Digital processing of human blastocyst images to obtain predictive variables of morphological quality

• Grant number: 18/19053-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2019
• End date: December 31, 2019
• Field of knowledge: Health Sciences - Medicine
• Principal Investigator: Marcelo Fábio Gouveia Nogueira
• Grantee: Dóris Spinosa Chéles
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

Assisted reproduction techniques, in the human species, have been increasingly used over the last years due to the greater demand for sub/infertility problems. In vitro fertilization is one of the most used procedures in clinics, where the choice of the best quality embryo is of fundamental importance for the success of this technique. Embryologists generally observe the embryos through optical microscopy and classify them based on the system developed by Gardner & Schoolcraft (1999) - or systems based on it - which evaluates the stage of blastocyst expansion and hatching and the quality of its inner cell mass and trophectoderm. Based on these parameters, embryo quality is defined. In this process, the intrinsic subjectivity of each embryologist influences the classification of the embryos and, consequently, the evaluation performed incurs low reproducibility. The use of the time-lapse system, associated with digital image processing and later application in software that classifies blastocyst images, would provide an alternative to the conventional technique. In this way, it would be possible to reduce the existing subjectivity in the current analysis and would allow the objective choice of the embryo of better morphology. Thus, the purpose of this project will be the application of digital processing techniques in human blastocyst images, so that it is possible to extract predictive mathematical variables of morphological quality. These will serve as input parameters for software that is capable of performing quality classification objectively and fully automated.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DE LOS ANGELES VALERA, MARIA; CELSO ROCHA, JOSE; BORI, LORENA; ALEGRE, LUCIA; GOUVEIA NOGUEIRA, MARCELO FABIO; SPINOSA CHELES, DORIS; MESEGUER, MARCOS. NOVEL ARTIFICIAL INTELLIGENCE ALGORITHM FOR IMPROVING EMBRYO SELECTION COMBINING MORPHOKINETICS AND NON-INVASIVE MEASUREMENT OF OXIDATIVE STRESS.. Fertility and Sterility, v. 114, n. 3, p. 2-pg., 2020-09-01. (18/19053-0, 17/19323-5)