Automatic Identification of Human Blastocyst Components via Texture.

Choosing the most viable embryo during human in vitro fertilization (IVF) is a prime factor in maximizing pregnancy rate. Embryologists visually inspect morphological structures of blastocysts under microscopes to gauge their health. Such grading introduces subjectivity amongst embryologists and adds to the difficulty of quality control during IVF. In this paper, we introduce an algorithm for automatic segmentation of two main components of human blastocysts named: Trophectoderm (TE) and inner cell mass (ICM). We utilize texture information along with biological and physical characteristics of day-5 human embryos (blastocysts) to identify TE or ICM regions according to their intrinsic properties. Both these regions are highly textured and very similar in the quality of their texture, and they often look connected to each other when imaged. These attributes make their automatic identification and separation from each other a difficult task even for an expert embryologist. By automatically identifying TE and ICM regions, we offer the opportunity to perform more detailed assessment of blastocysts. This could help in analyzing, in a quantitative way, various visual/geometrical characteristics of these regions that when combined with the pregnancy outcome can determine the predictive values of such attributes. Our work aids future research in understanding why certain embryos have higher pregnancy success rates. This paper is tested on a set of 211 blastocyst images. We report an accuracy of 86.6% for identification of TE and 91.3% for ICM.