A Method Based on Artificial Intelligence To Fully Automatize The Evaluation of Bovine Blastocyst Images

Author(s):Show less -

Rocha, Jose Celso ; Passalia, Felipe Jose ; Matos, Felipe Delestro ; Takahashi, Maria Beatriz ; Ciniciato, Diego de Souza ; Maserati, Marc Peter ; Alves, Mayra Fernanda ; de Almeida, Tamie Guibu ; Cardoso, Bruna Lopes ; Basso, Andrea Cristina ; Gouveia Nogueira, Marcelo Fabio

• Document type: Journal article
• Source: SCIENTIFIC REPORTS; v. 7, AUG 9 2017.
• Web of Science Citations: 7

Abstract

Morphological analysis is the standard method of assessing embryo quality; however, its inherent subjectivity tends to generate discrepancies among evaluators. Using genetic algorithms and artificial neural networks (ANNs), we developed a new method for embryo analysis that is more robust and reliable than standard methods. Bovine blastocysts produced in vitro were classified as grade 1 (excellent or good), 2 (fair), or 3 (poor) by three experienced embryologists according to the International Embryo Technology Society (IETS) standard. The images (n = 482) were subjected to automatic feature extraction, and the results were used as input for a supervised learning process. One part of the dataset (15%) was used for a blind test posterior to the fitting, for which the system had an accuracy of 76.4%. Interestingly, when the same embryologists evaluated a sub-sample (10%) of the dataset, there was only 54.0% agreement with the standard (mode for grades). However, when using the ANN to assess this sub-sample, there was 87.5% agreement with the modal values obtained by the evaluators. The presented methodology is covered by National Institute of Industrial Property (INPI) and World Intellectual Property Organization (WIPO) patents and is currently undergoing a commercial evaluation of its feasibility. (AU)

• FAPESP's process: 11/06179-7 - Use of artificial neural network based system to evaluate viability and quality of mouse embryos
• Grantee: Felipe Delestro Matos
• Support type: Scholarships in Brazil - Scientific Initiation
• FAPESP's process: 12/20110-2 - Software based on artificial neural networks for embryo morphologic evaluation
• Grantee: Felipe Delestro Matos
• Support type: Scholarships in Brazil - Master
• FAPESP's process: 06/06491-2 - Embryonic chimerism on murine and bovine species: Pattern of interaction between inner cell mass - from embryos produced in vivo - and recipient embryos produced in vitro
• Grantee: Marcelo Fábio Gouveia Nogueira
• Support type: Research Grants - Young Investigators Grants
• FAPESP's process: 12/50533-2 - GIFT: genomic improvement of fertilization traits in Danish and Brazilian cattle
• Grantee: Marcelo Fábio Gouveia Nogueira
• Support type: Research Projects - Thematic Grants
• FAPESP's process: 13/05083-1 - Modulation of oocyte nuclear maturation and its effects on cumulus-oocyte complexes and bovine embryo production in vitro
• Grantee: Marcelo Fábio Gouveia Nogueira
• Support type: Regular Research Grants