Automated Detection of Human Blastocyst Quality Using Convolutional Neural Network and Edge Detector
Irmawati Irmawati, Basari Basari, Dadang Gunawan · 2019
IVF (in vitro fertilization) is one type of assisted reproduction technology (ART) that can be a hope for couples with fertility problems (infertility) to get progeny. In supporting the success of IVF, there are several factors that can be an important role the one of which is in determining the quality of the embryo to be implantation. There are several numbers of previous researchers who had conducted research on determining the quality of the embryo but were still assisted by an embryologist and not automatically can detect the grade of embryo quality. In this paper, we propose a Convolutional Neural Network (CNN) model using image processing for detection quality of blastocyst grade with automatically and improve the accuracy. Keras is used for the implementation of CNN. We have tested our model and have been able to achieve a detection accuracy of 64.29% without image pre-processing and 84.62% using image pre-processing with Canny edge detector.