Embryo development assessment method and device, electronic equipment and storage medium

Abstract

The invention provides an embryonic development evaluation method and device, electronic equipment and a storage medium, and relates to the technical field of assisted reproduction. The method comprises the following steps: acquiring an embryo image of a to-be-evaluated embryo, and extracting an inner cell mass image from the embryo image; traversing the internal cell cluster image, and determining a pixel distribution index corresponding to the internal cell cluster image; determining at least one feature parameter of the internal cell mass image according to a pixel distribution index corresponding to the internal cell mass image; and determining an evaluation result of the to-be-evaluated embryo according to each characteristic parameter of the inner cell mass image. According to the method, pixel traversal is carried out on an extracted internal cell cluster image to obtain position indexes of a plurality of center pixel points so as to obtain a pixel distribution index, and feature mining is carried out based on pixel relative position difference information indicated by the pixel distribution index so as to obtain multiple feature parameters capable of representing texture information of the internal cell cluster image. Therefore, the method is used for evaluating embryonic development, and the accuracy and credibility of an evaluation result are improved.

Description

Technical Field

[0001] The present application relates to the field of assisted reproductive technology, and specifically, to an embryo development assessment method, device, electronic device, and storage medium. Background Art

[0002] With the development of computer vision and assisted reproductive technology, artificial intelligence is becoming increasingly involved in the field of assisted reproduction. Embryologists are closely monitoring how computer vision can help them better understand embryonic development, select high-quality embryos for transfer, and improve clinical live birth rates.

[0003] Traditional evaluation methods only make subjective measurements based on morphological characteristics such as the size, appearance, and roundness of the inner cell mass. The evaluation basis is relatively weak, resulting in poor accuracy of the evaluation results. Summary of the Invention

[0004] The purpose of this application is to address the deficiencies in the above-mentioned prior art and provide an embryo development assessment method, device, electronic device and storage medium to improve the accuracy and credibility of embryo development result assessment.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, the present invention provides a method for evaluating embryonic development, comprising:

[0007] Acquiring an embryonic image of the embryo to be evaluated, and extracting an inner cell mass image from the embryonic image;

[0008] Traversing the inner cell mass image, determining a pixel distribution index corresponding to the inner cell mass image; the pixel distribution index includes a position index of a plurality of central pixel points, and the position index of each central pixel point is used to indicate a position difference of the central pixel point relative to surrounding pixels;

[0009] determining at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image;

[0010] An evaluation result of the embryo to be evaluated is determined based on various characteristic parameters of the inner cell mass image.

[0011] Optionally, traversing the inner cell mass image and determining a pixel distribution index corresponding to the inner cell mass image includes:

[0012] Using a preset convolution kernel to sequentially traverse the pixels in the inner cell mass image, and determining the position index of the current center pixel based on the information of each pixel in the currently traversed pixel area;

[0013] According to the position index of each central pixel point, the pixel distribution index corresponding to the inner cell mass image is obtained.

[0014] Optionally, determining the position index of the current center pixel point based on information of each pixel point in the currently traversed pixel area includes:

[0015] The position index of the center pixel point is determined based on the pixel value of the center pixel point in the currently traversed pixel area and the pixel values ​​of the surrounding pixels of the center pixel point; the center pixel point and the surrounding pixels are determined based on the coverage area of ​​the preset convolution kernel.

[0016] Optionally, determining at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image includes:

[0017] According to the position index of each central pixel point, the position index mean is determined;

[0018] Determining a first parameter according to a position index of each central pixel point and a mean value of the position index;

[0019] Determining a second parameter according to the position index of each central pixel point;

[0020] A first characteristic parameter of the inner cell mass image is determined according to the first parameter and the second parameter, where the first characteristic parameter is used to characterize the uniformity of texture distribution of the inner cell mass image.

[0021] Optionally, determining at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image includes:

[0022] According to the position index of each central pixel point, the second characteristic parameter and the third characteristic parameter of the inner cell mass image are respectively determined; the second characteristic parameter is used to characterize the overall change amplitude of the image; and the third characteristic parameter is used to characterize the stability of the image.

[0023] Optionally, determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image according to the position index of each central pixel point includes:

[0024] According to the position index of each central pixel point, the position index mean is determined;

[0025] Determining the second characteristic parameter according to the position index of each central pixel point and the mean of the position index;

[0026] The third characteristic parameter is determined according to the position index of each central pixel point and the second characteristic parameter.

[0027] Optionally, determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image according to the position index of each central pixel point includes:

[0028] Determine the sum of the position indices according to the position indices of the central pixels;

[0029] determining the second characteristic parameter according to the sum of the position indices and the number of the central pixels;

[0030] According to the position index of each central pixel point, the standard deviation of the position index and the mean of the absolute value of the position index are determined;

[0031] The third characteristic parameter is determined according to the position index standard deviation and the mean of the absolute values ​​of the position index.

[0032] Optionally, determining the evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image includes:

[0033] Inputting the characteristic parameters into a pre-established embryo scoring system, analyzing the basic characteristics of the inner cell mass image by the embryo scoring system, and determining a first subdivision grade of the embryo to be evaluated;

[0034] Analyzing basic features of the trophoblast cell image using the embryo scoring system to determine a second subdivision grade of the embryo to be evaluated;

[0035] analyzing the characteristic parameters of the inner cell mass image by the embryo scoring system to determine a third subdivision level of the embryo to be evaluated;

[0036] A scoring level of the embryo to be evaluated is determined according to the first subdivision level, the second subdivision level, and the third subdivision level.

[0037] Optionally, the method for constructing the embryo scoring system includes:

[0038] Collect various characteristic parameters of the cell cluster image in the sample;

[0039] The basic scoring system is trained based on various characteristic parameters of the cell cluster image in the sample to obtain the embryo scoring system.

[0040] Optionally, acquiring an embryonic image of the embryo to be evaluated and extracting an inner cell mass image from the embryonic image includes:

[0041] Acquiring a designated focal plane image of the embryo to be evaluated;

[0042] After data cleaning of the designated focal plane image, a segmentation algorithm is used to extract an initial inner cell mass image from the cleaned designated focal plane image;

[0043] The initial inner cell mass image is subjected to image enhancement processing using a preset algorithm to obtain the inner cell mass image.

[0044] In a second aspect, an embodiment of the present application further provides an embryonic development assessment device, comprising: a collection module, a determination module, and an assessment module;

[0045] The acquisition module is used to acquire an embryonic image of the embryo to be evaluated and extract an inner cell mass image from the embryonic image;

[0046] The determination module is configured to traverse the inner cell mass image and determine a pixel distribution index corresponding to the inner cell mass image; the pixel distribution index includes a position index of a plurality of central pixel points, and the position index of each central pixel point is used to indicate a position difference of the central pixel point relative to surrounding pixels;

[0047] The determining module is configured to determine at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image;

[0048] The evaluation module is used to determine the evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image.

[0049] Optionally, the determination module is specifically configured to sequentially traverse the pixel points in the inner cell mass image using a preset convolution kernel, and determine the position index of the current center pixel point based on information of each pixel point in the currently traversed pixel area;

[0050] According to the position index of each central pixel point, the pixel distribution index corresponding to the inner cell mass image is obtained.

[0051] Optionally, the determination module is specifically used to determine the position index of the center pixel point based on the pixel value of the center pixel point in the currently traversed pixel area and the pixel values ​​of the surrounding pixels of the center pixel point; the center pixel point and the surrounding pixels are determined according to the coverage area of ​​the preset convolution kernel.

[0052] Optionally, the determining module is specifically configured to determine a position index mean value based on the position index of each central pixel point;

[0053] Determining a first parameter according to a position index of each central pixel point and a mean value of the position index;

[0054] Determining a second parameter according to the position index of each central pixel point;

[0055] A first characteristic parameter of the inner cell mass image is determined according to the first parameter and the second parameter, where the first characteristic parameter is used to characterize the uniformity of texture distribution of the inner cell mass image.

[0056] Optionally, the determination module is specifically used to determine the second characteristic parameter and the third characteristic parameter of the inner cell mass image according to the position index of each central pixel point; the second characteristic parameter is used to characterize the overall change amplitude of the image; and the third characteristic parameter is used to characterize the stability of the image.

[0057] Optionally, the determining module is specifically configured to determine a position index mean value based on the position index of each central pixel point;

[0058] Determining the second characteristic parameter according to the position index of each central pixel point and the mean of the position index;

[0059] The third characteristic parameter is determined according to the position index of each central pixel point and the second characteristic parameter.

[0060] Optionally, the determining module is specifically configured to determine a sum of position indices based on the position indices of the central pixels;

[0061] determining the second characteristic parameter according to the sum of the position indices and the number of the central pixels;

[0062] According to the position index of each central pixel point, the standard deviation of the position index and the mean of the absolute value of the position index are determined;

[0063] The third characteristic parameter is determined according to the position index standard deviation and the mean of the absolute values ​​of the position index.

[0064] Optionally, the evaluation module is specifically configured to input the characteristic parameters into a pre-established embryo scoring system, analyze the basic characteristics of the inner cell mass image through the embryo scoring system, and determine a first subdivision level of the embryo to be evaluated;

[0065] Analyzing basic features of the trophoblast cell image using the embryo scoring system to determine a second subdivision grade of the embryo to be evaluated;

[0066] analyzing the characteristic parameters of the inner cell mass image by the embryo scoring system to determine a third subdivision level of the embryo to be evaluated;

[0067] A scoring level of the embryo to be evaluated is determined according to the first subdivision level, the second subdivision level, and the third subdivision level.

[0068] Optionally, it further includes: a building module;

[0069] The construction module is used to collect various characteristic parameters of the cell cluster image in the sample;

[0070] The basic scoring system is trained based on various characteristic parameters of the cell cluster image in the sample to obtain the embryo scoring system.

[0071] Optionally, the acquisition module is specifically used to acquire a designated focal plane image of the embryo to be evaluated;

[0072] After data cleaning of the designated focal plane image, a segmentation algorithm is used to extract an initial inner cell mass image from the cleaned designated focal plane image;

[0073] The initial inner cell mass image is subjected to image enhancement processing using a preset algorithm to obtain the inner cell mass image.

[0074] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to implement the embryonic development assessment method provided in the first aspect.

[0075] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the embryonic development assessment method provided in the first aspect is executed.

[0076] The beneficial effects of this application are:

[0077] The present application provides an embryonic development assessment method, device, electronic device, and storage medium, comprising: collecting an embryonic image of an embryo to be assessed, and extracting an inner cell mass image from the embryonic image; traversing the inner cell mass image to determine a pixel distribution index corresponding to the inner cell mass image; determining at least one feature parameter of the inner cell mass image based on the pixel distribution index corresponding to the inner cell mass image; and determining an assessment result of the embryo to be assessed based on the various feature parameters of the inner cell mass image. The method traverses the extracted inner cell mass image pixel by pixel to obtain position indices of multiple center pixels, thereby obtaining a pixel distribution index. Based on the relative position difference information of the pixels indicated by the pixel distribution index, feature mining is performed to obtain multiple feature parameters that can characterize the texture information of the inner cell mass image, which are then used to assess embryonic development, thereby improving the accuracy and credibility of the assessment results.

[0078] Secondly, by adding the above-mentioned mined features to the basic scoring system to construct an embryo scoring system, embryos can be rated more subtly based on the embryo scoring system, and based on the rating results, more accurate embryo transplantation selection priorities can be provided, providing more reliable data support for embryo transplantation. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0080] Figure 1 A schematic diagram of a process for evaluating embryonic development provided in an embodiment of the present application;

[0081] Figure 2 A schematic diagram of another method for evaluating embryonic development provided in an embodiment of the present application;

[0082] Figure 3 A schematic diagram of a process for evaluating embryonic development provided in an embodiment of the present application;

[0083] Figure 4 A schematic diagram of another method for evaluating embryonic development provided in an embodiment of the present application;

[0084] Figure 5 A schematic diagram of another method for evaluating embryonic development provided in an embodiment of the present application;

[0085] Figure 6 Schematic diagram of the differences in inner cell mass images and texture features under different scores provided in the embodiments of this application;

[0086] Figure 7 This is a schematic diagram showing the difference in the degree of aggregation of inner cell mass images under different scores provided in the embodiments of the present application;

[0087] Figure 8 A schematic diagram showing the relationship between the degree of aggregation and the clinical outcome of embryonic development provided in the examples of this application;

[0088] Figure 9 A schematic diagram of the analysis of aggregation degree and clinical outcomes provided in an embodiment of the present application;

[0089] Figure 10 A schematic diagram of the multiple comparison results of the aggregation degree of the sample scoring group with a blastocyst expansion degree of four provided in the embodiment of the present application;

[0090] Figure 11 A schematic diagram of another method for evaluating embryonic development provided in an embodiment of the present application;

[0091] Figure 12 A schematic diagram of a process for evaluating embryonic development provided in an embodiment of the present application;

[0092] Figure 13 A schematic diagram of another method for evaluating embryonic development provided in an embodiment of the present application;

[0093] Figure 14 A schematic diagram of the scoring verification results of the embryo scoring system constructed as provided in the examples of the present application;

[0094] Figure 15 Schematic diagram of embryo priority evaluated by different scoring systems provided in the embodiments of this application;

[0095] Figure 16 A schematic diagram of an embryonic development assessment device provided in an embodiment of the present application;

[0096] Figure 17 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0097] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0098] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0099] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0100] With the development of computer vision and assisted reproductive technology, artificial intelligence is increasingly influencing the field of assisted reproduction. Embryologists are closely monitoring how computer vision can help them better understand the process of embryonic development, further understand the correlation between inner cell mass morphology and clinical outcomes, improve the inner cell mass assessment system, select the highest-quality embryos for transfer, and improve clinical live birth rates.

[0101] Traditional morphological scoring (Gardner's Istanbul Consensus) subjectively measures only the size and appearance (tightness, looseness) of the inner cell mass and is not unique (embryologists may disagree on the score for the same embryo). Furthermore, the Gardner score simply categorizes embryos into different grades and does not help embryologists make further choices given the same score. Richter, KS, added the dimension of inner cell mass roundness to make blastocyst scoring unique, but its biological significance remains unexplained. Embryo scoring models trained from an artificial intelligence perspective have further improved clinical live birth rates, but the entire scoring process is opaque, and some embryologists have low confidence in the model's results.

[0102] In other words, the current evaluation dimensions of the inner cell mass (size, roundness, and appearance) are insufficient to support the selection of high-quality blastocysts. The live birth success rate of high-quality blastocysts selected by the existing system is low. Therefore, it is necessary to deepen the understanding of the inner cell mass and explore more characteristics of the inner cell mass to improve the evaluation effect.

[0103] Figure 1 This is a flow chart of an embryonic development assessment method provided in an embodiment of the present application; the execution subject of this method can be a computer device, such as Figure 1 As shown, the method may include:

[0104] S101 . Acquire an embryonic image of an embryo to be evaluated, and extract an inner cell mass image from the embryonic image.

[0105] The embryo in the time-lapse culture dish can be captured by an acquisition device to obtain multi-focal plane images of the embryo to be evaluated, and the best focal plane image where the inner cell mass is located can be selected from the multi-focal plane images.

[0106] Eleven focal plane images may be collected, and a focal plane image showing the clearest inner cell mass is selected from the 11 focal plane images, and then the inner cell mass image is extracted from the focal plane image.

[0107] S102 , traversing the inner cell mass image to determine a pixel distribution index corresponding to the inner cell mass image.

[0108] The pixel distribution index includes position indexes of multiple central pixel points, and the position index of each central pixel point is used to indicate the position difference of the central pixel point relative to the surrounding pixel points.

[0109] The pixel distribution index can be obtained by performing pixel traversal on the inner cell mass image through a window of preset size to collect the position index of multiple central pixels.

[0110] The central pixel here does not refer to the central pixel of the inner cell mass image, but rather the central pixel within the traversed pixel region. Therefore, there are multiple central pixels, each of which is assigned a position index. The position index indicates the positional difference of the central pixel relative to the surrounding pixels, thereby quantifying the relative position of the central pixel on the inner cell mass image.

[0111] S103 : Determine at least one characteristic parameter of the inner cell mass image according to the pixel distribution index corresponding to the inner cell mass image.

[0112] In some embodiments, at least one characteristic parameter of the inner cell mass image may be expanded and generated based on the pixel distribution index corresponding to the inner cell mass image obtained by the above calculation.

[0113] Since the pixel distribution index indicates the position difference of the central pixel relative to the surrounding pixels, this difference can reflect the surface texture changes of the inner cell mass image, thereby expanding the generation of texture-related feature parameters that can characterize the inner cell mass image from different angles.

[0114] S104. Determine the evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image.

[0115] The relevant characteristics of the inner cell mass are closely related to the developmental state of the embryo.

[0116] By combining the characteristic parameters of the inner cell mass image obtained above and the basic morphological parameters of the inner cell mass, a developmental assessment can be performed on the embryo to be assessed to obtain an assessment result.

[0117] In summary, the embryonic development assessment method provided by this embodiment includes: collecting an embryonic image of the embryo to be assessed, and extracting an inner cell mass image from the embryonic image; traversing the inner cell mass image to determine the pixel distribution index corresponding to the inner cell mass image; determining at least one feature parameter of the inner cell mass image based on the pixel distribution index corresponding to the inner cell mass image; and determining the assessment result of the embryo to be assessed based on the various feature parameters of the inner cell mass image. This method performs pixel traversal on the extracted inner cell mass image to obtain the position index of multiple center pixels, thereby obtaining a pixel distribution index. Based on the pixel relative position difference information indicated by the pixel distribution index, feature mining is performed to obtain multiple feature parameters that can characterize the texture information of the inner cell mass image, which are used to assess embryonic development and improve the accuracy and credibility of the assessment results.

[0118] Figure 2 A flow chart of another embryonic development assessment method provided in an embodiment of the present application; optionally, in step S102, traversing the inner cell mass image and determining the pixel distribution index corresponding to the inner cell mass image may include:

[0119] S201 , using a preset convolution kernel to sequentially traverse the pixel points in the inner cell cluster image, and determining the position index of the current center pixel point based on the information of each pixel point in the currently traversed pixel area.

[0120] In some embodiments, a convolution kernel of a preset size can be used to sequentially traverse the pixels in the inner cell mass image. Specifically, a 7*7 convolution kernel can be used for traversal. During the traversal process, the 7*7 convolution kernel needs to be fully filled with pixels, so pixels at the edge of the inner cell mass image will not be used as center pixels.

[0121] For the currently traversed pixel area, the position index of the center pixel point in the pixel area can be determined based on the pixel information of each pixel point in the pixel area. The position index of the center pixel point is related to the pixel values ​​of the center pixel point and the pixels around the center pixel point.

[0122] S202 , obtaining a pixel distribution index corresponding to the inner cell mass image according to the position index of each central pixel point.

[0123] For each central pixel point traversed, the position index of the central pixel point can be determined, and the pixel distribution index corresponding to the inner cell mass image can be obtained based on the position index of each central pixel point.

[0124] Optionally, in step S201, the position index of the current center pixel point is determined based on the information of each pixel point in the currently traversed pixel area, which may include: determining the position index of the center pixel point based on the pixel value of the center pixel point in the currently traversed pixel area and the pixel values ​​of the surrounding pixels of the center pixel point; the center pixel point and the surrounding pixels are determined based on the coverage area of ​​the preset convolution kernel.

[0125] Assume that the pixel value of the central pixel is I c , the pixel value of the surrounding pixels is I i (where i = 1, 2, ..., 48). The reason why there are 48 surrounding pixels here is that a 7*7 convolution kernel is used, and the pixel area determined by it is a 7 by 7 matrix size. All pixels except the central pixel are regarded as the surrounding pixels of the central pixel.

[0126] Then, the position index of the center pixel can be calculated using the following formula:

[0127]

[0128] Among them, I c Represents the pixel value of the center pixel, I i Represents the pixel values ​​of the surrounding pixels. TPI is the position index of the central pixel.

[0129] By traversing the inner cell mass image, the TPI of all central pixels can be calculated to obtain the pixel distribution index {TPI1, TPI2, ..., TPI n}, where n represents the number of central pixels.

[0130] Figure 3 A flow chart of another embryonic development assessment method provided in an embodiment of the present application; optionally, in step S103, determining at least one characteristic parameter of the inner cell mass image based on a pixel distribution index corresponding to the inner cell mass image may include:

[0131] S301 : Determine a position index mean value based on the position index of each central pixel point.

[0132] Optionally, the position index of each central pixel can be averaged to obtain the position index mean

[0133] S302: Determine a first parameter according to the position index of each central pixel point and the average of the position indices.

[0134] The first parameter can be calculated using the following formula:

[0135]

[0136] Among them, |TPI j | represents the absolute value of the position index of the center pixel value, that is, represents the variance of the absolute value of the position index, This is the first parameter.

[0137] S303: Determine a second parameter according to the position index of each central pixel point.

[0138] The second parameter can be calculated using the following formula:

[0139]

[0140] S TPI Refers to the sum of the absolute values ​​of the position indices, S TPI This is the second parameter.

[0141] S304: Determine a first characteristic parameter of the inner cell mass image according to the first parameter and the second parameter.

[0142] The first characteristic parameter is used to characterize the uniformity of texture distribution of the inner cell mass image.

[0143] The following formula can be used to calculate the first characteristic parameter:

[0144]

[0145] Among them, ε takes the minimum value to avoid the denominator being 0.

[0146] The first characteristic parameter may refer to the degree of aggregation. The degree of aggregation is proportional to the density of the inner cell mass. The greater the degree of aggregation, the greater the density of the inner cell mass.

[0147] Optionally, in step S103, at least one characteristic parameter of the inner cell mass image is determined based on the pixel distribution index corresponding to the inner cell mass image, including: determining a second characteristic parameter and a third characteristic parameter of the inner cell mass image based on the position index of each central pixel point; the second characteristic parameter is used to characterize the overall change amplitude of the image; and the third characteristic parameter is used to characterize the stability of the image.

[0148] In some embodiments, a total variation (TV) can be defined to measure the overall variation of the inner cell mass image. The TV is also the second characteristic parameter.

[0149] Texture Uniformity (TU) can also be defined to measure whether the changes in the inner cell mass image are uniform, that is, to measure the stability of the changes. Uniformity is also known as the third characteristic parameter.

[0150] Figure 4 A flow chart of another embryonic development assessment method provided in an embodiment of the present application; optionally, in the above steps, determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image based on the position index of each central pixel point may include:

[0151] S401 : Determine a position index mean value based on the position index of each central pixel point.

[0152] In one implementation, the average value of the position indexes of the central pixels may be calculated first to obtain the position index mean.

[0153] S402: Determine a second characteristic parameter according to the position index of each central pixel point and the mean value of the position index.

[0154] Then, the second characteristic parameter TV is first determined by combining the position index of each central pixel point and the average value of the position index.

[0155] The second characteristic parameter TV can be calculated using the following formula:

[0156]

[0157] Among them, |TPI j | represents the absolute value of the position index, Represents the location index mean.

[0158] S403: Determine a third characteristic parameter according to the position index of each central pixel point and the second characteristic parameter.

[0159] Then, based on the position index of each central pixel point and the second characteristic parameter TV, the third characteristic parameter is determined.

[0160] Next, the third characteristic parameter TU can be calculated using the following formula:

[0161]

[0162] Among them, S TPI This is the second parameter mentioned above.

[0163] In this implementation, analysis reveals that:

[0164] 1. Large and uniform image changes (large TV and large TU): Typical cases: clear and regular textures, such as the inner cell mass in the fusion stage;

[0165] 2. Large and uneven image changes (large TV, small TU): Typical cases: chaotic and unstable textures, such as abnormal inner cell clusters;

[0166] 3. Small and uneven image changes (small TV, small TU): Typical cases: blur, random noise, such as low-quality cell clusters;

[0167] 4. Image changes are small and uniform (small TV, large TU): Typical case: smooth, such as the inner cell mass that is considered to have better fusion and greater potential.

[0168] Figure 5 A flow chart of another embryonic development assessment method provided in an embodiment of the present application; optionally, in the above steps, determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image based on the position index of each central pixel point may include:

[0169] S501 : Determine the sum of position indices according to the position indices of the central pixels.

[0170] In another implementation, the position index sum S can be obtained by first calculating the sum of the absolute values ​​of the position indices according to the position indices of the central pixels. TPI , the sum of the position indices S tPI Same as the second parameter above.

[0171] S can be calculated using the following formula TPI :

[0172]

[0173] S502: Determine a second characteristic parameter according to the sum of the position indices and the number of central pixels.

[0174] The second characteristic parameter TV can be calculated using the following formula:

[0175]

[0176] Here, n refers to the number of central pixels.

[0177] S503 : Determine the standard deviation of the position index and the mean of the absolute value of the position index according to the position index of each central pixel point.

[0178] S504: Determine a third characteristic parameter according to the standard deviation of the position index and the mean of the absolute value of the position index.

[0179] The third characteristic parameter TU can be calculated using the following formula:

[0180]

[0181] Among them, σ TPI represents the position index standard deviation, Represents the mean of the absolute values ​​of the position indices; a decimal ε is added here to avoid the denominator being 0.

[0182] In this implementation, analysis reveals that:

[0183] 1. The image changes greatly but evenly (large TV and large TU): The overall changes are dramatic, but the local changes are consistent.

[0184] 2. The image changes greatly and unevenly (large TV and small TU): The overall change is drastic, but there are large differences in local changes.

[0185] 3. The image changes are small and uneven (small TV, small TU): The overall change is small, but there is uneven distribution locally.

[0186] 4. The image changes are small and uniform (small TV, large TU): The overall change is small and the local changes are also relatively uniform.

[0187] It is worth noting that the second characteristic parameter TV mentioned above represents the overall change amplitude of the image. The larger the TV, the greater the overall change of the image. The third characteristic parameter TU represents the stability of the change and is used to measure whether the change is uniform. The larger the TU, the more uniform the image change.

[0188] Through the characteristic parameters obtained above, correlation analysis between the characteristic parameters and embryo development results can be performed.

[0189] Figure 6 This is a schematic diagram of the difference in inner cell mass image and texture features under different scores provided in the embodiment of this application. Figure 6 (a) is a sample example of the inner cell mass with a score of A; Figure 6 (b) in Figure 6 shows an example of an inner cell mass image with a score of B. Taking (a) in Figure 6 as an example, the first column represents the original embryo image, the second column represents the inner cell mass image after image enhancement, and the third column represents the texture feature image of the inner cell mass image. The depth of the image color is used to represent the texture variation of the inner cell mass image, with brighter colors indicating greater texture variation.

[0190] Looking at the overall texture characteristics of the inner cell mass images, those rated A showed a relatively greater and more uniform total grayscale variation on the surface; whereas those rated B showed a relatively smaller and less uniform grayscale variation on the surface texture. This is consistent with the calculation principle of the degree of aggregation, which states that the degree of aggregation is proportional to the density of the inner cell mass. Data verification revealed that inner cell masses rated A had a higher degree of aggregation.

[0191] Figure 7This is a schematic diagram of the difference in the degree of aggregation of inner cell mass images under different scores provided in the embodiment of the present application. It can be seen that the degree of aggregation of inner cell mass with score A is greater than that of inner cell mass with score B.

[0192] Figure 8 Schematic diagram of the relationship between the degree of aggregation and the clinical outcome of embryonic development provided in the examples of this application. Figure 8 (a) shows the relationship between the degree of aggregation and clinical pregnancy rate; Figure 8 (b) shows the relationship between the degree of aggregation and clinical live birth rate; Figure 8 (c) in the figure shows the relationship between the degree of aggregation and the clinical miscarriage rate.

[0193] It can be seen that the greater the degree of aggregation, the more uniform the texture of the inner cell mass, the higher the clinical pregnancy rate and clinical live birth rate of the embryo, and the degree of aggregation does not show a relationship with the clinical miscarriage rate.

[0194] Figure 9 A schematic diagram of the analysis of aggregation degree and clinical outcomes provided in an embodiment of the present application.

[0195] In order to improve the convenience of clinical use, the degree of aggregation can be divided into two categories, and the optimal threshold is determined to be 3241. According to this threshold, samples with an aggregation degree greater than 3241 are defined as "good aggregation" and scored A; samples with an aggregation degree less than 3241 are defined as "poor aggregation" and scored B. The analysis results show that there is a significant correlation between pregnancy rate and live birth rate. Figure 9 Embryos with an aggregation score of A (good aggregation) had a higher clinical pregnancy rate (65.23% VS 61.07%, p < 0.05) and clinical live birth rate (51.52% VS 46.38%, p < 0.05) than embryos with an aggregation score of B (poor aggregation), but no significant difference was found in the clinical miscarriage rate.

[0196] Figure 10 This is a schematic diagram of the multiple comparison results of the aggregation degree of the sample scoring group with a blastocyst expansion degree of four provided in the embodiment of the present application.

[0197] In the clinical data, the expansion samples accounted for 92.7% of the blastocyst stage 4 (the size of the inner cell mass in the blastocyst at this stage is within a certain range, and there are more samples at this stage). Therefore, this embodiment takes the blastocyst sample with an expansion degree of 4 as an example. By analyzing the blastocysts scored 4AA, 4AB, 4AC, 4BA, 4BB and 4BC, we found that the overall aggregation degree of the blastocysts of 4AA and 4AB was higher than that of the stage 4 blastocysts of various types of inner cell mass 4BX (p<0.05), the aggregation degree of 4AC blastocysts was greater than that of 4BC blastocysts (p<0.05), and there was a significant difference in the densification between the inner cell masses of different grades.

[0198] Notably, within embryos of the same inner cell mass grade, there was no significant difference in the degree of clustering among the 4AX groups. However, within the 4BX groups, the degree of clustering of the 4BB group was significantly higher than that of the 4BA and 4BC groups (p < 0.05). The significant differences in inner cell mass compaction between blastocysts from different 4BX groups indicate that there is greater variation in compaction among blastocysts with poor inner cell mass quality, suggesting that the large number of blastocysts of the same grade with relatively low inner cell mass quality that appear in clinical practice deserve further grading. In particular, within the 4BB group, there may be some blastocysts with higher clinical potential than 4BA blastocysts.

[0199] It should be noted that, taking 4AA as an example, 4 represents an expansion degree of 4, the first A represents the score of the inner cell mass, and the second A represents the score of the trophoblast cells. In this embodiment, the two-level score is used as the final score.

[0200] Therefore, by adding the degree of aggregation, total variation and uniformity of the inner cell mass to the basic scoring system, a new embryo scoring system can be constructed to further subdivide the embryo scoring, for example, the 4AA score can be subdivided into 4AA-A, 4AA-B, 4AA-C, etc.

[0201] Figure 11 A schematic flow chart of another embryo development assessment method provided in an embodiment of the present application; optionally, in step S104, determining the assessment result of the embryo to be assessed based on various characteristic parameters of the inner cell mass image may include:

[0202] S601: Input various characteristic parameters into a pre-built embryo scoring system, analyze the basic characteristics of the inner cell mass image through the embryo scoring system, and determine the first subdivision level of the embryo to be evaluated.

[0203] In some embodiments, various characteristic parameters of the extracted inner cell mass image can be input into a pre-built embryo scoring system to perform developmental scoring on the embryo to be evaluated.

[0204] The embryo scoring system can be developed by training a traditional scoring system by incorporating the aforementioned characteristic parameters of sample images. This system integrates assessments of various characteristics, such as the degree of inner cell mass aggregation, total variation, and uniformity, to improve the accuracy of scoring results.

[0205] Optionally, the embryo scoring system can obtain a first subdivision level by analyzing the basic features of the inner cell mass image. The first subdivision level can refer to a level evaluated based on the morphological features of the inner cell mass image, such as the size, appearance, roundness and other features of the inner cell mass.

[0206] S602: Analyze the basic features of the trophoblast cell image using the embryo scoring system to determine a second subdivision level of the embryo to be evaluated.

[0207] Similarly, the basic features of the trophoblast cell image can be analyzed by the embryo scoring system to obtain a second subdivision level, which is also the scoring level for the trophoblast cell image.

[0208] The first segmentation level and the second segmentation level can both be scored based on a traditional scoring system.

[0209] S603: Analyze various characteristic parameters of the inner cell mass image using the embryo scoring system to determine the third subdivision level of the embryo to be evaluated.

[0210] Based on an embryo scoring system that incorporates various features of the inner cell mass, such as the degree of inner cell mass aggregation, total variation, and uniformity, these characteristic parameters of the inner cell mass image can be analyzed to determine the third subdivision level of the embryo being evaluated. This third subdivision level is based on an assessment of the inner cell mass's texture characteristics. This third subdivision level cannot be derived from a traditional scoring system; instead, it is assessed using an embryo scoring system developed by training the traditional scoring system with the aforementioned characteristic parameters.

[0211] S604: Determine the scoring level of the embryo to be evaluated according to the first subdivision level, the second subdivision level, and the third subdivision level.

[0212] Combining the first, second, and third subdivision levels, the embryo score can be obtained. For example, the embryo score can be AAB, where the first A refers to the first subdivision level, the second A refers to the second subdivision level, and the third B refers to the third subdivision level.

[0213] Traditional scoring systems can only evaluate the first and second sub-levels at most. The embryo scoring system constructed by this method can provide a more detailed analysis to obtain the third sub-level.

[0214] Figure 12 A schematic flow chart of another embryo development assessment method provided in an embodiment of the present application; optionally, the method for constructing the embryo scoring system in step S601 may include:

[0215] S701. Collect various characteristic parameters of the cell cluster image in the sample.

[0216] The first characteristic parameter (aggregation degree), the second characteristic parameter (TV), and the third characteristic parameter (TU) of the cell cluster image in the sample may be collected.

[0217] S702: Based on various characteristic parameters of the cell cluster images in the sample, a basic scoring system is trained to obtain an embryo scoring system.

[0218] The various characteristic parameters of the cell cluster images collected in the samples are added as new characteristic data to the original training sample data of the basic scoring system to train an embryo scoring system.

[0219] The basic scoring system here is the traditional scoring system mentioned above.

[0220] Figure 13 A schematic flow chart of another embryonic development assessment method provided in an embodiment of the present application; in step S101, an embryonic image of the embryo to be assessed is acquired, and an inner cell mass image is extracted from the embryonic image, which may include:

[0221] S801. Acquire a designated focal plane image of the embryo to be evaluated.

[0222] Multiple focal plane images of the embryo to be evaluated can be acquired. As mentioned above, the multiple focal planes can include 11 focal plane images, and then the focal plane image with the clearest inner cell mass observation field is selected from the 11 focal plane images as the designated focal plane image.

[0223] S802 , after data cleaning of the designated focal plane image, a segmentation algorithm is used to extract the initial inner cell mass image from the cleaned designated focal plane image.

[0224] Data cleaning can be performed on the specified focal plane image, and then the initial inner cell mass image can be extracted from it using an image segmentation algorithm.

[0225] S803 , performing image enhancement processing on the initial inner cell mass image using a preset algorithm to obtain an inner cell mass image.

[0226] Then, the initial inner cell mass image is preprocessed, including but not limited to image enhancement processing, to reduce the negative impact of illumination on feature extraction, thereby reducing errors in image feature extraction.

[0227] In this embodiment, an adaptive histogram equalization method may be used to perform image enhancement processing on the initial inner cell mass image to improve feature extraction errors caused by exposure.

[0228] Figure 14 This is a schematic diagram of the scoring validation results of the constructed embryo scoring system provided in the examples of this application. The horizontal axis represents the 12 groups of the embryo scoring system, with the priority of the predicted scores decreasing from left to right. The vertical axis represents the five scoring groups, and the scale corresponding to each group represents the clinical pregnancy rate or live birth rate.

[0229] Based on the embryo scoring system constructed in this example, we found that the embryo scoring system can not only prioritize embryos with the same rating, but also prioritize embryos across groups. In the embryo scoring system, the 4AA-A group had the highest clinical pregnancy rate and live birth rate, followed by the 4AA-B group; closely followed by the 4BA-A and 4AB-A groups, although the differences between the two groups were smaller. A notable finding was that the clinical pregnancy rate and live birth rate of the 4BB-A group were significantly higher than those of the 4BA-B and 4AB-B groups. In other words, in the 4BB group, approximately 38% of blastocysts (4BB-A) should be prioritized for transfer.

[0230] Although the clinical potential of blastocysts in the 4BC-A and 4BC-B groups was low, the embryo scoring system was still able to distinguish individuals with higher clinical potential (4BC-A, accounting for approximately 28%). This refined classification provides an objective, data-driven basis for embryo selection, especially when the basic scoring system cannot distinguish potential outcomes. Due to the relatively small amount of data and considering the randomness of the results, we performed a five-fold cross-validation to analyze the performance of each training set, such as Figure 14 As shown in the figure, this phenomenon was found to be consistent in all five training sets, and the average AUC of the embryo scoring system for clinical pregnancy and live birth in the test set samples was 0.5724 and 0.5588.

[0231] Figure 15 This is a schematic diagram of the embryo priorities evaluated by different scoring systems provided in the examples of this application. The horizontal axis represents the different scoring systems, and the vertical axis 1-12 represents the priority order, with 1 being the first choice and 12 being the last choice.

[0232] We compared our constructed embryo scoring system with the basic scoring system along two dimensions: content and performance. The embryo scoring system is more precise in detail, further subdividing each existing scoring level. A blastocyst with an expansion degree of 4 is assigned 6 levels in the basic scoring system, while in this embodiment's embryo scoring system, it is assigned 12 levels. Regarding blastocyst selection strategy, the basic scoring system predicts the following blastocyst priorities: 4AA, followed by 4AB, 4BA, 4BB, 4AC, and 4BC. The embryo scoring system of this embodiment predicts the following blastocyst priorities: 4AA-A, 4AA-B, 4BA-A, 4AB-A, 4BB-A, 4BA-B, 4AB-B, 4BB-B, 4AC-A, 4AC-B, 4BC-A, and 4BC-B.

[0233] Compared with the basic scoring system, the embryo scoring system constructed in this example recommends giving priority to 4BB-A rather than 4BA-B or 4BC-B for embryo transfer.

[0234] In summary, the embodiments of the present application provide a method for evaluating embryonic development, comprising: collecting an embryonic image of an embryo to be evaluated, and extracting an inner cell mass image from the embryonic image; traversing the inner cell mass image to determine a pixel distribution index corresponding to the inner cell mass image; determining at least one feature parameter of the inner cell mass image based on the pixel distribution index corresponding to the inner cell mass image; and determining an evaluation result of the embryo to be evaluated based on the various feature parameters of the inner cell mass image. This method performs pixel traversal on the extracted inner cell mass image to obtain position indices of multiple center pixel points, thereby obtaining a pixel distribution index. Based on the pixel relative position difference information indicated by the pixel distribution index, feature mining is performed to obtain multiple feature parameters that can characterize the texture information of the inner cell mass image, thereby being used to evaluate embryonic development, thereby improving the accuracy and credibility of the evaluation results.

[0235] Secondly, by adding the above-mentioned mined features to the basic scoring system to construct an embryo scoring system, embryos can be rated more subtly based on the embryo scoring system, and based on the rating results, more accurate embryo transplantation selection priorities can be provided, providing more reliable data support for embryo transplantation.

[0236] The following describes the apparatus, equipment, storage medium, etc. used to implement the embryonic development assessment method provided in this application. The specific implementation process and technical effects are described above and will not be repeated below.

[0237] Figure 16This is a schematic diagram of an embryonic development assessment device provided in an embodiment of the present application. The functions implemented by the embryonic development assessment device correspond to the steps performed by the above method. The device can be understood as the above server, or the processor of the server, or as a component independent of the above server or processor that implements the functions of the present application under the control of the server, such as Figure 16 As shown, the apparatus may include: a collection module 160, a determination module 161, and an evaluation module 162;

[0238] an acquisition module 160 for acquiring an embryonic image of the embryo to be evaluated and extracting an inner cell mass image from the embryonic image;

[0239] A determination module 161 is configured to traverse the inner cell mass image and determine a pixel distribution index corresponding to the inner cell mass image; the pixel distribution index includes a position index of a plurality of central pixel points, and the position index of each central pixel point is used to indicate a position difference of the central pixel point relative to surrounding pixels;

[0240] a determination module 161 for determining at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image;

[0241] The evaluation module 162 is configured to determine an evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image.

[0242] Optionally, the determination module 161 is specifically configured to sequentially traverse the pixels in the inner cell mass image using a preset convolution kernel, and determine the position index of the current center pixel based on information of each pixel in the currently traversed pixel area;

[0243] According to the position index of each central pixel point, the pixel distribution index corresponding to the inner cell mass image is obtained.

[0244] Optionally, the determination module 161 is specifically used to determine the position index of the center pixel point based on the pixel value of the center pixel point in the currently traversed pixel area and the pixel values ​​of the surrounding pixels of the center pixel point; the center pixel point and the surrounding pixels are determined according to the coverage area of ​​the preset convolution kernel.

[0245] Optionally, the determination module 161 is specifically configured to determine a position index mean value based on the position index of each central pixel point;

[0246] Determine a first parameter based on a position index of each central pixel point and a mean of the position indices;

[0247] Determining a second parameter according to the position index of each central pixel point;

[0248] A first characteristic parameter of the inner cell mass image is determined according to the first parameter and the second parameter, where the first characteristic parameter is used to characterize the uniformity of texture distribution of the inner cell mass image.

[0249] Optionally, the determination module 161 is specifically configured to determine a second characteristic parameter and a third characteristic parameter of the inner cell mass image according to the position index of each central pixel point; the second characteristic parameter is used to characterize the overall variation amplitude of the image; and the third characteristic parameter is used to characterize the stability of the image.

[0250] Optionally, the determination module 161 is specifically configured to determine a position index mean value based on the position index of each central pixel point;

[0251] Determine a second characteristic parameter based on the position index of each central pixel point and the mean of the position index;

[0252] The third characteristic parameter is determined according to the position index of each central pixel point and the second characteristic parameter.

[0253] Optionally, the determination module 161 is specifically configured to determine a sum of position indices based on the position indices of the central pixels;

[0254] Determine a second characteristic parameter according to the sum of the position indices and the number of central pixels;

[0255] According to the position index of each central pixel point, the standard deviation of the position index and the mean of the absolute value of the position index are determined;

[0256] The third characteristic parameter is determined according to the standard deviation of the position index and the mean of the absolute values ​​of the position index.

[0257] Optionally, the evaluation module 162 is specifically configured to input various characteristic parameters into a pre-established embryo scoring system, analyze basic characteristics of the inner cell mass image through the embryo scoring system, and determine a first subdivision level of the embryo to be evaluated;

[0258] The basic features of the trophoblast cell image are analyzed by the embryo scoring system to determine the second subdivision grade of the embryo to be evaluated;

[0259] The embryo scoring system is used to analyze the characteristic parameters of the inner cell mass image to determine the third subdivision level of the embryo to be evaluated;

[0260] The scoring level of the embryo to be evaluated is determined according to the first subdivision level, the second subdivision level and the third subdivision level.

[0261] Optionally, it further includes: a building module;

[0262] A construction module is used to collect various characteristic parameters of the cell cluster image in the sample;

[0263] Based on the characteristic parameters of the cell cluster images in the sample, the basic scoring system is trained to obtain the embryo scoring system.

[0264] Optionally, the acquisition module 160 is specifically configured to acquire a designated focal plane image of the embryo to be evaluated;

[0265] After data cleaning of the designated focal plane image, a segmentation algorithm is used to extract the initial inner cell mass image from the cleaned designated focal plane image;

[0266] The initial inner cell mass image is enhanced using a preset algorithm to obtain an inner cell mass image.

[0267] The above-mentioned device is used to execute the method provided in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0268] The above modules can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), one or more digital singnal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0269] The above modules can be connected or communicate with each other via a wired connection or a wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may include a connection in the form of a LAN, a WAN, Bluetooth, ZigBee, or NFC, or any combination thereof. Two or more modules can be combined into a single module, and any module can be divided into two or more units. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application.

[0270] Figure 17This is a structural diagram of an electronic device provided in an embodiment of the present application. The device can be integrated into a terminal device or a chip of a terminal device. The terminal can be a computing device with data processing capabilities.

[0271] The device includes: a processor 801 and a storage medium 802 .

[0272] The storage medium 802 is used to store programs, and the processor 801 calls the programs stored in the storage medium 802 to execute the above method embodiment. The specific implementation methods and technical effects are similar and will not be repeated here.

[0273] Among them, the storage medium 802 stores program code, and when the program code is executed by the processor 801, the processor 801 executes the various steps of the embryo development assessment method according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0274] The processor 801 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.

[0275] Storage medium 802 is a kind of non-volatile computer readable storage medium, which can be used for storing non-volatile software programs, non-volatile computer executable programs and modules. Storage medium can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card type storage medium, random access storage medium (Random Access Memory, RAM), static random access storage medium (Static Random Access Memory, SRAM), programmable read-only storage medium (Programmable Read Only Memory, PROM), read-only storage medium (Read Only Memory, ROM), electrically erasable programmable read-only storage medium (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic storage medium, disk, optical disk, etc. Storage medium is any other medium that can be used to carry or store desired program code with instruction or data structure form and can be accessed by computer, but is not limited to this. The storage medium 802 in the embodiment of the present application can also be a circuit or other arbitrarily capable of realizing storage function, for storing program instructions and / or data.

[0276] Optionally, the present application also provides a program product, such as a computer-readable storage medium, comprising a program, which is used to perform the above method embodiment when executed by a processor.

[0277] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0278] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0279] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0280] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor (English: processor) to execute some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only storage medium (English: Read-Only Memory, abbreviated: ROM), a random access storage medium (English: Random Access Memory, abbreviated: RAM), a disk or an optical disk, and other media that can store program code.

Claims

1. A method for evaluating embryonic development, characterized in that: include: Acquiring an embryonic image of the embryo to be evaluated, and extracting an inner cell mass image from the embryonic image; Traversing the inner cell mass image, determining a pixel distribution index corresponding to the inner cell mass image; the pixel distribution index includes a position index of a plurality of central pixel points, and the position index of each central pixel point is used to indicate a position difference of the central pixel point relative to surrounding pixels; determining at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image; An evaluation result of the embryo to be evaluated is determined based on various characteristic parameters of the inner cell mass image.

2. The method according to claim 1, characterized in that The traversing the inner cell mass image and determining a pixel distribution index corresponding to the inner cell mass image includes: Using a preset convolution kernel to sequentially traverse the pixels in the inner cell mass image, and determining the position index of the current center pixel based on the information of each pixel in the currently traversed pixel area; According to the position index of each central pixel point, the pixel distribution index corresponding to the inner cell mass image is obtained.

3. The method according to claim 2, characterized in that The determining of the position index of the current center pixel point based on the information of each pixel point in the currently traversed pixel area includes: The position index of the center pixel point is determined based on the pixel value of the center pixel point in the currently traversed pixel area and the pixel values ​​of the surrounding pixels of the center pixel point; the center pixel point and the surrounding pixels are determined based on the coverage area of ​​the preset convolution kernel.

4. The method according to claim 1, wherein Determining at least one characteristic parameter of the inner cell mass image according to the pixel distribution index corresponding to the inner cell mass image includes: According to the position index of each central pixel point, the position index mean is determined; Determining a first parameter according to a position index of each central pixel point and a mean value of the position indices; Determining a second parameter according to the position index of each central pixel point; A first characteristic parameter of the inner cell mass image is determined according to the first parameter and the second parameter, where the first characteristic parameter is used to characterize the uniformity of texture distribution of the inner cell mass image.

5. The method according to claim 1, wherein Determining at least one characteristic parameter of the inner cell mass image according to the pixel distribution index corresponding to the inner cell mass image includes: According to the position index of each central pixel point, the second characteristic parameter and the third characteristic parameter of the inner cell mass image are respectively determined; the second characteristic parameter is used to characterize the overall change amplitude of the image; and the third characteristic parameter is used to characterize the stability of the image.

6. The method according to claim 5, characterized in that Determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image according to the position index of each central pixel point includes: According to the position index of each central pixel point, the position index mean is determined; Determining the second characteristic parameter according to the position index of each central pixel point and the mean of the position index; The third characteristic parameter is determined according to the position index of each central pixel point and the second characteristic parameter.

7. The method according to claim 5, characterized in that Determining the second characteristic parameter and the third characteristic parameter of the inner cell mass image according to the position index of each central pixel point includes: Determine the sum of the position indices according to the position indices of the central pixels; determining the second characteristic parameter according to the sum of the position indices and the number of the central pixels; According to the position index of each central pixel point, the standard deviation of the position index and the mean of the absolute value of the position index are determined; The third characteristic parameter is determined according to the position index standard deviation and the mean of the absolute values ​​of the position index.

8. The method according to claim 1, characterized in that Determining the evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image includes: Inputting the characteristic parameters into a pre-established embryo scoring system, analyzing the basic characteristics of the inner cell mass image by the embryo scoring system, and determining a first subdivision grade of the embryo to be evaluated; Analyzing basic features of the trophoblast cell image using the embryo scoring system to determine a second subdivision grade of the embryo to be evaluated; analyzing the characteristic parameters of the inner cell mass image by the embryo scoring system to determine a third subdivision level of the embryo to be evaluated; A scoring level of the embryo to be evaluated is determined according to the first subdivision level, the second subdivision level, and the third subdivision level.

9. The method according to claim 8, characterized in that The method for constructing the embryo scoring system comprises: Collect various characteristic parameters of the cell cluster image in the sample; The basic scoring system is trained based on various characteristic parameters of the cell cluster image in the sample to obtain the embryo scoring system.

10. The method according to claim 1, characterized in that The step of acquiring an embryonic image of an embryo to be evaluated and extracting an inner cell mass image from the embryonic image comprises: Acquiring a designated focal plane image of the embryo to be evaluated; After data cleaning of the designated focal plane image, a segmentation algorithm is used to extract an initial inner cell mass image from the cleaned designated focal plane image; The initial inner cell mass image is subjected to image enhancement processing using a preset algorithm to obtain the inner cell mass image.

11. An embryonic development assessment device, characterized in that: include: Acquisition module, determination module and evaluation module; The acquisition module is used to acquire an embryonic image of the embryo to be evaluated and extract an inner cell mass image from the embryonic image; The determination module is configured to traverse the inner cell mass image and determine a pixel distribution index corresponding to the inner cell mass image; the pixel distribution index includes a position index of a plurality of central pixel points, and the position index of each central pixel point is used to indicate a position difference of the central pixel point relative to surrounding pixels; The determining module is configured to determine at least one characteristic parameter of the inner cell mass image according to a pixel distribution index corresponding to the inner cell mass image; The evaluation module is used to determine the evaluation result of the embryo to be evaluated based on various characteristic parameters of the inner cell mass image.

12. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the program instructions to implement the embryo development assessment method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which is used to implement the embryo development assessment method according to any one of claims 1 to 10 when executed by a processor.

Images