Adaptive adversarial neural networks for the analysis of lossy and domain-shifted datasets of medical images.

In machine learning for image-based medical diagnostics, supervised convolutional neural networks are typically trained with large and expertly annotated datasets obtained using high-resolution imaging systems. Moreover, the network's performance can degrade substantially when applied to a dataset with a different distribution. Here, we show that adversarial learning can be used to develop high-performing networks trained on unannotated medical images of varying image quality. Specifically, we used low-quality images acquired using inexpensive portable optical systems to train networks for the evaluation of human embryos, the quantification of human sperm morphology and the diagnosis of malarial infections in the blood, and show that the networks performed well across different data distributions. We also show that adversarial learning can be used with unlabelled data from unseen domain-shifted datasets to adapt pretrained supervised networks to new distributions, even when data from the original distribution are not available. Adaptive adversarial networks may expand the use of validated neural-network models for the evaluation of data collected from multiple imaging systems of varying quality without compromising the knowledge stored in the network.

Deep learning early warning system for embryo culture conditions and embryologist performance in the ART laboratory.

Staff competency is a crucial component of the in vitro fertilization (IVF) laboratory quality management system because it impacts clinical outcomes and informs the key performance indicators (KPIs) used to continuously monitor and assess culture conditions. Contemporary quality control and assurance in the IVF lab can be automated (collect, store, retrieve, and analyze), to elevate quality control and assurance beyond the cursory monthly review. Here we demonstrate that statistical KPI monitoring systems for individual embryologist performance and culture conditions can be detected by artificial intelligence systems to provide systemic, early detection of adverse outcomes, and identify clinically relevant shifts in pregnancy rates, providing critical validation for two statistical process controls proposed in the Vienna Consensus Document; intracytoplasmic sperm injection (ICSI) fertilization rate and day 3 embryo quality.

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.

Around one in seven couples have trouble conceiving, which means there is a high demand for solutions such as in vitro fertilization, also known as IVF. This process involves fertilizing and developing embryos in the laboratory and then selecting a few to implant into the womb of the patient. IVF, however, only has a 30% success rate, is expensive and can be both mentally and physically taxing for patients. Selecting the right embryos to implant is therefore extremely important, as this increases the chance of success, minimizes complications and ensures the baby will be healthy. Currently the tools available for making this decision are limited, highly subjective, time-consuming, and often extremely expensive. As a result, embryologists often rely on their experience and observational skills when choosing which embryos to implant, which can lead to a lot of variability. An automated system based on artificial intelligence (AI) could therefore improve IVF success rates by assisting embryologists with this decision and ensuring more consistent results. The AI system could learn how embryos develop over time and then uses this information to select the best embryos to implant from just a single image. This would offer a cheaper alternative to current analysis tools that are only available at the most expensive IVF clinics. Now, Bormann, Kanakasabapathy, Thirumalaraj et al. have developed an AI system for IVF based on thousands of images of embryos. Using individual images, the system selected embryos of a comparable quality to those selected by a human specialist. It also showed a greater ability to identify embryos that will lead to successful implantation. Indeed, the software outperformed 15 embryologists from five different centers across the United States in detecting which embryos were most likely to implant out of a group of high-quality embryos with few visible differences. Artificial intelligence has many potential applications to support expert clinical decision-making. Systems like these could improve success, reduce errors and lead to faster, cheaper and more accessible results. Beyond immediate IVF applications, this system could also be used in research and industry to help understand differences in embryo quality.

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.