BR102012031953B1 - method for determining embryo viability and quality - Google Patents

Abstract

method for determining the viability and quality of embryos. and described the invention of a method for determining the viability and quality of embryos that allows a quick assessment and with minimal interference in embryonic development, using a microscopy system associated with digital image capture, providing a set of values for each embryo it represents how much q embryo is able to be considered in each of the four possible degrees, using the technique of artificial neural networks, providing objectivity and reproducibility.

Description

METHOD FOR DETERMINING EMBRYO FEASIBILITY AND QUALITY

FIELD OF THE INVENTION

The present invention describes a method for determining embryo viability and quality. More specifically it comprises a method that allows to determine the quality of embryos from the morphological analysis of a two-dimensional figure, using the technique of artificial neural networks (ANN), providing an objective and reproducible quality index.

BACKGROUND OF THE INVENTION

Since the development of the first successful techniques of artificial fertilization and embryo transfer in mammalian embryos, a direct relationship between embryonic quality and the success rate of transfers of these embryos in recipient females has become visible, with embryos morphologically classified as quality high have a higher success rate (HR Tervit, MW Cooper, Pamela G. Goold, GM Haszard, Non-surgicalembryotransfer in cattle, Theriogenology, Volume 13, Issue 1, January 1980, Pages 63-71, ISSN 0093-691X, 10.1016 / 0093-691X (80) 90015-1) e (HJ Schneider Jr., RS Castleberry, JL Griffin, Commercial aspects of bovine embryo transfer, Theriogenology, Volume 13, Issue 1, January 1980, Pages 73-85, ISSN 0093- 691X, 10.1016 / 0093-691X (80) 90016-3).

Embryonic morphological classification is of great importance for numerous laboratory techniques, from basic research to applied in assisted reproduction. It is from this that success rates (pregnancy), use of associated biotechniques (cryopreservation, biopsy, bipartition, microinjection, etc.) or

2/17 even for standardization of embryos used in scientific experiments.

To this end, methods for standardizing the elements that categorize embryos in different degrees according to their quality (and therefore also according to their viability) were developed, and the four-degree system is currently widely used: Excellent (Excellent), Good ( Good), Regular (Fair) and Bad or Poor (Gary M. Lindner, Raymond W. Wright Jr., Bovineembryomorphologyandevaluation, Theriogenology, Volume 20, Issue4, October 1983, Pages 407-416, ISSN 0093-691X, 10.101616 / 0093-691X (83) 90201-7) e (RW Wright Jr., J. Ellington, Morphological and physiological differences between in vivo- and in vitro- produced pre implantatio nembryos from live stock species, Theriogenology, Volume 44, Issue 8 , December 1995, Pages 11671189, ISSN 0093-691X, 10.1016 / 0093-691 X (95) 00327-5). This system is based on the qualitative visual morphological analysis of the embryo, commonly done through optical microscopy (stereomicroscope). The technique depends on the embryologist's experience and accuracy in analyzing and categorizing from the obvious factors to the nuances that make an embryo more or less apt for development. In this classic morphological analysis, such factors are not objectively measured, so that it becomes subjective and of low repeatability (BalázsBényei, IstvánKomlósi, Anna Pécsi, GeoffryPollott, Cruvinel Heraldo Marcos, Alexandre de Oliveira Campos, Maida Paula Lemes, The effect of internal and external factors on bovine embryo transfer results in a tropical environment, Animal Reproduction Science, Volume 93, Issues 3-4, July 2006, Pages 268-279, ISSN 0378-4320, 10.1016 / j.anireprosci.2005.07.012).

3/17

It follows that the same embryo measured by different specialists can obtain different degrees of classification. Such disagreement occurs mainly between close degrees, as between good and excellent embryos (PW Farin, JH Britt, DW Shaw, BD Slenning, Agreement among evaluators of bovine embryos produced in vivo or in vitro, Theriogenology, Volume 44, Issue3, August 1995, Pages 339-349, ISSN 0093-691X, 10.1016 / 0093-691X (95) 00189-F).

Seeking solutions to the issue of subjectivity in morphological analysis, several alternative methods were developed. Among them, in vitro embryo culture, blastomeric membrane integrity, analysis of embryonic metabolism can be highlighted (Eric W. Overstrõm, In vitro assessment of embryo viability, Theriogenology, Volume 45, Issue 1, 1 January 1996, Pages

3-16, ISSN 0093-691X, 10.1016 / 0093-691X (96) 84625-5.), Measurement of cellular respiration (HiroyoshiHoshi, ln vitro production of bovine embryos and their application for embryo transfer, Theriogenology, Volume 59, Issue 2 , 15 January 2003, Pages 675685, ISSN 0093-691X, 10.1016 / S0093-691X (02) 01247-5), analysis with electron microscopy (López-Damián E. P, Galina CS, Merchant H., Cedillo-Peláez C. , Aspron M., Assessment of Bostaurus embryos comparing stereoscopic microscopy and transmission electron microscopy.Journal of Cell and Animal Biology Vol. 2 (3), pp. 072-078, March 2008, ISSN 1996-0867 © 2008 Academicjournals) and use of birefringence indices of the pellucid zone (Held, Eva, Mertens, Eva-Maria, Mohammadi-Sangcheshmeh, Abdollah, SalilewWondim, Dessie, Besenfelder, Urban, Havlicek, Vitezslav, Herder, Andreas, Tesfaye, Dawit, Schellander, Michael, andHolker (2011). Zonapellucida birefringence correlates with developmental capacity of

4/17 bovine oocytes classified by maturational environment, COC morphology and G6PDH activity. Play Fertile. Dev. 24, 568-579).

However, no method has yet presented a definitive solution for measuring quality and viability, and it is still necessary to develop methods that are fast, non-invasive and objective.

Another factor to be analyzed is the high cost of some methods, which prevents its widespread use. Thus, despite subjectivity and low repeatability, visual morphological analysis remains widely used to determine embryonic quality.

Therefore, the present invention describes a method for determining the viability and quality of embryos that allows a quick assessment and with minimal interference in embryonic development, as a microscopy system associated with digital image capture is required, providing a set of values for each embryo that represents how much the embryo is able to be considered in each of the four possible degrees, using the technique of Artificial Neural Networks, providing objectivity and reproducibility.

SUMMARY

A characteristic of the invention is a method for determining the viability and quality of embryos from the morphological analysis of a two-dimensional figure, using the technique of Artificial Neural Networks (ANN).

Characteristic of the invention is a method for determining the viability and quality of embryos that provides an objective and reproducible index of embryo quality as a result.

Characteristic of the invention is a method for determining the

5/17 viability and quality of embryos with potential application in scientific research involving mouse / rat embryos, in the quality classification of bovine embryos produced for commercial use (in vitro production), as well as for the evaluation of embryonic quality of human embryos in assisted reproduction clinics.

A characteristic of the invention is a method for determining the viability and quality of embryos based on the objectivity of the analysis and which does not depend on the quality of the microscope, the experience of the embryologist and the restricted capacity of the degrees of embryonic quality, classically used for the evaluation.

The invention features a method for determining the viability and quality of embryos that does not damage the embryos, is non-invasive and can be performed in a short time, allowing the evaluator to interpret the response, so that the individual clinical experience can maximize the result obtained by the method.

BRIEF DESCRIPTION OF THE FIGURES '

Figure 1 shows the representation of the measurement of the measurement of the first embryo diameter (DE1).

Figure 2 shows the representation of the measurement of the measurement of the second embryo diameter (DE2).

Figure 3 shows the representation of the first diameter of the pellucid zone (DZP1).

Figure 4 shows the representation of the marking of the second diameter of the pellucid zone (DZP2).

Figure 5 shows the representation of the marking of the embryo area (LA).

Figure 6 shows the representation of the area's marking.

6/17 pellucid zone (AZP).

Figure 7 shows the representation of the Dead Cell Area (ACM) marking.

Figure 8 shows the color density marking of the pellucid zone (DCZP).

Figure 9 shows the flowchart of the method used to evaluate the RNA architecture.

DETAILED DESCRIPTION OF THE INVENTION

The method for determining the viability and quality of embryos, the object of the present invention, allows the morphological evaluation of embryos in an objective way, by extracting information from embryo images and later analyzing it through a computer program based on networks Artificial Neural (ANN), an Artificial Intelligence technique indicated for solving nonlinear problems and with interconnected variables (Guoqiang Zhang, B. EddyPatuwo, Michael Y. Hu, Forecastingwith artificial neural networks: The state of the art, International Journal of Forecasting, Volume 14, Issue 1, 1 March 1998, Pages 35-62, ISSN 0169-2070, 10.1016 / S0169-2070 (97) 00044-7) e (Eldon Y. Li, Artificial neural networks and their business applications, Information & Management, Volume 27, Issue 5, November 1994, Pages 303-313, ISSN 0378-7206, 10.1016 / 0378-7206 (94) 90024-8).

Basically, an Artificial Neural Network is a system that acts in solving problems, simulating the functioning of a set of biological neurons. Such RNA neurons (also called perceptrons) need to be exposed to training data in order to learn how to generalize an output from a set of input data. Once properly trained,

7/17 RNA is able to make predictions without the output data (Guoqiang Zhang, B. Eddy Patuwo, Michael Y. Hu, Forecasting with artificial neural networks: The state of the art, International Journal of Forecasting, Volume 14, Issue 1, 1 March 1998, Pages 35-62, ISSN 0169-2070, 10.1016 / S0169-2070 (97) 00044-7) and (Haykin, S., Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice Hall, 1999 ISBN: 0132733501).

In the present method for determining the viability and quality of embryos, the information is extracted from the embryo image using a protocol, and then processed by a computer program that works with the received data, transforming them into input variables for RNA and performs the processing, providing as a result an embryonic quality index in the same standards that an embryologist would provide (Excellent, Good, Regular and Bad grades).

In a first stage of the method for determining the viability and quality of embryos, images of the embryo are obtained, with images of blastocysts being preferably selected, from the initial blastocyst phase to expanded blastocyst.

Necessarily, the image must present the embryo in its entirety, with clearness of the pellucid area and the boundary of the blastocele must be visible.

In a second step, the image of the embryo is processed by image processing software, and measurements are obtained from the selection of image points.

The variables obtained using the image processing computer program include:

a) First embryo diameter (DE1), which comprises the

8/17 measure of embryo diameter obtained through a line that joins the most extreme points of the embryo, disregarding the diameter of the pellucid zone (Figure 1);

b) Second embryo diameter (DE2), which comprises the embryo diameter measurement obtained through a line approximately perpendicular to the DE1 line, which connects the most extreme points of the embryo, without taking into account the diameter of the pellucid zone (Figure 2 );

c) First diameter of the pellucid zone (DZP1), which comprises the embryo diameter measurement obtained through a line that connects the most extreme points of the embryo, taking into account the diameter of the pellucid zone (Figure 3);

d) Second diameter of the pellucid zone (DZP2), which comprises the measurement of the embryo diameter obtained through a line perpendicular to the DZP1, connecting the most extreme points of the embryo and taking into account the diameter of the pellucid zone (Figure 4);

e) Embryo area (AE), with a contour that involves the entire area of the embryo (without considering the area of the pellucid area). The accuracy of this selection is important, since several information are extracted from the measurement of the area (embryo area, embryo color density, embryo circularity) (Figure 5);

f) Area of the zona pellucida (AZP), with an outline being made that involves the entire area of the embryo, being considered the area of the pellucid zone. The accuracy of this selection is important, as several information are extracted from the measurement of the area (Area of the pellucid zone, total color density, circularity of the pellucid zone) (Figure 6);

g) Area of dead cells (ACM), with an outline being made that

9/17 involves the entire area of dead cells, including both dead cells that are still attached and loose from the embryo (Figure 7);

h) Color density of the pellucid zone (DCZP), with a contour that involves only the area of the pellucid zone, not including the area of the embryo. This variable does not need to be obtained if the perivitelline space is absent, as in this specific case it can be calculated using AE (area of the embryo) and AZP (area of the pellucid zone) (Figure 8).

In a third step, the variables obtained by the computer program for image analysis are processed to serve as input to the ANN, being stored in a database.

The embryo diameter (DE) data is obtained by formula 1.

Formula 1: embryo diameter (DE)

DEI + DE2

..

The data relating to the diameter of the pellucid zone (DZP) is obtained by formula 2.

Formula 2: diameter of the pellucid zone (DZP)

DZP1 + DZP2 _DZ p = ------- 2

The data referring to the area of living cells (LCA) is obtained by formula 3.

Formula 3: ACV (Living cell area)

ACV = AE- ACM

The data referring to the color density of the embryo (DCE) is obtained by the first computer program together with the area of the

10/17 embryo (AE).

The total color density (DCTotal) data is obtained by the first computer program together with the area of the pellucid zone (AZP).

The data regarding the color density of the pellucid zone (DCZP) is obtained by the formula 4 _ (DCTotal X AZP) - (DCE x AE) _DCZP _ _____

Where:

DCZP is the average color of the pellucid zone,

DCTotal is the average color of the pellucid zone together with the embryo

AZP is the area of the zona pellucida along with that of the embryo

DCE is the average color of the embryo

AE is the area of the embryo

The embryo circularity data (EC) is obtained together with the embryo area (AE). .

The data regarding the Circularity of the zona pellucida (CZP) is obtained together with Area of the Pellucid Zone (AZP).

The data referring to the Embryonic Development Phase (EDE) is obtained by the visual morphological analysis of the embryo, with three possible values: EDE = 0.0 in the case of initial blastocyst, FDE = 0.5 in the case of blasticite and EDE = 1, 0 in the case of an expanded blastocyte, due to the morphological difference of the embryos during their pre-implantation development (from zygote to blastocyst).

The data referring to Post-copulation Days (DPC) comprises the time (in days) elapsed since the copulation of the mammal that generated the embryo. This data is relevant in order to allow the comparison between the / 17 stage that the embryo is in (EDE) and the ideal stage for the time elapsed since fertilization.

The data referring to the Relationship with the Group Average (RMG) comprises the relationship between the development phase (EDE) and the Group Average, determined by formula 5. Thus, values greater than 1 will indicate that the embryo is ahead in relation to to your group, while values less than 1 will indicate that the embryo is lagging behind your group.

Formula 5: relationship with the group average (RMG):

IT'S FROM

RMG = - _; --EDEgroup

Where:

EDE group corresponds to the average embryonic phase of all other embryos of the same harvest.

The degree of roughness or granulation of the embryos (EDG) is obtained through a macro for the computer program, allowing to identify the regions of contrast in the embryo and count these regions, in order to represent this visual characteristic numerically.

The Sharp Edges (EDG) macro uses the basic Sharpen and FindEdges operations of image analysis software, consisting of the following operations:

run (UnsharpMask ..., radius = 10 mask = 0.50);

run (FindEdges);

Afterwards, the FindMaxima option (Noise: 100; No light background) should be used.

The embryo mean diameter ratio (RDM) data is obtained by formula 6, where DE (embryo diameter) and DZP (diameter of the embryo)

12/17 pellucid zone) are obtained by means of the average between the largest and the smallest diameter, respectively for the embryo and the pellucid zone, favored by the great constancy of the diameter of the pellucid zone, when compared with that of the embryo itself.

Formula 6: average diameter ratio (RDM)

IN

RDM = —DZP

The data regarding the ratio of living cells (RCV) is obtained by formula 7.

Formula 7: ratio of living cells (RCV)

LCA

RCV = - AZP

The data referring to the Dead Cell Ratio (SPC) is obtained using formula 8. The higher the SPC value, the greater the proportion of dead cells in the embryo, which will have a negative impact on its quality.

Formula 8: ratio of dead cells (SmPC)

ACM ' ^RCM = -ÃCV

The data regarding the embryo color density ratio (RDC) is obtained using formula 9. The color of the embryo is an important factor to be analyzed, as it is directly influenced by its density of cells and how is their viability. This variable is highly dependent on the conditions in which the image was obtained. However, these variations are compensated when an embryo color relationship (DCE) is established with that of the pellucid zone (DCZP).

Formula 9: embryo color density ratio (RDC)

13/17

DRC =

DCE

DCZP

RDC values less than 1 indicate an embryo lighter than its pellucid zone, while values greater than 1 a darker embryo.

The color intensity (DCE and DCZP) is measured by averaging the brightness values for each pixel in the area in question. This value ranges from 0 for completely dark to 255 for completely white.

The data relating to the Square Circularity Ratio (RCE2) is obtained by formula 10.

Formula 10: circularity ratio (CER)

An ideal circle will have a value of 1. The closer to zero, the less the measured shape resembles a circle.

Circularity is defined as RCE = CE / CZP, where CE is the embryo's circularity and CZP is the circularity of the pellucid zone.

As the pellucid zone is constant and very circular, values close to 1 indicate high embryo circularity, while values close to 0 indicate very low circularity.

However, for the purpose of attributing different characteristics to circular or slightly circular embryos on the part of the ANN, considering that the values are always very close to 1, the RCE2 (high square ratio) is used in order to emphasize numerically small differences in circularity, where the most circular embryos continue to tend to 1.

The data regarding the embryonic quality (Q) varies on a scale of Excellent, Good, Regular and Bad, being used as

14/17 template for training the Artificial Neural Network. The RNA has 4 neurons in its output layer, each representing one of the possible quality classes (Neurons with values 0 or 1).

In a fourth step, the RNA architecture is developed, with definition of the number of layers, number of neurons in the layers, transfer functions between neurons and training functions.

The structure of a Neural Network is composed of several elements, such as the number of layers of neurons, the number of neurons in each layer, their transfer functions and the training function of the network. Although the correct determination of these factors is of paramount importance for the best development of ANN, there is no fixed protocol for determining the best architecture (Xin Yao, Yong Liu, Towards designing artificial neural networks by evolution, Applied Mathematics and Computation, Volume 91 , Issuel, April 1998, Pages 83-90, ISSN 0096-3003, 10.1016 / S0096-3003 (97) 10005-4).

The program was carried out, with a stop condition of 10,000 cycles, an interval of 5 to 20 neurons in the first and second layers, drawing of transfer functions between tansig, logsig and purelin and drawing of training functions between trainlm, trainscg and traingdx. The error was calculated with confusion matrix (percentage of erroneous classifications). The ANN developed using the backpropagation algorithm.

Thus, the best RNA architecture was obtained for this specific case, being a network with 18 neurons in the first layer and the purelin transfer function (linear function), 13 neurons in the second layer and the logsig transfer function (logistic function). THE

15/17 training function, chosen by the algorithm, was trainscg (ScaledConjugateGradientAlgorithm).

As shown in figure 9, the inputs comprise variables used to create the different ANN configurations. The computer program draws values for all variables and creates an ANN that is trained with the database defined in the third stage of the present method containing the data related to the embryos, using the division of the data in training, validation and testing according to the choice at the beginning of the program. This process occurs cyclically, with each cycle the program compares the error of the current network with the past networks, keeping the ANN with the smallest error. Once any of the stop variables are reached, the program ends the cycle and shows the best result.

Next, a graphical interface with fields is used to input the variables obtained through the image analysis program, with the standardization of the variables and a simulation with the previously trained ANN.

The RNA input variables comprise the EDE (Embryonic Development Stage), the DPC (Post-Copulation Days), the RMG (Relationship between the development stage and the Group Average), the RDM (Relationship between the average diameter of the embryo and the pellucid zone), RCV (Relationship between Living Cell area and total area), RCM (Relationship between Dead Cell area and living cell area), RDC (Embryo Color Density Relationship), RCE2 (Relationship between Circularity of the Embryo and the squared pellucid zone), EDG (Macro Sharp EDGes), RAB (Relationship between Blastocele Area and embryo area), RDCB (Relationship between Color Density of

16/17

Blastocele with embryo color density), RCB2 (Relationship between Blastocele Circularity and square embryo circularity).

The evaluation of embryonic quality by RNA can be presented by means of a bar graph, which represents each of the RNA exits (the 4 degrees of quality), the height of each bar being determined by the magnitude of the output value; and / or through a quality index, according to the highest value of the network output, the results being preferably presented as Excellent, Good, Regular and Bad; and / or a descriptive vector, which is the real RNA output vector, representing the values of the four neurons in the output layer ("Excellent," Good "," Regular "and" Bad ", respectively).

Table 1 shows the ANN results for the Test data. The ID column represents the identification of the embryo in the database. The error column was calculated by subtracting the quality provided by the RNA in relation to the quality provided as a template (embryologist evaluation), so that 0 indicates a correct answer, +1 that the RNA attributed a lower quality than the template and -1 that the RNA attributed a higher quality to the template.

TABLE 1: ANN results for the test data. The four outputs of the ANN represent the grades of quality of the analyzed embryo, being 1 (excellent), 2 (good), 3 (regular) and 4 (poor).

ID RNA outputs Quality RNA Quality Feedback Mistake 1 2 3 4 003D 0.11 0.84 0.03 0.01 2 1 1 004E 0.45 0.64 0.00 0.00 2 2 0 004F 0.83 0.10 0.01 0.01 1 2 -1 004G 0.86 0.09 0.01 0.01 1 2 -1 008C 0.53 0.40 0.11 0.00 1 1 0

17/17

008D 0.21 0.62 0.05 0.00 2 2 0 011A 0.75 0.27 0.02 0.00 1 1 0 012C 0.47 0.48 0.11 0.00 2 2 0 013G 0.84 0.13 0.01 0.00 1 1 0 015A 0.55 0.47 0.05 0.00 1 1 0 016B 0.94 0.04 0.02 0.00 1 1 0 016D 0.37 0.63 0.02 0.01 2 2 0 016E 0.74 0.07 0.21 0.00 1 1 0 017F 0.21 0.85 0.02 0.00 2 1 1 024C 0.22 0.79 0.03 0.00 2 2 0 027B 0.63 0.04 0.34 0.00 1 1 0 027J 0.00 0.20 0.18 0.90 4 3 1 028I 1.00 0.00 0.00 0.01 1 1 0 029F 0.00 0.58 0.58 0.15 2 2 0 029E 0.00 0.27 0.51 0.14 3 3 0

I 4

Claims (4)

1. METHOD FOR DETERMINING VIABILITY AND EMBRYO QUALITY characterized by understanding the steps of: a) obtaining the digital image of the embryo in the blastocyst phase; b) processing the digital image of the embryo in an image processing computer program, obtaining measurements from the selection of image points; c) obtaining the variables: c.1) first embryo diameter (DE1), which comprises the embryo diameter measurement obtained through a line that joins the most extreme points of the embryo; c.2) second embryo diameter (DE2), which comprises the embryo diameter measurement obtained through a line approximately perpendicular to the DE1 line, which connects the most extreme points of the embryo; c.3) first diameter of the pellucid zone (DZP1), which comprises the measurement of the embryo diameter obtained through a line that connects the most extreme points of the embryo, taking into account the diameter of the pellucid zone; c.4) second diameter of the pellucid zone (DZP2), which comprises the measurement of the embryo diameter obtained through a line perpendicular to the DZP1, connecting the most extreme points of the embryo and taking into account the diameter of the pellucid zone; c.5) embryo area (AE), without considering the area of the Petition 870190103570, of 10/14/2019, p. 11/26 2 I 4 obtained (DZP) obtained by the formula obtained by the formula ACV = pellucid zone; c.6) area of the zona pellucida (AZP), being considered the area of the pellucid zone; c.7) area of dead cells (ACM); c.8) color density of the pellucid zone (DCZP); d) processing of the variables obtained, to serve as input to the Artificial Neural Network, being: d.1) embryo diameter (DE) DE1 + DE2. 2 ^; d.2) diameter of the pellucid zone DZP = ^{DZPÍ + DZP2} ; d.3) living cell area (LCA) AE-ACM; d.4) embryo color density (DCE) obtained together with the embryo area (AE); d.5) total color density (DCTotal) obtained together with the area of the pellucid zone (AZP); d.6) color density of the pellucid zone (DCZP) obtained by the formula DCZP = ^{(DCTotal x AZP} >> ^{- (DCE χΛ £)} ; (AZP — Ae) d.7) embryo circularity (CE) obtained together with embryo area (AE); d.8) circularity of the zona pellucida (CZP) obtained together with Area of the Pellucid Zone (AZP); d.9) Embryonic Development (EDE) phase obtained by visual morphological analysis of the embryo, with EDE = 0.0 no by the formula DE = Petition 870190103570, of 10/14/2019, p. 12/26 3 I 4 case of initial blastocyst, FDE = 0.5 in the case of blasticite and EDE = 1.0 in the case of expanded blastocyte; d.10) Post-copulation days (DPC) comprises the time (in days) elapsed since the copulation of the mammal that generated the embryo; d.11) relationship with the group average (RMG) comprises the relationship between the development phase (EDE) and the IT'S FROM Group, determined by the formula RMG = -------; EDEgroup d.12) degree of roughness or granulation of the embryos (EDG) obtained by means of a macro for the image processing computer program; d.13) embryo mean diameter ratio (RDM) is obtained DF using the formula RDM = -; ^r DZP d.14) ratio of living cells (RCV) obtained by the formula RCV = -; AZP d.15) Dead Cell (RCM) ratio obtained using the RCM = ^^ formula; d.16) embryo color density (RDC) ratio obtained DCF through the formula RDC = ---; DCZP d.17) squared circularity ratio (RCE2) obtained by the formula RCE2 =; e) development of the Artificial Neural Network architecture, with definition of the number of layers, definition of the number of neurons in the layers, definition of the transfer functions between the neurons and definition of the training functions according to the variables presented in step d e Petition 870190103570, of 10/14/2019, p. 13/26 4 I 4 related to a template that represents the evaluation of an embiologist; f) standardization of variables and simulation with previously trained ANN, using a graphical interface with fields for input of variables obtained through the computer program for image analysis; g) evaluation of embryonic quality by Artificial Neural Network. 2. METHOD FOR DETERMINING THE FEASIBILITY AND QUALITY OF EMBRYOS, according to claim 1, characterized by the fact that the digital image of the embryo presents the pellucid zone with sharpness and the delimitation of the blastocele. 3. METHOD FOR DETERMINING VIABILITY AND EMBRYO QUALITY, according to claim 1, characterized by the fact that the assessment of embryonic quality by Artificial Neural Network is presented by means of a bar graph, which represents each of the RNA outputs, being the height of each bar determined by the magnitude of the output value; and / or through a quality index, according to the highest value of the network output, the results being preferably presented as Excellent, Good, Regular and Bad; and / or a descriptive vector, which is the real RNA output vector, representing the values of the four neurons in the output layer ("Excellent", "Good", "Regular" and "Bad", respectively).