Identification of Viable Embryos Using Deep Learning for Medical Image

Abstract

Identifying viable embryos for implantation is one of the most relevant aspects in assisted reproductive technology. However, embryo selection highly depends on visual examination by embryologists via microscopy, and their evaluations are often subjective. The rapid growth of image processing technology has resulted in increased interest in the use of machine learning methods for embryo selection in in vitro fertilization (IVF) programs. The present study uses deep learning method for the morphological classification of embryos based on medical images. The proposed system is trained and tested on a real data set of 1,310 images from 344 embryos and evaluated by comparison with other traditional machine learning methods to solve similar classification problems. The results indicate that our new deep learning model significantly outperforms other methods. Our work contributes immensely to the fields of assisted reproductive technology, medical image processing, and decision support system design.