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.

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.