Artificial intelligence-enabled system for embryo classification and selection based on image analysis

Application of artificial intelligence in gametes and embryos selection

Gamete and embryo quality are critical to the success rate of Assisted Reproductive Technology (ART) cycles, but there remains a lack of methods to accurately measure the quality of sperm, oocytes and embryos. The ability of Artificial Intelligence (AI) technology to analyze large amounts of data, especially video and images, is particularly useful in gamete and embryo assessment and selection. The well-trained model has fast calculation speed and high accuracy, which can help embryologists to perform more objective gamete and embryo selection. Various artificial intelligence models have been developed for gamete and embryo assessment, some of which exhibit good performance. In this review, we summarize the latest applications of AI technology in semen analysis, as well as selection for sperm, oocyte and embryo, and discuss the existing problems and development directions of artificial intelligence in this field.

Quality assurance (QA) for monitoring the performance of assisted reproductive technology (ART) staff using artificial intelligence (AI)

PURPOSE

Deep learning neural networks have been used to predict the developmental fate and implantation potential of embryos with high accuracy. Such networks have been used as an assistive quality assurance (QA) tool to identify perturbations in the embryo culture environment which may impact clinical outcomes. The present study aimed to evaluate the utility of an AI-QA tool to consistently monitor ART staff performance (MD and embryologist) in embryo transfer (ET), embryo vitrification (EV), embryo warming (EW), and trophectoderm biopsy (TBx).

METHODS

Pregnancy outcomes from groups of 20 consecutive elective single day 5 blastocyst transfers were evaluated for the following procedures: MD performed ET (N = 160 transfers), embryologist performed ET (N = 160 transfers), embryologist performed EV (N = 160 vitrification procedures), embryologist performed EW (N = 160 warming procedures), and embryologist performed TBx (N = 120 biopsies). AI-generated implantation probabilities for the same embryo cohorts were estimated, as were mean AI-predicted and actual implantation rates for each provider and compared using Wilcoxon singed-rank test.

RESULTS

Actual implantation rates following ET performed by one MD provider: "H" was significantly lower than AI-predicted (20% vs. 61%, p = 0.001). Similar results were observed for one embryologist, "H" (30% vs. 60%, p = 0.011). Embryos thawed by embryologist "H" had lower implantation rates compared to AI prediction (25% vs. 60%, p = 0.004). There were no significant differences between actual and AI-predicted implantation rates for EV, TBx, or for the rest of the clinical staff performing ET or EW.

CONCLUSIONS

AI-based QA tools could provide accurate, reproducible, and efficient staff performance monitoring in an ART practice.

Blastocyst Prediction of Day-3 Cleavage-Stage Embryos Using Machine Learning

Background: Embryo selection plays an important role in the success of in vitro fertilization (IVF). However, morphological embryo assessment has a number of limitations, including the time required, lack of accuracy, and inconsistency. This study determined whether a machine learning-based model could predict blastocyst formation using day-3 embryo images.

Methods: Day-3 embryo images from IVF/intracytoplasmic sperm injection (ICSI) cycles performed at My Duc Phu Nhuan Hospital between August 2018 and June 2019 were retrospectively analyzed to inform model development. Day-3 embryo images derived from two-pronuclear (2PN) zygotes with known blastocyst formation data were extracted from the CCM-iBIS time-lapse incubator (Astec, Japan) at 67 hours post ICSI, and labeled as blastocyst/non-blastocyst based on results at 116 hours post ICSI. Images were used as the input dataset to train (85%) and validate (15%) the convolutional neural network (CNN) model, then model accuracy was determined using the training and validation dataset. The performance of 13 experienced embryologists for predicting blastocyst formation based on 100 day-3 embryo images was also evaluated.

Results: A total of 1,135 images were allocated into training ([Formula: see text] 967) and validation ([Formula: see text] 168) sets, with an even distribution for blastocyst formation outcome. The accuracy of the final model for blastocyst formation was 97.72% in the training dataset and 76.19% in the validation dataset. The final model predicted blastocyst formation from day-3 embryo images in the validation dataset with an area under the curve of 0.75 (95% confidence interval [CI] 0.69–0.81). Embryologists predicted blastocyst formation with the accuracy of 70.07% (95% CI 68.12%–72.03%), sensitivity of 87.04% (95% CI 82.56%–91.52%), and specificity of 30.93% (95% CI 29.35%–32.51%).

Conclusions: The CNN-based machine learning model using day-3 embryo images predicted blastocyst formation more accurately than experienced embryologists. The CNN-based model is a potential tool to predict additional IVF outcomes.

Clinical implementation of algorithm-based embryo selection is associated with improved pregnancy outcomes in single vitrified warmed euploid embryo transfers

PURPOSE

To assess whether utilization of a mathematical ranking algorithm for assistance with embryo selection improves clinical outcomes compared with traditional embryo selection via morphologic grading in single vitrified warmed euploid embryo transfers (euploid SETs).

METHODS

A retrospective cohort study in a single, academic center from September 2016 to February 2020 was performed. A total of 4320 euploid SETs met inclusion criteria and were included in the study. Controls included all euploid SETs in which embryo selection was performed by a senior embryologist based on modified Gardner grading (traditional approach). Cases included euploid SETs in which embryo selection was performed using an automated algorithm-based approach (algorithm-based approach). Our primary outcome was implantation rate. Secondary outcomes included ongoing pregnancy/live birth rate and clinical loss rate.

RESULTS

The implantation rate and ongoing pregnancy/live birth rate were significantly higher when using the algorithm-based approach compared with the traditional approach (65.3% vs 57.8%, p<0.0001 and 54.7% vs 48.1%, p=0.0001, respectively). After adjusting for potential confounding variables, utilization of the algorithm remained significantly associated with improved odds of implantation (aOR 1.51, 95% CI 1.04, 2.18, p=0.03) ongoing pregnancy/live birth (aOR 1.99, 95% CI 1.38, 2.86, p=0.0002), and decreased odds of clinical loss (aOR 0.42, 95% CI 0.21, 0.84, p=0.01).

CONCLUSIONS

Clinical implementation of an automated mathematical algorithm for embryo ranking and selection is significantly associated with improved implantation and ongoing pregnancy/live birth as compared with traditional embryo selection in euploid SETs.

Evaluation of deep convolutional neural networks in classifying human embryo images based on their morphological quality

A critical factor that influences the success of an in-vitro fertilization (IVF) treatment cycle is the quality of the transferred embryo. Embryo morphology assessments, conventionally performed through manual microscopic analysis suffer from disparities in practice, selection criteria, and subjectivity due to the experience of the embryologist. Convolutional neural networks (CNNs) are powerful, promising algorithms with significant potential for accurate classifications across many object categories. Network architectures and hyper-parameters affect the efficiency of CNNs for any given task. Here, we evaluate multi-layered CNNs developed from scratch and popular deep-learning architectures such as Inception v3, ResNET-50, Inception-ResNET-v2, NASNetLarge, ResNeXt-101, ResNeXt-50, and Xception in differentiating between embryos based on their morphological quality at 113 h post insemination (hpi). Xception performed the best in differentiating between the embryos based on their morphological quality.

Performance of a deep learning based neural network in the selection of human blastocysts for implantation

Deep learning in in vitro fertilization is currently being evaluated in the development of assistive tools for the determination of transfer order and implantation potential using time-lapse data collected through expensive imaging hardware. Assistive tools and algorithms that can work with static images, however, can help in improving the access to care by enabling their use with images acquired from traditional microscopes that are available to virtually all fertility centers. Here, we evaluated the use of a deep convolutional neural network (CNN), trained using single timepoint images of embryos collected at 113 hr post-insemination, in embryo selection amongst 97 clinical patient cohorts (742 embryos) and observed an accuracy of 90% in choosing the highest quality embryo available. Furthermore, a CNN trained to assess an embryo's implantation potential directly using a set of 97 euploid embryos capable of implantation outperformed 15 trained embryologists (75.26% vs. 67.35%, p<0.0001) from five different fertility centers.

Consistency and objectivity of automated embryo assessments using deep neural networks

OBJECTIVE

To evaluate the consistency and objectivity of deep neural networks in embryo scoring and making disposition decisions for biopsy and cryopreservation in comparison to grading by highly trained embryologists.

DESIGN

Prospective double-blind study using retrospective data.

SETTING

U.S.-based large academic fertility center.

PATIENTS

Not applicable.

INTERVENTION(S)

Embryo images (748 recorded at 70 hours postinsemination [hpi]) and 742 at 113 hpi) were used to evaluate embryologists and neural networks in embryo grading. The performance of 10 embryologists and a neural network were also evaluated in disposition decision making using 56 embryos.

MAIN OUTCOME MEASURES

Coefficients of variation (%CV) and measures of consistencies were compared.

RESULTS

Embryologists exhibited a high degree of variability (%CV averages: 82.84% for 70 hpi and 44.98% for 113 hpi) in grading embryo. When selecting blastocysts for biopsy or cryopreservation, embryologists had an average consistency of 52.14% and 57.68%, respectively. The neural network outperformed the embryologists in selecting blastocysts for biopsy and cryopreservation with a consistency of 83.92%. Cronbach's α analysis revealed an α coefficient of 0.60 for the embryologists and 1.00 for the network.

CONCLUSIONS

The results of our study show a high degree of interembryologist and intraembryologist variability in scoring embryos, likely due to the subjective nature of traditional morphology grading. This may ultimately lead to less precise disposition decisions and discarding of viable embryos. The application of a deep neural network, as shown in our study, can introduce improved reliability and high consistency during the process of embryo selection and disposition, potentially improving outcomes in an embryology laboratory.

Development and evaluation of inexpensive automated deep learning-based imaging systems for embryology

Embryo assessment and selection is a critical step in an in vitro fertilization (IVF) procedure. Current embryo assessment approaches such as manual microscopy analysis done by embryologists or semi-automated time-lapse imaging systems are highly subjective, time-consuming, or expensive. Availability of cost-effective and easy-to-use hardware and software for embryo image data acquisition and analysis can significantly empower embryologists towards more efficient clinical decisions both in resource-limited and resource-rich settings. Here, we report the development of two inexpensive (<$100 and <$5) and automated imaging platforms that utilize advances in artificial intelligence (AI) for rapid, reliable, and accurate evaluations of embryo morphological qualities. Using a layered learning approach, we have shown that network models pre-trained with high quality embryo image data can be re-trained using data recorded on such low-cost, portable optical systems for embryo assessment and classification when relatively low-resolution image data are used. Using two test sets of 272 and 319 embryo images recorded on the reported stand-alone and smartphone optical systems, we were able to classify embryos based on their cell morphology with >90% accuracy.