Automatized image processing of bovine blastocysts produced in vitro for quantitative variable determination

There is currently no objective, real-time and non-invasive method for evaluating the quality of mammalian embryos. In this study, we processed images of in vitro produced bovine blastocysts to obtain a deeper comprehension of the embryonic morphological aspects that are related to the standard eval...

Full description

Saved in:

Bibliographic Details
Published in:	Scientific data Vol. 4; no. 1; p. 170192
Main Authors:	Rocha, José Celso, Passalia, Felipe José, Matos, Felipe Delestro, Takahashi, Maria Beatriz, Maserati Jr, Marc Peter, Alves, Mayra Fernanda, de Almeida, Tamie Guibu, Cardoso, Bruna Lopes, Basso, Andrea Cristina, Nogueira, Marcelo Fábio Gouveia
Format:	Journal Article
Language:	English
Published:	London Nature Publishing Group UK 19-12-2017 Nature Publishing Group
Subjects:	631/136/1455 631/1647/245 631/1647/328 639/705/1041 Artificial intelligence Blastocysts Data Descriptor Humanities and Social Sciences Image processing multidisciplinary Neural networks Science
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	There is currently no objective, real-time and non-invasive method for evaluating the quality of mammalian embryos. In this study, we processed images of in vitro produced bovine blastocysts to obtain a deeper comprehension of the embryonic morphological aspects that are related to the standard evaluation of blastocysts. Information was extracted from 482 digital images of blastocysts. The resulting imaging data were individually evaluated by three experienced embryologists who graded their quality. To avoid evaluation bias, each image was related to the modal value of the evaluations. Automated image processing produced 36 quantitative variables for each image. The images, the modal and individual quality grades, and the variables extracted could potentially be used in the development of artificial intelligence techniques (e.g., evolutionary algorithms and artificial neural networks), multivariate modelling and the study of defined structures of the whole blastocyst. Design Type(s) observation design • image analysis objective Measurement Type(s) Cellular Morphology Technology Type(s) light microscopy Factor Type(s) Sample Characteristic(s) Bos taurus • blastocyst Machine-accessible metadata file describing the reported data (ISA-Tab format)
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3 J.C.R., F.D.M., M.B.T., and M.F.G.N. designed this study based on a previously published study in mice. M.P.M.Jr, M.F.A., T.G.A., and B.L.C. evaluated the blastocyst images one or more times. M.P.M.Jr, F.D.M., and F.J.P. captured the digital images. A.C.B. gave consent from the company In Vitro Brasil to provide the embryos and the digital image capture system for use in this work. F.D.M., F.J.P., M.B.T., and J.C.R. developed the software to fully automatize the extraction of quantitative variables from images. J.C.R., F.J.P., F.D.M., M.B.T., A.C.B., and M.F.G.N. wrote, formatted, and revised the manuscript.
ISSN:	2052-4463 2052-4463
DOI:	10.1038/sdata.2017.192