South China University of Technology - SCUT

Infertility remains a global challenge in part because deciding which embryos have the best chance of leading to pregnancy through in vitro fertilization (IVF) is still subjective and inefficient. A new review examines how artificial intelligence is being applied to embryo grading and pregnancy prediction in assisted reproductive technology by organizing research around the types of data used, including static images, time-lapse videos, and structured clinical tables. By reframing the problem through data modality, the authors clarify how different AI models capture embryo quality and where design tradeoffs emerge. They also evaluate persistent barriers such as multi-modal data fusion, limited datasets, generalization across clinics, and evolving regulatory constraints. Smarter integration of diverse data – not just better algorithms – may be the key to improving IVF success rates. 𝗥𝗲𝗮𝗱 𝗺𝗼𝗿𝗲: link.springer.com/article/10… 𝗥𝗲𝘃𝗶𝗲𝘄: Multi-modal Artificial Intelligence of Embryo Grading and Pregnancy Prediction in Assisted Reproductive Technology: A Review 𝗔𝘂𝘁𝗵𝗼𝗿𝘀: Xueqiang Ouyang and Jia Wei @SCUT1918 𝗦𝘂𝗯𝗺𝗶𝘁 𝘆𝗼𝘂𝗿 𝗺𝗮𝗻𝘂𝘀𝗰𝗿𝗶𝗽𝘁: link.springer.com/journal/10…