Oocyte Microscopic Image Fertilization Prediction based on First Polar Body Morphology using YOLOv8

The development of oocytes is crucial in the development and fertility of embryos in In Vitro Fertilization (IVF). There are several internal and external factors that could affect the fertilization competency of oocytes, one of which is the first polar body (PBI). However, there is still a debate regarding the influence of PBI on the developmental competency of oocytes. This work aims to find the correlation of the successful fertilization in which the mature oocyte develops into the stage of two pronuclei (2PN) by using You Only Look Once (YOLO), which is a type of Convolutional Neural Network (CNN) widely applied to medical imaging problems. Our pipeline consists of exclusive segmentation CNN and classification CNN. First, light microscopic images of oocytes in the metaphase of meiosis II (MII) stage are captured, followed by the prediction of the likelihood of 2PN development after fertilization through intracytoplasmic sperm injection (ICSI). The image has its PBI segmented by the CNN and then cropped out of the original image. The PBI image is then fed into the prediction CNN to obtain the final result. The experiment showed that the best model is YOLOv8l-cls, trained on a dataset of 1006 images, with the top accuracy at 96.98% accuracy, 95.69% sensitivity and 98.28% specificity. Furthermore, the ability of the model to predict without any additional features indicates the correlation between the PBI and the development tendency of oocytes.