Felipe Delestro Matos

Methods for assessing the quality of mammalian embryos: How far we are from the gold standard?

Morphological embryo classification is of great importance for many laboratory techniques, from basic research to the ones applied to assisted reproductive technology. However, the standard classification method for both human and cattle embryos, is based on quality parameters that reflect the overall morphological quality of the embryo in cattle, or the quality of the individual embryonic structures, more relevant in human embryo classification. This assessment method is biased by the subjectivity of the evaluator and even though several guidelines exist to standardize the classification, it is not a method capable of giving reliable and trustworthy results. Latest approaches for the improvement of quality assessment include the use of data from cellular metabolism, a new morphological grading system, development kinetics and cleavage symmetry, embryo cell biopsy followed by pre-implantation genetic diagnosis, zona pellucida birefringence, ion release by the embryo cells and so forth. Nowadays there exists a great need for evaluation methods that are practical and non-invasive while being accurate and objective. A method along these lines would be of great importance to embryo evaluation by embryologists, clinicians and other professionals who work with assisted reproductive technology. Several techniques shows promising results in this sense, one being the use of digital images of the embryo as basis for features extraction and classification by means of artificial intelligence techniques (as genetic algorithms and artificial neural networks). This process has the potential to become an accurate and objective standard for embryo quality assessment.

A method using artificial neural networks to morphologically assess mouse blastocyst quality.

BackgroundMorphologically classifying embryos is important for numerous laboratory techniques, which range from basic methods to methods for assisted reproduction. However, the standard method currently used for classification is subjective and depends on an embryologist’s prior training. Thus, our work was aimed at developing software to classify morphological quality for blastocysts based on digital images.MethodsThe developed methodology is suitable for the assistance of the embryologist on the task of analyzing blastocysts.The software uses artificial neural network techniques as a machine learning technique. These networks analyze both visual variables extracted from an image and biological features for an embryo.ResultsAfter the training process the final accuracy of the system using this method was 95%. To aid the end-users in operating this system, we developed a graphical user interface that can be used to produce a quality assessment based on a previously trained artificial neural network.ConclusionsThis process has a high potential for applicability because it can be adapted to additional species with greater economic appeal (human beings and cattle). Based on an objective assessment (without personal bias from the embryologist) and with high reproducibility between samples or different clinics and laboratories, this method will facilitate such classification in the future as an alternative practice for assessing embryo morphologies.

Utilização de redes neurais artificiais para a determinação do número de refeições diárias de um restaurante universitário

OBJECTIVE: This study aimed to build an artificial neural network to help the managers of university cafeterias to predict the number of daily meals. METHODS: This study was based on a survey of eight variables that influence the number of daily meals served by a university cafeteria. Backpropagation training algorithm was used and the results obtained by the network are compared with results of the studied series and the results estimated by simple arithmetic average. RESULTS: The proposed network follows the numerous changes that occur in the number of daily meals of the university cafeteria. In 73% of the analyzed days, the artificial neural networks method presented a greater success rate than the simple arithmetic average method. CONCLUSION: Artificial neural network predicted the number of meals better than the simple average method or than decisions made subjectively.

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 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.

Code source used to determine variables from blastocyst - HistProps

Code source used to determine some variables from blastocyst with reduced radius and from trophectoderm.

Algoritmo Genético aplicado na obtenção de arquiteturas ótimas de Redes Neurais Artificiais

A principal dificuldade na utilizacao das Redes Neurais Artificiais (RNA) e a obtencao da melhor arquitetura de RNA para a solucao de um determinado problema. Como forma de solucionar a determinacao da melhor arquitetura, foi desenvolvido um software baseado em Algoritmo Genetico e o mesmo foi aplicado para problemas de classificacao de blastocistos bovinos e classificacao de vidro.