Enhancing predictive accuracy in embryo implantation: The Bonna algorithm and its clinical implications

In the context of in vitro fertilization (IVF), selecting embryos for transfer is critical in determining pregnancy outcomes, with implantation as the essential first milestone for a successful pregnancy. This study introduces the Bonna algorithm, an advanced deep-learning framework engineered to predict embryo implantation probabilities. The algorithm employs a sophisticated integration of machine-learning techniques, utilizing MobileNetV2 for pixel and context embedding, a custom Pix2Pix model for precise segmentation, and a Vision Transformer for additional depth in embedding. MobileNetV2 was chosen for its robust feature extraction capabilities, focusing on textures and edges. The custom Pix2Pix model is adapted for precise segmentation of significant biological features such as the zona pellucida and blastocyst cavity. The Vision Transformer adds a global perspective, capturing complex patterns not apparent in local image segments. Tested on a dataset of images of human blastocysts collected from Ukraine, Israel, and Spain, the Bonna algorithm was rigorously validated through 10-fold cross-validation to ensure its robustness and reliability. It demonstrates superior performance with a mean area under the receiver operating characteristic curve (AUC) of 0.754, significantly outperforming existing models. The study not only advances predictive accuracy in embryo selection but also highlights the algorithm’s clinical applicability due to reliable confidence reporting.