AI System BELA Revolutionizes IVF Embryo Assessment

Breakthrough in IVF Technology: Introducing BELA

Researchers at Weill Cornell Medicine have developed a groundbreaking artificial intelligence system called BELA (Blastocyst Evaluation using Learning Algorithms) that promises to revolutionize the assessment of in vitro fertilization (IVF) embryos. This innovative technology, described in a recent paper published in Nature Communications, offers a fully automated and objective approach to determining embryo quality 1

1

How BELA Works

BELA utilizes machine learning to analyze nine time-lapse video images of an embryo taken approximately five days after fertilization. The system generates an embryo quality score based on these images and combines it with maternal age to predict whether the embryo has a normal (euploid) or abnormal (aneuploid) number of chromosomes – a critical factor in IVF success 2

2

Unlike previous AI-based methods, BELA does not rely on subjective assessments from embryologists. This objectivity enhances its potential for widespread adoption in embryology clinics, potentially improving IVF efficiency and outcomes 3

3

Advantages Over Current Methods

Traditionally, embryologists assess IVF embryo quality through microscopic examination. In cases where potential issues are suspected, such as advanced maternal age, a more invasive procedure called preimplantation genetic testing for aneuploidy (PGT-A) is employed. BELA offers a non-invasive alternative that could reduce the need for such risky procedures 1

1

Dr. Iman Hajirasouliha, the study's senior author, emphasized the system's advantages: "This is a fully automated and more objective approach compared to prior approaches, and the larger amount of image data it uses can generate greater predictive power" 2

2

Related Stories

AI Analysis Reveals Optimal Follicle Sizes for Improved IVF Success Rates

World's First Baby Born Through AI-Assisted Automated IVF

AI-Powered STAR System Achieves First Successful Pregnancy in Severe Male Infertility Case

AI-Powered STAR System Helps Couple Conceive After 18 Years of Infertility

Development and Testing

The research team, led by doctoral student Suraj Rajendran and including experts Dr. Nikica Zaninovic and Dr. Zev Rosenwaks, trained BELA using a dataset of nearly 2,000 embryos with known PGT-A-tested ploidy status. The system was then tested on new datasets from Weill Cornell Medicine and IVF clinics in Florida and Spain 3

3

Results showed that BELA predicted ploidy status with moderately higher accuracy than previous versions and performed well across both internal and external datasets 1

1

Future Implications

The researchers are planning a randomized, controlled clinical trial to further test BELA's predictive power. If successful, this technology could have far-reaching implications for IVF treatment worldwide 2

2

Dr. Zaninovic highlighted the potential impact: "BELA and AI models like it could expand the availability of IVF to areas that don't have access to high-end IVF technology and PGT testing, improving equity in IVF care across the world" 3

3

Beyond ploidy prediction, the researchers envision BELA's application in general embryo quality estimation, prediction of embryo development stages, and other customizable functions for embryology clinics 1

1

As AI continues to advance in the field of reproductive medicine, BELA represents a significant step towards more accessible, efficient, and successful IVF treatments, potentially bringing hope to millions of people struggling with infertility worldwide.