Use of artificial intelligence embryo selection based on static images to predict first-trimester pregnancy loss.

RESEARCH QUESTION: Can an artificial intelligence embryo selection assistant predict the incidence of first-trimester spontaneous abortion using static images of IVF embryos? DESIGN: In a blind, retrospective study, a cohort of 172 blastocysts from IVF cases with single embryo transfer and a positive biochemical pregnancy test was ranked retrospectively by the artificial intelligence morphometric algorithm ERICA. Making use of static embryo images from a light microscope, each blastocyst was assigned to one of four possible groups (optimal, good, fair or poor), and linear regression was used to correlate the results with the presence or absence of a normal fetal heart beat as an indicator of ongoing pregnancy or spontaneous abortion, respectively. Additional analyses included modelling for recipient age and chromosomal status established by preimplantation genetic testing for aneuploidy (PGT-A). RESULTS: Embryos classified as optimal/good had a lower incidence of spontaneous abortion (16.1%) compared with embryos classified as fair/poor (25%; OR = 0.46, P = 0.005). The incidence of spontaneous abortion in chromosomally normal embryos (determined by PGT-A) was 13.3% for optimal/good embryos and 20.0% for fair/poor embryos, although the difference was not significant (P = 0.531). There was a significant association between embryo rank and recipient age (P = 0.018), in that the incidence of spontaneous abortion was unexpectedly lower in older recipients (21.3% for age ≤35 years, 17.9% for age 36-38 years, 16.4% for age ≥39 years; OR = 0.354, P = 0.0181). Overall, these results support correlation between risk of spontaneous abortion and embryo rank as determined by artificial intelligence; classification accuracy was calculated to be 67.4%. CONCLUSIONS: This preliminary study suggests that artificial intelligence (ERICA), which was designed as a ranking system to assist with embryo transfer decisions and ploidy prediction, may also be useful to provide information for couples on the risk of spontaneous abortion. Future work will include a larger sample size and karyotyping of miscarried pregnancy tissue.

New frontiers in embryo selection.

Human infertility is a major global public health issue estimated to affect one out of six couples, while the number of assisted reproduction cycles grows impressively year over year. Efforts to alleviate infertility using advanced technology are gaining traction rapidly as infertility has an enormous impact on couples and the potential to destabilize entire societies if replacement birthrates are not achieved. Artificial intelligence (AI) technologies, leveraged by the highly advanced assisted reproductive technology (ART) industry, are a promising addition to the armamentarium of tools available to combat global infertility. This review provides a background for current methodologies in embryo selection, which is a manual, time-consuming, and poorly reproducible task. AI has the potential to improve this process (among many others) in both the clinician's office and the IVF laboratory. Embryo selection is evolving through digital methodologies into an automated procedure, with superior reliability and reproducibility, that is likely to result in higher pregnancy rates for patients. There is an emerging body of data demonstrating the utility of AI applications in multiple areas in the IVF laboratory. AI platforms have been developed to evaluate individual embryologist performance; to provide quality assurance for culture systems; to correlate embryologist's assessments and AI systems; to predict embryo ploidy, implantation, fetal heartbeat, and live birth outcome; and to replace the current "analogue" system of embryo selection with a digital paradigm. AI capability will distinguish high performing, high profit margin, low-cost, and highly successful IVF clinic business models. We think it will become the standard, "new normal" in IVF labs, as rapidly and thoroughly as vitrification, blastocyst culture, and intracytoplasmic sperm injection replaced their predecessor technologies. At the time of this review, the AI technology to automate embryo evaluation and selection has robustly matured, and therefore, it is the main focus of this review.

Automated identification of blastocyst regions at different development stages.

The selection of the best single blastocyst for transfer is typically based on the assessment of the morphological characteristics of the zona pellucida (ZP), trophectoderm (TE), blastocoel (BC), and inner cell-mass (ICM), using subjective and observer-dependent grading protocols. We propose the first automatic method for segmenting all morphological structures during the different developmental stages of the blastocyst (i.e., expansion, hatching, and hatched). Our database contains 592 original raw images that were augmented to 2132 for training and 55 for validation. The mean Dice similarity coefficient (DSC) was 0.87 for all pixels, and for the BC, BG (background), ICM, TE, and ZP was 0.85, 0.96, 0.54, 0.63, and 0.71, respectively. Additionally, we tested our method against a public repository of 249 images resulting in accuracies of 0.96 and 0.93 and DSC of 0.67 and 0.67 for ICM and TE, respectively. A sensitivity analysis demonstrated that our method is robust, especially for the BC, BG, TE, and ZP. It is concluded that our approach can automatically segment blastocysts from different laboratory settings and developmental phases of the blastocysts, all within a single pipeline. This approach could increase the knowledge base for embryo selection.

Automation in ART: Paving the Way for the Future of Infertility Treatment.

In vitro fertilisation (IVF) is estimated to account for the birth of more than nine million babies worldwide, perhaps making it one of the most intriguing as well as commoditised and industrialised modern medical interventions. Nevertheless, most IVF procedures are currently limited by accessibility, affordability and most importantly multistep, labour-intensive, technically challenging processes undertaken by skilled professionals. Therefore, in order to sustain the exponential demand for IVF on one hand, and streamline existing processes on the other, innovation is essential. This may not only effectively manage clinical time but also reduce cost, thereby increasing accessibility, affordability and efficiency. Recent years have seen a diverse range of technologies, some integrated with artificial intelligence, throughout the IVF pathway, which promise personalisation and, at least, partial automation in the not-so-distant future. This review aims to summarise the rapidly evolving state of these innovations in automation, with or without the integration of artificial intelligence, encompassing the patient treatment pathway, gamete/embryo selection, endometrial evaluation and cryopreservation of gametes/embryos. Additionally, it shall highlight the resulting prospective change in the role of IVF professionals and challenges of implementation of some of these technologies, thereby aiming to motivate continued research in this field.

Computer software (SiD) assisted real-time single sperm selection associated with fertilization and blastocyst formation.

RESEARCH QUESTION: Is it possible to explore an association between individual sperm kinematics evaluated in real time and spermatozoa selected by an embryologist for intracytoplasmic sperm injection (ICSI), with subsequent normal fertilization and blastocyst formation using a novel artificial vision-based software (SiD V1.0; IVF 2.0, UK)? DESIGN: ICSI procedures were randomly video recorded and subjected to analysis using SiD V1.0, proprietary software developed by our group. In total, 383 individual spermatozoa were retrospectively analysed from a dataset of 78 ICSI-assisted reproductive technology cycles. SiD software computes the progressive motility parameters, straight-line velocity (VSL) and linearity of the curvilinear path (LIN), of each sperm trajectory, along with a quantitative value, head movement pattern (HMP), which is an indicator of the characteristics of the sperm head movement patterns. The mean VSL, LIN and HMP measurements for each set of spermatozoa were compared based on different outcome measures. RESULTS: Statistically significant differences were found in VSL, LIN and HMP among those spermatozoa selected for injection (P < 0.001). Additionally, LIN and HMP were found to be significantly different between successful and unsuccessful fertilization (P = 0.038 and P = 0.029, respectively). Additionally, significantly higher SiD scores were found for those spermatozoa that achieved both successful fertilization (P = 0.004) and blastocyst formation (P = 0.013). CONCLUSION: The possibility of carrying out real-time analyses of individual spermatozoa using an automatic tool such as SiD creates the opportunity to assist the embryologist in selecting the better spermatozoon for injection in an ICSI procedure.

Evaluating predictive models in reproductive medicine.

Predictive modeling has become a distinct subdiscipline of reproductive medicine, and researchers and clinicians are just learning the skills and expertise to evaluate artificial intelligence (AI) studies. Diagnostic tests and model predictions are subject to evaluation. Their use offers potential for both harm and benefit in terms of diagnosis, treatment, and prognosis. The performance of AI models and their potential clinical utility hinge on the quality and size of the databases used, the types and distribution of data, and the particular AI method applied. Additionally, when images are involved, the method of capturing, preprocessing, and treatment and accurate labeling of images becomes an important component of AI modeling. Inconsistent image treatment or inaccurate labeling of images can lead to an inconsistent database, resulting in poor AI accuracy. We discuss the critical appraisal of AI models in reproductive medicine and convey the importance of transparency and standardization in reporting AI models so that the risk of bias and the potential clinical utility of AI can be assessed.

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

Artificial intelligence (AI) systems have been proposed for reproductive medicine since 1997. Although AI is the main driver of emergent technologies in reproduction, such as robotics, Big Data, and internet of things, it will continue to be the engine for technological innovation for the foreseeable future. What does the future of AI research look like?

Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation.

RESEARCH QUESTION: Can a deep machine learning artificial intelligence algorithm predict ploidy and implantation in a known data set of static blastocyst images, and how does its performance compare against chance and experienced embryologists? DESIGN: A database of blastocyst images with known outcome was applied with an algorithm dubbed ERICA (Embryo Ranking Intelligent Classification Algorithm). It was evaluated against its ability to predict euploidy, compare ploidy prediction against randomly assigned prognosis labels and against senior embryologists, and if it could rank an euploid embryo highly. RESULTS: A total of 1231 embryo images were classed as good prognosis if euploid and implanted or poor prognosis if aneuploid and failed to implant. An accuracy of 0.70 was obtained with ERICA, with positive predictive value of 0.79 for predicting euploidy. ERICA had greater normalized discontinued cumulative gain (ranking metric) than random selection (P = 0.0007), and both embryologists (P = 0.0014 and 0.0242, respectively). ERICA ranked an euploid blastocyst first in 78.9% and at least one euploid embryo within the top two blastocysts in 94.7% of cases, better than random classification and the two senior embryologists. Average embryo ranking time for four blastocysts was under 25 s. CONCLUSION: Artificial intelligence lends itself well to image pattern recognition. We have trained ERICA to rank embryos based on ploidy and implantation potential using single static embryo image. This tool represents a potentially significant advantage to assist embryologists to choose the best embryo, saving time spent annotating and does not require time lapse or invasive biopsy. Future work should be directed to evaluate reproducibility in different data sets.

Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning.

Assessing the viability of a blastosyst is still empirical and non-reproducible nowadays. We developed an algorithm based on artificial vision and machine learning (and other classifiers) that predicts pregnancy using the beta human chorionic gonadotropin (b-hCG) test from both the morphology of an embryo and the age of the patients. We employed two high-quality databases with known pregnancy outcomes (n = 221). We created a system consisting of different classifiers that is feed with novel morphometric features extracted from the digital micrographs, along with other non-morphometric data to predict pregnancy. It was evaluated using five different classifiers: probabilistic bayesian, Support Vector Machines (SVM), deep neural network, decision tree, and Random Forest (RF), using a k-fold cross validation to assess the model's generalization capabilities. In the database A, the SVM classifier achieved an F1 score of 0.74, and AUC of 0.77. In the database B the RF classifier obtained a F1 score of 0.71, and AUC of 0.75. Our results suggest that the system is able to predict a positive pregnancy test from a single digital image, offering a novel approach with the advantages of using a small database, being highly adaptable to different laboratory settings, and easy integration into clinical practice.

Estrategia combinada en fertilización in vitro: mínima estimulación y transferencia de embrión único con diagnóstico genético. Experiencia de 3 años en dos centros de reproducción en México / A combined in-vitro fertilization strategy: minimal stimulation IVF, PGT-A and SET. Results from 3 years' experience at two IVF centers in Mexico

Resumen OBJETIVO: Evaluar los desenlaces de una estrategia combinada para fertilización in vitro: mínima estimulación ovárica, diagnóstico genético preimplantación para aneuploidias y transferencia de un solo embrión. MATERIALES Y MÉTODOS: Estudio de cohorte, retrospectivo, efectuado en dos centros de reproducción de México, en un periodo de tres años. Se incluyeron pacientes entre 25 y 45 años, en protocolo de fertilización in vitro, con mínima estimulación, diagnóstico genético preimplantación para aneuploidias (PGT-A) y transferencia de embrión único. El diagnóstico genético preimplantación se estableció mediante microarreglos y secuenciación de nueva generación (NGS). Para el análisis estadístico se integraron 5 grupos, según la edad de las pacientes: menores de 35 años; 35 a 37 años; 38 a 40 años; 41 a 42 años; y mayores de 42 años. Mediante estadística descriptiva se analizaron las variables numéricas y categóricas. RESULTADOS: Se analizaron 175 ciclos, en 125 pacientes (edad promedio: 39 años ± 5). Se obtuvieron, en promedio, 5 óvulos por ciclo. La tasa de fertilización fue de 86.5% y la de blastocisto por óvulo fertilizado de 50.7%. Se tomó biopsia para diagnóstico genético preimplantación para aneuploidias a 404 embriones. La tasa general de euploidia fue de 33%. Se efectuaron 69 transferencias de embrión único, con una tasa de embarazo por transferencia de 71%. La tasa de nacimiento por transferencia fue de 60.8% (42 nacimientos). CONCLUSIONES: La combinación de mínima estimulación, diagnóstico genético preimplantación para aneuploidias y transferencia de embrión único, es un procedimiento adecuado para alcanzar una tasa de nacimiento alta.

Abstract OBJECTIVE: To evaluate results of a combined approach in IVF, using minimal stimulation, preimplantation genetic testing for aneuploidy, and single blastocyst transfer. MATERIALS AND METHODS: Retrospective cohort study over a three years' period in two fertility centers in Mexico. A total of 125 patients were included, between 25 and 45 years old, with minimal stimulation IVF, preimplantation genetic testing for aneuploidy (PGT-A) and single euploid embryo transfer. PGT was performed using microarrays and next generation sequencing (NGS). RESULTS: A total of 175 cycles (mean age: 39 years old) were analyzed in 125 patients. On average, five eggs were collected per cycle; fertilization rate was 86.57%; blastocyst rate was 50.7% per fertilized egg. Only 33% of embryos were euploid. Pregnancy rate per transferred embryo was 71%. Live birth rate was 60.8% (42 births). CONCLUSIONS: A combination of minimal stimulation, PGT-A and single blastocyst embryo transfer can yield a high live birth rate.

Sorter de citometría de flujo: repercusiones en los indicadores clave de rendimiento de un laboratorio de reproducción asistida / Flow cytometry sorter: results in the key performance indicators of an assisted reproductive technology

Resumen OBJETIVO: Evaluar si la manipulación de gametos con sorter de citometría de flujo repercute negativamente en los indicadores clave de rendimiento de un laboratorio de reproducción asistida. MATERIALES Y MÉTODOS: Estudio descriptivo y retrospectivo, llevado a cabo en parejas a quienes se efectuó fecundación in vitro mediante inyección intracitoplasmática de espermatozoides (ICSI), con selección espermática, mediante un sorter de citometría de flujo, para selección de sexo. El estudio se efectuó en el New Hope Fertility Center de Guadalajara y Ciudad de México, de junio de 2014 a agosto de 2017. Los resultados se compararon con un grupo control seleccionado al azar. Se evaluaron los indicadores decisivos de rendimiento (KPI´s); tasa de fecundación normal, anormal (1PN, ≥ 3 PN) y fallida; tasa de degeneración posterior a ICSI; tasas de segmentación o división, blastocisto, implantación (segmentación y blastocisto) y recién nacido. Se utilizó la prueba t de Student para dos muestras y se consideró estadísticamente significativo el valor de p < 0.05. RESULTADOS: Se evaluaron 150 ciclos. Grupo 1: ICSI con selección espermática y sorter de citometría de flujo (n = 40); Grupo 2: ICSI sin sorter de citometría de flujo (n = 110). Los indicadores clave de rendimiento del grupo 1 disminuyeron; se reportaron tasas de fecundación fallida de 1.6%, blastocisto 17.4%, implantación en la segmentación 10%, implantación en blastocisto 14.2% y de recién nacido 14.5%. CONCLUSIONES: La manipulación de gametos con sorter de citometría de flujo reportó un efecto negativo en los indicadores clave de rendimiento del laboratorio de reproducción asistida, específicamente en las tasas de blastocisto, implantación de blastocisto y de recién nacido.

Abstract OBJECTIVE: To evaluate if the manipulation of gametes with a flow cytometry sorter has a negative effect on the key performance indicators (KPI´s). MATERIALS AND METHOD: Descriptive and retrospective analysis, in couples undergoing In a Vitro Fertilization (IVF) by ICSI, with sperm selection, using a flow cytometry sorter for sex selection. The study was conducted at the New Hope Fertility Center in Guadalajara and Mexico City, from June 2014 to August 2017. The results were compared with a randomly group without a flow cytometry sorter. KPI´s were evaluated; normal fertilization rate, abnormal (1PN, ≥3 PN), failed fertilization, ICSI damage rate, cleavage rate, blastocyst development rate, implantation rate (cleavage and blastocyst-stage) and live birth rate. A Student's t-test was made for two samples considering significant differences with p < 0.05. RESULTS: 150 cycles were evaluated. Group 1: ICSI with sperm selection by a flow cytometry sorter (n = 40); Group 2: ICSI without sperm selection (n = 110). Observing with statistical significance a decreased of the KPI´s of Group 1: failed fertilization rate (1.6%), blastocyst development rate (17.4%), implantation rate (cleavage-stage) (10%), implantation rate (blastocyst-stage) (14.2%) and live birth rate (14.5%). CONCLUSIONS: The manipulation of gametes with the flow cytometry sorter, has a negative effect on the assisted reproductive technology KPI´s; specifically, in the blastocyst rate, blastocyst implantation rate and live birth rate.

Live birth derived from oocyte spindle transfer to prevent mitochondrial disease.

Mutations in mitochondrial DNA (mtDNA) are maternally inherited and can cause fatal or debilitating mitochondrial disorders. The severity of clinical symptoms is often associated with the level of mtDNA mutation load or degree of heteroplasmy. Current clinical options to prevent transmission of mtDNA mutations to offspring are limited. Experimental spindle transfer in metaphase II oocytes, also called mitochondrial replacement therapy, is a novel technology for preventing mtDNA transmission from oocytes to pre-implantation embryos. Here, we report a female carrier of Leigh syndrome (mtDNA mutation 8993T > G), with a long history of multiple undiagnosed pregnancy losses and deaths of offspring as a result of this disease, who underwent IVF after reconstitution of her oocytes by spindle transfer into the cytoplasm of enucleated donor oocytes. A male euploid blastocyst wasobtained from the reconstituted oocytes, which had only a 5.7% mtDNA mutation load. Transfer of the embryo resulted in a pregnancy with delivery of a boy with neonatal mtDNA mutation load of 2.36-9.23% in his tested tissues. The boy is currently healthy at 7 months of age, although long-term follow-up of the child's longitudinal development remains crucial.

Minimal stimulation IVF vs conventional IVF: a randomized controlled trial.

BACKGROUND: Minimal stimulation in vitro fertilization (mini-in vitro fertilization) is an alternative in vitro fertilization treatment protocol that may reduce ovarian hyperstimulation syndrome, multiple pregnancy rates, and cost while retaining high live birth rates. OBJECTIVE: We performed a randomized noninferiority controlled trial with a prespecified border of 10% that compared 1 cycle of mini-in vitro fertilization with single embryo transfer with 1 cycle of conventional in vitro fertilization with double embryo transfer. STUDY DESIGN: Five hundred sixty-four infertile women (<39 years old) who were undergoing their first in vitro fertilization cycle were allocated randomly to either mini-in vitro fertilization or conventional in vitro fertilization. The primary outcome was cumulative live birth rate per woman over a 6-month period. Secondary outcomes included ovarian hyperstimulation syndrome, multiple pregnancy rates, and gonadotropin use. The primary outcome was cumulative live birth per randomized woman within a time horizon of 6 months. RESULTS: Five hundred sixty-four couples were assigned randomly between February 2009 and August 2013 with 285 couples allocated to mini-in vitro fertilization and 279 couples allocated to conventional in vitro fertilization. The cumulative live birth rate was 49% (140/285) for mini-in vitro fertilization and 63% (176/279) for conventional in vitro fertilization (relative risk, 0.76; 95% confidence interval, 0.64-0.89). There were no cases of ovarian hyperstimulation syndrome after mini-in vitro fertilization compared with 16 moderate/severe ovarian hyperstimulation syndrome cases (5.7%) after conventional in vitro fertilization. The multiple pregnancy rates were 6.4% in mini-in vitro fertilization compared with 32% in conventional in vitro fertilization (relative risk, 0.25; 95% confidence interval, 0.14-0.46). Gonadotropin consumption was significantly lower with mini-in vitro fertilization compared with conventional in vitro fertilization (459 ± 131 vs 2079 ± 389 IU; P < .0001). CONCLUSION: Compared with conventional in vitro fertilization with double embryo transfer, mini-in vitro fertilization with single embryo transfer lowers live birth rates, completely eliminates ovarian hyperstimulation syndrome, reduces multiple pregnancy rates, and reduces gonadotropin consumption.

Necrospermia, antisperm antibodies, and vasectomy.

OBJECTIVE: To present a case of necrospermia and antisperm antibodies after vasectomy reversal and in which motile sperm, subsequently used in intracytoplasmic sperm injection (ICSI) treatment, was found after testicular sperm retrieval. DESIGN: Case report and literature review. SETTING: Reproductive medicine unit based in a women's hospital in the United Kingdom. PATIENT(S): A 36-year-old man with secondary infertility who presented with necrospermia and antisperm antibodies after vasectomy reversal. INTERVENTION(S): Testicular sperm retrieval and IVF with ICSI. MAIN OUTCOME MEASURE(S): Presence of motile sperm in testicular sperm extraction biopsies. RESULT(S): Motile sperm found after testicular sperm retrieval successfully fertilized oocytes in an ICSI cycle. CONCLUSION(S): It appears difficult to dissociate the presence of antisperm antibodies from the necrospermia in our patient. Testicular sperm retrieval appeared to partially overcome the effect of the antisperm antibodies by retrieving sperm before they reach seminal plasma, where they would be exposed to the antibodies.