A recent study published in Nature Communications introduces the Blastocyst Evaluation Learning Algorithm (BELA), a machine-learning model developed to advance embryo selection in in vitro fertilization (IVF). This innovation promises to improve IVF outcomes through noninvasive techniques powered by artificial intelligence (AI).
Study: Automatic ploidy prediction and quality assessment of human blastocysts using time-lapse imaging. Image Credit: Alex Mit/Shutterstock.com
Advancement in Embryo Assessment
Since IVF was first introduced in 1978, it has helped bring over 8 million babies into the world. A key factor of IVF success is selecting high-quality embryos, primarily determined by their ploidy status. Ploidy status represents the chromosomal composition of an embryo, which significantly influences pregnancy outcomes.
Euploid embryos, with a normal chromosome count, are more likely to lead to successful pregnancies. In contrast, aneuploid embryos, which have chromosomal abnormalities, are often associated with an increased risk of miscarriage and genetic disorders.
Traditional methods for assessing ploidy, such as preimplantation genetic testing for aneuploidy (PGT-A), are often invasive, expensive, and time-intensive, with potential implications for embryo viability. However, recent advancements in AI and computer vision have enabled non-invasive, automated embryo assessments through time-lapse imaging, offering a promising alternative.
BELA: An Innovative AI Model
In this study, the authors presented BELA, an AI-based model designed to predict embryo ploidy status using time-lapse sequences of embryo development. They employed deep learning techniques to analyze these sequences across various stages of growth.
BELA operates in two primary phases. The first phase involves predicting the blastocyst score (BS), an intermediary measure of embryo quality. To do this, BELA analyzes day-5 time-lapse videos, capturing essential developmental stages using a pre-trained 16-layer Visual Geometry Group (VGG16) convolutional neural network (CNN). This architecture efficiently extracts spatial and temporal features from the images.
Next, BELA applies a bidirectional long-short-term memory (BiLSTM) network to forecast specific morphological scores, including inner cell mass (ICM), trophectoderm (TE), and expansion scores. These individual scores are synthesized to produce a model-derived blastocyst score (MDBS). In the second phase, BELA leverages the MDBS, combined with maternal age, to predict embryo ploidy status using logistic regression.
Key Findings and Insights
The outcomes revealed that BELA excelled in accurately predicting embryo ploidy status, achieving an AUC of 0.66 in classifying embryos as euploid or aneuploid. This performance improved to 0.76 when maternal age was included, aligning with models based on embryologists' manual assessments.
BELA also demonstrated strong capabilities in identifying complex aneuploid embryos, reaching an AUC of 0.826 when factoring in maternal age. This indicates BELA's effectiveness in detecting embryos with multiple chromosomal abnormalities, which are typically more difficult to identify. The study emphasized maternal age as a critical predictor of ploidy, revealing that lower maternal age correlates with higher rates of euploid predictions.
In comparison to traditional models that rely solely on time-lapse imaging or manual annotations, BELA showed superior performance. Its robustness across datasets from various clinics with different practices highlights its adaptability.
Applications
This research proposed a non-invasive, accurate, and efficient method for predicting embryo ploidy status, enhancing the efficiency and accuracy of embryo selection in IVF. BELA has the potential to improve pregnancy outcomes and reduce the risks associated with invasive procedures like PGT-A. Its ability to provide explainable predictions through model-derived blastocyst scores can assist embryologists in making informed decisions.
Furthermore, the authors developed a web-based application called STORK-V to facilitate the clinical use of BELA, making it accessible to IVF clinics and embryologists. This platform not only predicts ploidy status but also offers intermediary quality scores, enriching the analytical tools available to medical professionals.
Conclusion and Future Directions
In summary, BELA represents a significant advancement in automating embryo assessment in IVF and could revolutionize the field of reproductive medicine. Its performance across multiple datasets and adaptability to different clinical workflows highlight its potential to improve the embryo selection process. While BELA is not intended to replace PGT-A, it provides valuable supplementary information that can support embryologists in their decision-making, ultimately enhancing IVF success rates.
Future work should focus on refining the model by incorporating additional maternal features and exploring advanced video classification architectures. Expanding the training dataset to include more diverse clinical settings could enhance the model's generalizability.
Journal Reference
Rajendran, S., Brendel, M., Barnes, J. et al. Automatic ploidy prediction and quality assessment of human blastocysts using time-lapse imaging. Nat Commun 15, 7756 (2024). DOI: 10.1038/s41467-024-51823-7, https://www.nature.com/articles/s41467-024-51823-7
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.