DEVELOPMENT OF AN ARTIFICIAL INTELLIGENCE SOFTWARE, USING DEEP LEARNING, FOR DETERMINATION OF PLOIDY OF HUMAN EMBRYOS

• Grant number: 23/05345-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2023
• End date: December 31, 2023
• Field of knowledge: Health Sciences - Medicine
• Principal Investigator: José Celso Rocha
• Grantee: Murilo Costa Maffeis
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

Infertility, nowadays, is considered a public health problem worldwide, affecting about 48 million couples and 186 million individuals, according to data from the World Health Organization. Thus, assisted reproduction appears as an alternative for these couples, offering a way to overcome this obstacle. Although it is a relatively new area, starting in the 1970s, the techniques used in assisted reproduction, such as in vitro fertilization and intracytoplasmic sperm injection, have a low success rate (25% to 40%). Therefore, the task of choosing the best embryo to be implanted is crucial to increase this rate. One of the main factors analyzed for the evaluation of a human embryo is the identification of aneuploidies in its cells, which can cause implantation failures, miscarriages and malformations in live births. Currently, the most used technique to identify aneuploidy is the Preimplantation Genetic Test, which consists of an embryonic biopsy, where cells from the embryo's trophectoderm are collected and subsequently analyzed. This technique, as it is highly invasive and presents possible false positive results, is not recommended in several countries. In order to develop a new non-invasive means of analysis, the objective of this project is to elaborate a software, which uses image analysis tools and artificial intelligence, capable of identifying the ploidy of human embryos.