An intelligent identification method and system for zebrafish osteoporosis model

Abstract

The present invention provides an intelligent identification method and system for a zebrafish osteoporosis model, which relates to the technical field of bioinformatics and artificial intelligence. The method comprises: capturing an overall image of a zebrafish by a high-resolution camera or a microscope; preprocessing the captured image to obtain a preprocessed image; using image processing technology to extract the skeletal features of the zebrafish, including skeletal density, morphology and structure, according to the preprocessed overall image; segmenting and locating the cells and heart region of the zebrafish in the captured overall image to obtain a static cell image and a heart image; and performing morphological analysis on the cell image to obtain a cell analysis result. The present invention can comprehensively evaluate and accurately identify the osteoporosis condition of zebrafish by comparing the skeletal features, cell analysis results, heart analysis results and the physiological state of the zebrafish with the characteristic indicators of the osteoporosis model.

Description

Technical Field

[0001] The present invention relates to the technical field of bioinformatics and artificial intelligence, and in particular to an intelligent identification method and system for a zebrafish osteoporosis model. Background Art

[0002] As a small freshwater fish, zebrafish has the advantages of fast reproduction, clear genetic background, easy breeding and observation. In addition, its bone development and metabolic processes are highly similar to those of humans, making zebrafish an ideal model for studying the pathogenesis of osteoporosis and exploring treatment methods. However, traditional research methods have many limitations when studying zebrafish osteoporosis. These methods often rely on manual observation and data analysis, which is not only time-consuming and labor-intensive, but also difficult to fully and accurately capture the multi-dimensional information of zebrafish osteoporosis.

[0003] Manual observation is limited by the subjectivity and experience of the observer, and it is difficult to conduct a comprehensive and objective assessment of zebrafish bone morphology, cell dynamics, and cardiac function. At the same time, the data analysis process is often cumbersome and complex, requiring a lot of time and effort. More importantly, these methods find it difficult to simultaneously consider multiple dimensions of information such as bone characteristics, cell analysis results, cardiac analysis results, and physiological status, and thus cannot fully and accurately reflect the true condition of zebrafish osteoporosis. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an intelligent identification method and system for a zebrafish osteoporosis model. By comparing bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish with the characteristic indicators of the osteoporosis model, the osteoporosis condition of zebrafish can be comprehensively evaluated and accurately identified.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, an intelligent identification method for a zebrafish osteoporosis model is provided, the method comprising:

[0007] Capture whole-body images of zebrafish using high-resolution cameras or microscopes;

[0008] Preprocessing the captured image to obtain a preprocessed image;

[0009] Based on the pre-processed overall image, image processing technology is used to extract the zebrafish's bone features, including bone density, morphology and structure;

[0010] In the captured whole image, the cells and heart regions of the zebrafish are segmented and located to obtain static cell images and heart images;

[0011] Perform morphological analysis on the cell images to obtain cell analysis results;

[0012] Perform grayscale and morphological analysis on the cardiac image to obtain cardiac analysis results;

[0013] The osteoporosis status of zebrafish was identified based on the bone characteristics, cell analysis results, heart analysis results and the physiological status of zebrafish.

[0014] Further, the captured image is preprocessed to obtain a preprocessed image, including:

[0015] Acquire images of zebrafish under a microscope;

[0016] The zebrafish images were passed through Processing to obtain the filtered image, where Indicates that after filtering, the coordinate The pixel value at is the filter kernel (also called convolution kernel) at position The weight value at and Indicates the size range of the filter kernel, Represents the image at coordinates The pixel value at ;

[0017] The preprocessed image is obtained by adjusting the contrast and brightness of the filtered image and performing color correction on the adjusted image.

[0018] Further, based on the pre-processed overall image, image processing technology is used to extract the skeletal features of zebrafish, including bone density, morphology and structure, including:

[0019] Performing feature recognition training on the convolutional neural network using the labeled training data set to obtain a trained convolutional neural network;

[0020] According to the trained convolutional neural network, the preprocessed images are recognized and classified to extract the skeletal features of zebrafish, including bone density, morphology and structure.

[0021] Furthermore, in the captured whole image, the cells and heart regions of the zebrafish are segmented and located to obtain static cell images and heart images, including:

[0022] Convert the captured whole image into a grayscale histogram of the image, analyze the grayscale histogram of the image, and use a preset threshold to distinguish cells, heart, and background;

[0023] The image is divided into several sub-regions, and the gray value of each pixel in each sub-region is compared with a preset threshold value to obtain a comparison result;

[0024] According to the comparison result, segmentation is performed to obtain segmented cells and the heart;

[0025] The same cell is identified and tracked in the segmented cells, the trajectory information of each cell in the image is obtained, and static cell images and heart images are obtained.

[0026] Further, the cell image is subjected to morphological analysis to obtain cell analysis results, including:

[0027] Obtain trajectory information of static cell images;

[0028] According to the trajectory information, Calculate the flow velocity of cells and analyze the flow state to obtain cell analysis results. Indicates the speed at which cells move in the blood, in pixels per second. ( , ) is the coordinate position of the cell in the starting video frame, ( , ) is the coordinate position of the cell in the ending video frame, is the number of frames per second, is the time interval between two frames.

[0029] Further, grayscale and morphological analysis is performed on the cardiac image to obtain cardiac analysis results, including:

[0030] The segmented heart image is converted into a binary image to obtain a grayscale analysis of the heart image;

[0031] According to the grayscale analysis of the heart image, Calculate the area to get the heart area, Represents the image at coordinates The pixel value at represents the actual heart area, and are the length and width of the actual physical area represented by the image, are the pixel width and pixel height of the image, respectively. is the specific pixel value of the heart region marker, is the number of pixels representing the heart area; is a conditional expression that means when the image is at coordinates The pixel value at is equal to the specific pixel value of the heart area marker When , the expression evaluates to 1, otherwise it evaluates to 0;

[0032] According to the heart area, the maximum heart area at the end of diastole and the minimum heart area at the end of systole are obtained. Get the ejection fraction of the heart image, where represents the ejection fraction, It refers to the area of ​​the heart at the end of diastole when the ventricle is filled with blood. It refers to the area of ​​the heart after the ventricle pumps out blood at the end of contraction.

[0033] According to the heart area, a waveform is drawn with time as the horizontal axis and heart area as the vertical axis, and according to the waveform, Calculate heart rate data to obtain cardiac dynamic analysis results. The number of heart beats per minute, It represents the average time interval from one end-diastole to the next end-diastole, and 60 represents 60 seconds;

[0034] The cardiac analysis results are obtained based on the cardiac area, ejection fraction and heart rate data of the cardiac image.

[0035] Furthermore, based on the bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish, the osteoporosis condition of zebrafish is identified, including:

[0036] Obtain characteristic indicators of the zebrafish osteoporosis model, including bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish;

[0037] The bone characteristics, cell analysis results, heart analysis results and physiological status of zebrafish were compared with characteristic indicators of zebrafish osteoporosis model to obtain comparative results;

[0038] Based on the comparison results, the osteoporosis status of zebrafish was identified and evaluated.

[0039] In a second aspect, an intelligent recognition system for a zebrafish osteoporosis model comprises:

[0040] An acquisition module is used to capture an overall image of the zebrafish through a high-resolution camera or a microscope; preprocess the captured image to obtain a preprocessed image; and use image processing technology to extract the skeletal features of the zebrafish, including skeletal density, morphology, and structure, based on the preprocessed overall image;

[0041] The processing module is used to segment and locate the cells and heart area of ​​the zebrafish in the captured whole image to obtain static cell images and heart images; perform morphological analysis on the cell images to obtain cell analysis results; perform grayscale and morphological analysis on the heart images to obtain heart analysis results; and identify the osteoporosis condition of the zebrafish based on the bone characteristics, cell analysis results, heart analysis results and the physiological state of the zebrafish.

[0042] According to a third aspect, a computing device includes:

[0043] one or more processors;

[0044] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0045] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0046] The above solution of the present invention includes at least the following beneficial effects:

[0047] By combining the zebrafish's skeletal characteristics, cell analysis results, heart analysis results, and physiological status information in multiple dimensions, comprehensive and accurate data support is provided for the identification of osteoporosis conditions. Through image processing technology and machine learning algorithms, a large amount of zebrafish image data can be efficiently processed and analyzed, and its physiological state can be obtained through image analysis. Static cell images and heart images can be obtained. By tracking the flow trajectory of cells in the blood and analyzing the flow state of cells, dynamic monitoring capabilities are provided for osteoporosis research. By comparing the skeletal characteristics, cell analysis results, heart analysis results, and the physiological state of zebrafish with the characteristic indicators of the osteoporosis model, the osteoporosis condition of zebrafish can be comprehensively evaluated and accurately identified. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of an intelligent identification method for a zebrafish osteoporosis model provided by an embodiment of the present invention.

[0049] Figure 2 It is a schematic diagram of an intelligent identification system for a zebrafish osteoporosis model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in a form and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0051] like Figure 1 As shown, an embodiment of the present invention provides an intelligent identification method for a zebrafish osteoporosis model, the method comprising the following steps:

[0052] Step 11, capturing a whole body image of the zebrafish using a high-resolution camera or microscope;

[0053] Step 12, preprocessing the captured image to obtain a preprocessed image;

[0054] Step 13, using image processing technology to extract the skeletal features of the zebrafish, including bone density, morphology and structure, based on the preprocessed overall image;

[0055] Step 14, in the captured whole image, segmenting and locating the cells and heart region of the zebrafish to obtain a static cell image and a heart image;

[0056] Step 15, performing morphological analysis on the cell image to obtain a cell analysis result;

[0057] Step 16, performing grayscale and morphological analysis on the heart image to obtain a heart analysis result;

[0058] Step 17, identifying the osteoporosis condition of the zebrafish based on the bone characteristics, cell analysis results, heart analysis results and the physiological state of the zebrafish.

[0059] In the embodiments of the present invention, by combining the information of multiple dimensions of zebrafish's skeletal features, cell analysis results, heart analysis results, and physiological state, comprehensive and accurate data support is provided for the identification of osteoporosis conditions. By capturing images with a high-resolution camera or microscope and combining image processing technology, a large amount of zebrafish image data can be efficiently processed and analyzed. By obtaining its physiological state through image analysis, interference and damage to the experimental subjects can be reduced. By using image processing technology and threshold segmentation methods, the cells and heart areas of zebrafish can be accurately segmented and located, and static cell images and heart images can be obtained. By tracking the flow trajectory of cells in the blood and analyzing the flow state of cells, dynamic monitoring capabilities are provided for osteoporosis research. By comparing the skeletal features, cell analysis results, heart analysis results, and the physiological state of zebrafish with the characteristic indicators of the osteoporosis model, the osteoporosis condition of zebrafish can be comprehensively evaluated and accurately identified.

[0060] In a preferred embodiment of the present invention, the above step 12 may include:

[0061] Acquire images of zebrafish under a microscope;

[0062] The zebrafish images were passed through Processing to obtain the filtered image, where Indicates that after filtering, the coordinate The pixel value at is the filter kernel (also called convolution kernel) at position The weight value at and Indicates the size range of the filter kernel, Represents the image at coordinates The pixel value at ;

[0063] The preprocessed image is obtained by adjusting the contrast and brightness of the filtered image and performing color correction on the adjusted image.

[0064] In the embodiment of the present invention, the filtering process can remove the noise in the image and make the image clearer. By adjusting the contrast and brightness, the details in the image can be made more prominent, the visibility of the image can be improved, and it is helpful to more accurately identify and analyze the physiological characteristics of zebrafish. The color correction step can eliminate the color deviation caused by factors such as lighting and equipment, making the image color more realistic and reliable. The pre-processed image has higher quality, less noise, and more obvious features, which helps to improve the accuracy and efficiency of subsequent image analysis.

[0065] In a specific embodiment of the present invention, a camera or imaging system equipped with a microscope is used to capture an image of zebrafish. For each pixel in the image, the pixel value after filtering is calculated, and the contrast and brightness of the image are adjusted as needed. If the image is in color, color correction may be required to eliminate color deviations caused by lighting conditions and equipment differences. The image after filtering, contrast and brightness adjustment, and color correction is saved as a preprocessed image.

[0066] In a preferred embodiment of the present invention, the above step 13 may include:

[0067] Performing feature recognition training on the convolutional neural network using the labeled training data set to obtain a trained convolutional neural network;

[0068] According to the trained convolutional neural network, the preprocessed images are recognized and classified to extract the skeletal features of zebrafish, including bone density, morphology and structure.

[0069] In an embodiment of the present invention, the convolutional neural network has a powerful feature learning ability and can automatically learn the key features of the zebrafish skeleton, including bone density, morphology and structure, from a large amount of training data, thereby improving the accuracy and efficiency of feature extraction. Once the convolutional neural network training is completed, feature extraction can be automatically performed on new preprocessed images without manual intervention, which greatly saves time and energy. Through the diversity of the training data set, the convolutional neural network can learn the zebrafish skeleton features under different lighting, angles, scales and other conditions, making the feature extraction results more stable and reliable. The extracted bone features, such as bone density, morphology and structure, can be used as quantitative feature indicators for the assessment of osteoporosis.

[0070] In a preferred embodiment of the present invention, the above step 14 may include:

[0071] Convert the captured whole image into a grayscale histogram of the image, analyze the grayscale histogram of the image, and use a preset threshold to distinguish cells, heart, and background;

[0072] The image is divided into several sub-regions, and the gray value of each pixel in each sub-region is compared with a preset threshold value to obtain a comparison result;

[0073] According to the comparison result, segmentation is performed to obtain segmented cells and the heart;

[0074] The same cell is identified and tracked in the segmented cells, the trajectory information of each cell in the image is obtained, and static cell images and heart images are obtained.

[0075] In an embodiment of the present invention, through grayscale histogram analysis and preset threshold setting, cells, heart and background in the image can be distinguished more accurately, thereby improving the accuracy of image segmentation. The image is divided into several sub-areas, and the grayscale values ​​of the pixels in each sub-area are compared, so that more refined image segmentation can be achieved and clearer cell and heart contours can be obtained. By tracking the trajectory of the same cell in the image, the dynamic behavior information of the cell can be obtained, providing in-depth data support for cell research, not only focusing on static cell images and heart images, but also providing dynamic information through cell tracking, enhancing the comprehensiveness of image analysis.

[0076] In a specific embodiment of the present invention, the captured color image is converted into a grayscale image, a histogram of the grayscale image is generated, the number of pixels at each grayscale level in the image is displayed, the grayscale histogram is analyzed, and the grayscale distribution of cells, heart and background is observed; according to the observation results, thresholds are preset to distinguish cells, heart and background, wherein two thresholds are set, one for distinguishing cells from background, and the other for distinguishing heart from background;

[0077] The image is divided into several sub-regions. For each pixel in each sub-region, its grayscale value is compared with a preset threshold. Based on the comparison result, the pixel is assigned to a cell, heart or background to obtain segmented cell and heart images. For the segmented cell images, an image tracking algorithm is used to identify and track the position of the same cell in different image frames. The tracking algorithm is based on cell features such as shape, size, texture and motion pattern. Through tracking, the trajectory information of each cell in the image sequence is obtained. Based on the results of cell tracking, static cell images and heart images can be extracted from the original image sequence.

[0078] In a preferred embodiment of the present invention, the above step 15 may include:

[0079] Obtain trajectory information of static cell images;

[0080] According to the trajectory information, Calculate the flow velocity of cells and analyze the flow state to obtain cell analysis results. Indicates the speed at which cells move in the blood, in pixels per second. ( , ) is the coordinate position of the cell in the starting video frame, ( , ) is the coordinate position of the cell in the ending video frame, is the number of frames per second, is the time interval between two frames.

[0081] In an embodiment of the present invention, by calculating the flow velocity of the cells, a quantitative index of the movement speed of the cells in the blood can be obtained, which helps to more accurately describe the dynamic behavior of the cells and evaluate the overall flow state of the cells; the flow state of the cells is an important manifestation of the physiological function of the cells. By analyzing the flow state, we can have a deeper understanding of the physiological characteristics and functions of the cells, providing a new perspective for cell research. The acquisition and analysis of trajectory information is based on objective image data, which improves the accuracy and reliability of the results.

[0082] In a preferred embodiment of the present invention, the above step 16 may include:

[0083] The segmented heart image is converted into a binary image to obtain a grayscale analysis of the heart image;

[0084] According to the grayscale analysis of the heart image, Calculate the area to get the heart area, Represents the image at coordinates The pixel value at represents the actual heart area, and are the length and width of the actual physical area represented by the image, are the pixel width and pixel height of the image, respectively. is the specific pixel value of the heart region marker, is the number of pixels representing the heart area; is a conditional expression that means when the image is at coordinates The pixel value at is equal to the specific pixel value of the heart area marker When , the expression evaluates to 1, otherwise it evaluates to 0;

[0085] According to the heart area, the maximum heart area at the end of diastole and the minimum heart area at the end of systole are obtained. Get the ejection fraction of the heart image, where represents the ejection fraction, It refers to the area of ​​the heart at the end of diastole when the ventricle is filled with blood. It refers to the area of ​​the heart after the ventricle pumps out blood at the end of contraction.

[0086] According to the heart area, a waveform is drawn with time as the horizontal axis and heart area as the vertical axis, and according to the waveform, Calculate heart rate data to obtain cardiac dynamic analysis results. The number of heart beats per minute, It represents the average time interval from one end-diastole to the next end-diastole, and 60 represents 60 seconds;

[0087] The cardiac analysis results are obtained based on the cardiac area, ejection fraction and heart rate data of the cardiac image.

[0088] In the embodiment of the present invention, by calculating the heart area, a quantitative index of the heart size can be obtained, which is helpful to evaluate the development and pathological state of the heart; the heart's ejection fraction is an important indicator of the heart's pumping function. By calculating the ejection fraction, a deeper understanding of the heart's working efficiency and health status can be obtained. The binarization processing, grayscale analysis, area calculation and ejection fraction calculation of the heart image are all based on objective image data, which improves the accuracy and reliability of the heart function assessment. By drawing a waveform diagram of the heart area, the functional state of the heart can be monitored in real time.

[0089] In a specific embodiment of the present invention, by comparing the grayscale value of each pixel in the image with a preset threshold, if the pixel value is higher than or equal to the threshold, it is set to a specific value, for example, 255, representing white, indicating that the pixel belongs to the heart area; otherwise, it is set to another specific value, for example, 0, representing black, indicating the background; the segmented heart image is converted into a binary image. In the binary image, by calculating the number of all pixels marked as the heart area, the total number of pixels in the heart area can be obtained. Given the length and width of the actual physical area represented by the image, as well as the pixel width and height of the image, the area corresponding to each pixel in the actual physical area is calculated;

[0090] The areas of the heart at the end of diastole when the ventricles are filled with blood and at the end of systole after the ventricles have pumped out blood are calculated, and the ejection fraction is obtained through calculation. The periodic changes in the area of ​​the heart are observed by drawing a waveform graph with time as the horizontal axis and the area of ​​the heart as the vertical axis. The time interval from one end of diastole to the next end of diastole is measured, and the number of heart beats per minute is obtained through calculation. The heart area, ejection fraction and heart rate data are combined to comprehensively evaluate the development of the heart and its pumping function to obtain the heart analysis results.

[0091] In a preferred embodiment of the present invention, the above step 17 may include:

[0092] Obtain characteristic indicators of the zebrafish osteoporosis model, including bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish;

[0093] The bone characteristics, cell analysis results, heart analysis results and physiological status of zebrafish were compared with characteristic indicators of zebrafish osteoporosis model to obtain comparative results;

[0094] Based on the comparison results, the osteoporosis status of zebrafish was identified and evaluated.

[0095] In an embodiment of the present invention, by comprehensively considering bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish, the osteoporosis condition of zebrafish can be more comprehensively evaluated; by comparing the acquired characteristic indicators with the characteristic indicators of the osteoporosis model, it is possible to more accurately identify whether the zebrafish has osteoporosis, thereby improving the accuracy of identification.

[0096] In a specific embodiment of the present invention, the extracted bone features, cell analysis results, heart analysis results and physiological status are compared one by one with the characteristic indicators of the known zebrafish osteoporosis model. When comparing, it is important to consider the normal range of each indicator and the changing trend during osteoporosis. Based on the comparison results, it is determined whether the zebrafish exhibits characteristics of osteoporosis, the severity of osteoporosis is identified, including mild, moderate or severe, and the impact of osteoporosis on the overall health of the zebrafish is evaluated.

[0097] like Figure 2 As shown, an embodiment of the present invention further provides an intelligent identification system 20 for a zebrafish osteoporosis model, comprising:

[0098] The acquisition module 21 is used to capture the whole image of the zebrafish through a high-resolution camera or a microscope; preprocess the captured image to obtain a preprocessed image; and use image processing technology to extract the skeletal features of the zebrafish, including bone density, morphology and structure, based on the preprocessed whole image.

[0099] The processing module 22 is used to segment and locate the cells and heart area of ​​the zebrafish in the captured whole image to obtain a static cell image and a heart image; perform morphological analysis on the cell image to obtain a cell analysis result; perform grayscale and morphological analysis on the heart image to obtain a heart analysis result; and identify the osteoporosis condition of the zebrafish based on the bone characteristics, the cell analysis results, the heart analysis results and the physiological state of the zebrafish.

[0100] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0101] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0102] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0103] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent identification method for zebrafish osteoporosis model, characterized in that: The method comprises: Capture whole-body images of zebrafish using high-resolution cameras or microscopes; Preprocessing the captured image to obtain a preprocessed image; Based on the pre-processed overall image, image processing technology is used to extract the zebrafish's bone features, including bone density, morphology and structure; In the captured whole image, the cells and heart regions of the zebrafish are segmented and located to obtain static cell images and heart images; Perform morphological analysis on the cell images to obtain cell analysis results; Perform grayscale and morphological analysis on the cardiac image to obtain cardiac analysis results; Based on the bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish, the osteoporosis condition of zebrafish is identified; morphological analysis is performed on the cell images to obtain cell analysis results, including: Obtain trajectory information of static cell images; According to the trajectory information, Calculate the flow velocity of cells and analyze the flow state to obtain cell analysis results. Indicates the speed at which cells move in the blood, in pixels per second. ( , ) is the coordinate position of the cell in the starting video frame, ( , ) is the coordinate position of the cell in the ending video frame, is the number of frames per second, is the time interval between two frames; Perform grayscale and morphological analysis on cardiac images to obtain cardiac analysis results, including: The segmented heart image is converted into a binary image to obtain a grayscale analysis of the heart image; According to the grayscale analysis of the heart image, Calculate the area to get the heart area, Represents the image at coordinates The pixel value at represents the actual heart area, and are the length and width of the actual physical area represented by the image, and are the pixel width and pixel height of the image, respectively. is the specific pixel value of the heart region marker, is the number of pixels representing the heart area; is a conditional expression that means when the image is at coordinates The pixel value at is equal to the specific pixel value of the heart area marker When , the expression evaluates to 1, otherwise it evaluates to 0; According to the heart area, the maximum heart area at the end of diastole and the minimum heart area at the end of systole are obtained. Get the ejection fraction of the heart image, where represents the ejection fraction, It refers to the area of ​​the heart at the end of diastole when the ventricle is filled with blood. It refers to the area of ​​the heart after the ventricle pumps out blood at the end of contraction. According to the heart area, a waveform is drawn with time as the horizontal axis and heart area as the vertical axis, and according to the waveform, Calculate heart rate data to obtain cardiac dynamic analysis results. The number of heart beats per minute, It represents the average time interval from one end-diastole to the next end-diastole, and 60 represents 60 seconds; The cardiac analysis results are obtained based on the cardiac area, ejection fraction and heart rate data of the cardiac images.

2. The intelligent identification method of zebrafish osteoporosis model according to claim 1, characterized in that: The captured image is preprocessed to obtain a preprocessed image, including: Acquire images of zebrafish under a microscope; The zebrafish images were passed through Processing to obtain the filtered image, where Indicates that after filtering, the coordinate The pixel value at is the filter kernel at position The weight value at and Indicates the size range of the filter kernel, Represents the image at coordinates The pixel value at ; The preprocessed image is obtained by adjusting the contrast and brightness of the filtered image and performing color correction on the adjusted image.

3. The intelligent identification method of zebrafish osteoporosis model according to claim 2, characterized in that: Based on the pre-processed overall image, image processing technology is used to extract the zebrafish's skeletal features, including bone density, morphology and structure, including: Performing feature recognition training on the convolutional neural network using the labeled training data set to obtain a trained convolutional neural network; According to the trained convolutional neural network, the preprocessed images are recognized and classified to extract the skeletal features of zebrafish, including bone density, morphology and structure.

4. The intelligent identification method of zebrafish osteoporosis model according to claim 3, characterized in that: In the captured whole image, the zebrafish cells and heart regions are segmented and located to obtain static cell images and heart images, including: Convert the captured whole image into a grayscale histogram of the image, analyze the grayscale histogram of the image, and use a preset threshold to distinguish cells, heart, and background; The image is divided into several sub-regions, and the gray value of each pixel in each sub-region is compared with a preset threshold value to obtain a comparison result; According to the comparison result, segmentation is performed to obtain segmented cells and the heart; The same cell is identified and tracked in the segmented cells, the trajectory information of each cell in the image is obtained, and static cell images and heart images are obtained.

5. The intelligent identification method of zebrafish osteoporosis model according to claim 4, characterized in that: Based on the bone characteristics, cell analysis results, heart analysis results and the physiological status of zebrafish, the osteoporosis status of zebrafish is identified, including: Obtain characteristic indicators of the zebrafish osteoporosis model, including bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish; The bone characteristics, cell analysis results, heart analysis results and physiological status of zebrafish were compared with characteristic indicators of zebrafish osteoporosis model to obtain comparative results; Based on the comparison results, the osteoporosis status of zebrafish was identified and evaluated.

6. An intelligent recognition system for zebrafish osteoporosis model, characterized in that: include: an acquisition module for capturing whole-body images of zebrafish using a high-resolution camera or microscope; Preprocessing the captured image to obtain a preprocessed image; Based on the pre-processed overall image, image processing technology is used to extract the zebrafish's bone features, including bone density, morphology and structure; A processing module, used for segmenting and locating cells and heart regions of zebrafish in the captured whole image, and obtaining a static cell image and heart image; Perform morphological analysis on the cell image to obtain the cell analysis result; perform grayscale and morphological analysis on the heart image to obtain the heart analysis result; identify the osteoporosis condition of zebrafish based on the bone characteristics, cell analysis results, heart analysis results and the physiological state of zebrafish; Perform morphological analysis on cell images to obtain cell analysis results, including: Obtain trajectory information of static cell images; According to the trajectory information, Calculate the flow velocity of cells and analyze the flow state to obtain cell analysis results. Indicates the speed at which cells move in the blood, in pixels per second. ( , ) is the coordinate position of the cell in the starting video frame, ( , ) is the coordinate position of the cell in the ending video frame, is the number of frames per second, is the time interval between two frames; Perform grayscale and morphological analysis on cardiac images to obtain cardiac analysis results, including: The segmented heart image is converted into a binary image to obtain a grayscale analysis of the heart image; According to the grayscale analysis of the heart image, Calculate the area to get the heart area, Represents the image at coordinates The pixel value at represents the actual heart area, and are the length and width of the actual physical area represented by the image, and are the pixel width and pixel height of the image, respectively. is the specific pixel value of the heart region marker, is the number of pixels representing the heart area; is a conditional expression that means when the image is at coordinates The pixel value at is equal to the specific pixel value of the heart area marker When , the expression evaluates to 1, otherwise it evaluates to 0; According to the heart area, the maximum heart area at the end of diastole and the minimum heart area at the end of systole are obtained. Get the ejection fraction of the heart image, where represents the ejection fraction, It refers to the area of ​​the heart at the end of diastole when the ventricle is filled with blood. It refers to the area of ​​the heart after the ventricle pumps out blood at the end of contraction. According to the heart area, a waveform is drawn with time as the horizontal axis and heart area as the vertical axis, and according to the waveform, Calculate heart rate data to obtain cardiac dynamic analysis results. The number of heart beats per minute, It represents the average time interval from one end-diastole to the next end-diastole, and 60 represents 60 seconds; The cardiac analysis results are obtained based on the cardiac area, ejection fraction and heart rate data of the cardiac images.

7. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to any one of claims 1 to 5 when executed by a processor.

Images