Predicting pregnancy rate following multiple embryo transfers using algorithms developed through static image analysis

Abstract

Single-embryo image assessment involves a high degree of inaccuracy because of the imprecise labelling of the transferred embryo images. In this study, we considered the entire transfer cycle to predict the implantation potential of embryos, and propose a novel algorithm based on a combination of local binary pattern texture feature and Adaboost classifiers to predict pregnancy rate. The first step of the proposed method was to extract the features of the embryo images using the local binary pattern operator. After this, multiple embryo images in a transfer cycle were considered as one entity, and the pregnancy rate was predicted using three classifiers: the Real Adaboost, Gentle Adaboost, and Modest Adaboost. Finally, the pregnancy rate was determined via the majority vote rule based on classification results of the three Adaboost classifiers. The proposed algorithm was verified to have a good predictive performance and may assist the embryologist and clinician to select embryos to transfer and in turn improve pregnancy rate.