.9,p < 0.0001). Analyzing only euploid embryos, the results on positive clinical pregnancy were also significant different between subgroups [subgroup 1: 35.3% (6/17); subgroup 2: 45.2% (42/93); subgroup 3: 61.0% (72/118),p = 0,024, and subgroup 1 + 2 versus subgroup 3,p = 0,0115]. Maternal age between positive and negative clinical pregnancies in PGT-A cycles were similar (37,81±1,61 versus 38,38±3,25,p = 0,069). Analyzing only non-biopsied embryos, the results on positive clinical pregnancy were also significant different between subgroups [subgroup 1: 0.0% (0/12); subgroup 2: 41.0% (25/61); subgroup 3: 66.7% (76/114),p = 0,0343, and subgroup 1 + 2 versus subgroup 3,p < 0.0001]. Maternal age between positive and negative clinical pregnancies in non-biopsied cycles were also similar (39,40±4,75 versus 39,22±4,43,p = 0,7816). Positive clinical pregnancy in subgroup 3 were similar in biopsied and non-biopsied subgroups (61% versus 66.7%,p = 0.4133). Limitations, reasons for caution The retrospective nature and low data of subgroup 1 (1.0-3.9 score), since they naturally are the last option to be chosen for transfer. Wider implications of the findings Differences on positive clinical pregnancy between subgroups (mainly scores greater than 7.0) reinforce the use of A.I. as a complementary tool for embryo selection. Interestingly, positive clinical pregnancy in 7.0-9.9 subgroup were similar in euploid and non-biopsied embryos, strengthening another potential application of A.I. in transposing embryo aneuploidy barrier. Trial registration number Not Applicable

Download Full-text

NOVEL ARTIFICIAL INTELLIGENCE ALGORITHM FOR IMPROVING EMBRYO SELECTION COMBINING MORPHOKINETICS AND NON-INVASIVE MEASUREMENT OF OXIDATIVE STRESS

Fertility and Sterility ◽

10.1016/j.fertnstert.2020.08.415 ◽

2020 ◽

Vol 114 (3) ◽

pp. e140-e141

Author(s):

María de los Ángeles Valera ◽

José Celso Rocha ◽

Lorena Bori ◽

Lucia Alegre ◽

Marcelo Fábio Gouveia Nogueira ◽

...

Keyword(s):

Oxidative Stress ◽

Artificial Intelligence ◽

Embryo Selection ◽

Selection Combining ◽

Non Invasive ◽

Intelligence Algorithm ◽

Artificial Intelligence Algorithm ◽

Invasive Measurement

Download Full-text

O-098 Embryo selection using Artificial Intelligence (AI): Epistemic and ethical considerations

Human Reproduction ◽

10.1093/humrep/deab125.034 ◽

2021 ◽

Vol 36 (Supplement_1) ◽

Author(s):

M Afnan ◽

Y Liu ◽

V Conitzer ◽

C Rudin ◽

A Mishra ◽

...

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Ethical Issues ◽

Clinical Effectiveness ◽

Black Box ◽

Embryo Selection ◽

Societal Implications ◽

Ethical Considerations ◽

Box Models ◽

Black Box Models

Abstract Study question What are the epistemic and ethical considerations of clinically implementing Artificial Intelligence (AI) algorithms in embryo selection? Summary answer AI embryo selection algorithms used to date are “black-box” models with significant epistemic and ethical issues, and there are no trials assessing their clinical effectiveness. What is known already The innovation of time-lapse imaging offers the potential to generate vast quantities of data for embryo assessment. Computer Vision allows image data to be analysed using algorithms developed via machine learning which learn and adapt as they are exposed to more data. Most algorithms are developed using neural networks and are uninterpretable (or “black box”). Uninterpretable models are either too complicated to understand or proprietary, in which case comprehension is impossible for outsiders. In the IVF context, these outsiders include doctors, embryologists and patients, which raises ethical questions for its use in embryo selection. Study design, size, duration We performed a scoping review of articles evaluating AI for embryo selection in IVF. We considered the epistemic and ethical implications of current approaches. Participants/materials, setting, methods We searched Medline, Embase, ClinicalTrials.gov and the EU Clinical Trials Register for full text papers evaluating AI for embryo selection using the following key words: artificial intelligence* OR AI OR neural network* OR machine learning OR support vector machine OR automatic classification AND IVF OR in vitro fertilisation OR embryo*, as well as relevant MeSH and Emtree terms for Medline and Embase respectively. Main results and the role of chance We found no trials evaluating clinical effectiveness either published or registered. We found efficacy studies which looked at 2 types of outcomes – accuracy for predicting pregnancy or live birth and agreement with embryologist evaluation. Some algorithms were shown to broadly differentiate well between “good-” and “poor-” quality embryos but not between embryos of similar quality, which is the clinical need. Almost universally, the AI models were opaque (“black box”) in that at least some part of the process was uninterpretable. “Black box” models are problematic for epistemic and ethical reasons. Epistemic concerns include information asymmetries between algorithm developers and doctors, embryologists and patients; the risk of biased prediction caused by known and/or unknown confounders during the training process; difficulties in real-time error checking due to limited interpretability; the economics of buying into commercial proprietary models, brittle to variation in the treatment process; and an overall difficulty troubleshooting. Ethical pitfalls include the risk of misrepresenting patient values; concern for the health and well-being of future children; the risk of disvaluing disability; possible societal implications; and a responsibility gap, in the event of adverse events. Limitations, reasons for caution Our search was limited to the two main medical research databases. Although we checked article references for more publications, we were less likely to identify studies that were not indexed in Medline or Embase, especially if they were not cited in studies identified in our search. Wider implications of the findings It is premature to implement AI for embryo selection outside of a clinical trial. AI for embryo selection is potentially useful, but must be done carefully and transparently, as the epistemic and ethical issues are significant. We advocate for the use of interpretable AI models to overcome these issues. Trial registration number not applicable

Download Full-text