A method for analyzing uterine muscle cell tension based on uterine muscle cell activity images

Abstract

The application provides a uterine muscle cell tension analysis method based on uterine muscle cell activity images, and relates to the technical field of image processing. The method comprises the following steps: obtaining a tension analysis mode, a resting state analysis mode tension analysis, a contraction state analysis mode tension analysis and tension analysis result feedback. The application obtains the tension analysis mode, if it is the resting state analysis mode, obtains the resting uterine muscle cell image and obtains the resting uterine muscle cell tension analysis result, if it is the contraction state analysis mode, obtains the contraction uterine muscle cell image and obtains the contraction uterine muscle cell tension analysis result, and finally transmits the uterine muscle cell tension analysis result to a preset medical staff terminal, thereby improving the reliability of the uterine muscle cell tension analysis result and solving the problem that the reliability of the uterine muscle cell tension analysis result is unstable due to the difference in ultrasonic probe scanning in the prior art.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method for analyzing uterine myocyte tension based on images of uterine myocyte activity. Background Technology

[0002] With the continuous development of biomedical technology, the study of cell mechanics has become an important direction in cell biology. Particularly in the study of uterine myocytes, understanding their tension changes is crucial for revealing the mechanisms of uterine contraction and researching pregnancy-related diseases (such as premature birth and uterine fibroids). Tension analysis methods based on images of uterine myocyte activity, utilizing advanced image processing and mechanical modeling techniques, can accurately assess cell tension, thus promoting the development of cell mechanics research and its clinical applications.

[0003] Existing analytical methods mainly include traction force microscopy (TFM), optical tweezers, and image analysis algorithms. TFM assesses cell tension by detecting deformation in the interaction between cells and the matrix; optical tweezers measure minute forces between cells by manipulating a light beam. Image analysis techniques, such as deep learning algorithms, can automatically process cell morphology and deformation data, providing accurate tension estimates. Despite these advancements, challenges remain, including image noise and cell heterogeneity.

[0004] For example, the invention patent announcement CN118279912B discloses a method and system for assessing stem cell differentiation degree based on image analysis, which includes: acquiring initial stem cell image data to be processed and performing preprocessing with a fully convolutional network to obtain enhanced stem cell image data; performing dense gated channel transformation and cell segmentation to obtain stem cell segmentation image data; performing feature extraction and direction-aware regression analysis to obtain a directional feature dataset; inputting the directional feature dataset into the initial stem cell differentiation degree assessment model for multi-scale feature fusion and stem cell differentiation degree assessment to obtain differentiation degree assessment information; and performing global search and local optimum solution of model parameters based on the adaptive mayfly algorithm and differentiation degree assessment information to obtain the target stem cell differentiation degree assessment model.

[0005] For example, the invention patent announcement CN114241478B discloses a method and apparatus for identifying abnormal cell images in cervical cell images, comprising: inputting multi-scale cervical cell images into a pre-trained multi-scale fusion network, wherein the multi-scale cervical cells include different sizes of the same cervical cell image; extracting key node features of cervical cell images at each scale through the multi-scale fusion network; determining the grading result of abnormal cell images in cervical cell images corresponding to the key node features of cervical cell images at each scale through the Berthesda grading system; fusing the grading results of abnormal cell images in cervical cell images at each scale, and outputting abnormal cell images in cervical cell images and the abnormal cell image with the highest grade in the grading results.

[0006] However, in the process of implementing the technical solutions in the embodiments of the present invention, it was found that the above-mentioned technology has at least the following technical problems:

[0007] In existing technologies, corresponding ultrasound elastography images are obtained through ultrasound detection. However, during the ultrasound elastography image scanning process, due to differences in the operation of the probe by medical staff, there is a problem that the reliability of the uterine myocyte tension analysis results is unstable due to the differences in ultrasound probe scanning. Summary of the Invention

[0008] This invention provides a method for analyzing uterine myocyte tension based on images of uterine myocyte activity, which solves the problem of unstable reliability of uterine myocyte tension analysis results caused by differences in ultrasound probe scanning in the prior art, and improves the reliability of uterine myocyte tension analysis results.

[0009] This invention provides a method for analyzing uterine myocyte tension based on images of uterine myocyte activity, comprising the following steps: obtaining an initial judgment image through an initial scan; determining the tension analysis state based on the initial judgment image and selecting the tension analysis mode for the object to be analyzed, including a resting state analysis mode and a uterine contraction state analysis mode; if the tension analysis mode is a resting state analysis mode, performing ultrasound elastography to obtain the corresponding resting uterine myocyte image; evaluating the effectiveness of the ultrasound scan based on the resting uterine myocyte image to determine whether to rescan; if a rescan is performed, evaluating the effectiveness of the ultrasound scan based on the rescanned resting uterine myocyte image, and determining the effectiveness of the rescan based on the resting uterine myocyte image that meets the scanning effectiveness criteria. The process involves obtaining resting uterine myocyte tension analysis results, or directly obtaining the results based on resting uterine myocyte images. If the tension analysis mode is uterine contraction state analysis mode, ultrasound elastography is performed to obtain corresponding uterine contraction myocyte images. Based on the uterine contraction myocyte images, the image tension performance is determined, and corresponding tension analysis optimization measures are taken to obtain the corresponding uterine contraction myocyte tension analysis results. The obtained uterine myocyte tension analysis results are transmitted to a preset medical staff terminal. The uterine myocyte tension analysis results include resting uterine myocyte tension analysis results and uterine contraction myocyte tension analysis results. The uterine myocyte tension analysis results represent a collection of uterine myocyte images, elastograms, and uterine myocyte tension analysis data.

[0010] Optionally, the effectiveness of ultrasound scanning is evaluated based on the resting myometrial cell image to determine whether a rescan is necessary. The specific steps are as follows: K1, The effectiveness of ultrasound scanning is evaluated on the acquired resting myometrial cell image to obtain an ultrasound detection effectiveness judgment value. The ultrasound detection effectiveness judgment value is used to determine the effectiveness of the current ultrasound scan image of the myometrial cells; K2, If the ultrasound detection effectiveness judgment value is not less than the ultrasound detection evaluation threshold obtained from the preset database, it indicates that the resting myometrial cell image is qualified and K4 is executed. If the ultrasound detection effectiveness judgment value is less than the ultrasound detection evaluation threshold obtained from the preset database, the preset medical staff is prompted to change the scanning area for rescanning and K3 is executed; K3, Based on the liquid interference judgment data, it is determined whether to optimize the ultrasound imaging parameters to obtain a qualified resting myometrial cell image and K4 is executed; K4, The resting myometrial cell image is divided into scar region and non-scar region according to the color identifier of the qualified resting myometrial cell image, and tension feedback is performed on the scar region of the resting myometrial cell image. Tension feedback means that the tension of the scar region in the resting myometrial cell image is fed back to the preset medical staff.

[0011] Optionally, the specific process for obtaining the ultrasound detection validity judgment value is as follows: Obtain ultrasound detection evaluation data of resting uterine myocyte images, including echo intensity, image grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio; obtain ultrasound evaluation parameters from a preset database, including ultrasound evaluation reference values ​​and ultrasound evaluation influence weights. Ultrasound evaluation reference values ​​include echo intensity reference range, grayscale value reference range, minimum elastic modulus limit, minimum attenuation coefficient threshold, and minimum signal-to-noise ratio classification value. Ultrasound evaluation influence weights include echo intensity influence weight, grayscale value influence weight, elastic modulus influence weight, attenuation coefficient influence weight, and signal-to-noise ratio influence weight; compare the echo intensity with the corresponding echo intensity reference range. Range deviation quantization is performed to obtain the echo intensity deviation; range deviation quantization is performed between the image grayscale value and the corresponding grayscale value reference range to obtain the grayscale value deviation; deviation degree quantization is performed between the elastic modulus, attenuation coefficient, and signal-to-noise ratio and the corresponding ultrasound evaluation reference values ​​to obtain the corresponding elastic modulus deviation value, attenuation coefficient deviation value, and signal-to-noise ratio deviation value; after weighting the echo intensity deviation, grayscale value deviation, elastic modulus deviation value, attenuation coefficient deviation value, and signal-to-noise ratio deviation value with the corresponding ultrasound evaluation influence weight, an ultrasound detection validity judgment value is obtained. The ultrasound detection validity judgment value is used to determine the reliability of the resting uterine myocyte image obtained by ultrasound elastography.

[0012] Optionally, the process of determining whether to optimize ultrasound imaging parameters based on liquid interference judgment data is as follows: Liquid interference judgment data is obtained based on resting uterine myocyte images. This liquid interference judgment data includes the average grayscale value and the average echo intensity of the image. The liquid interference judgment data is compared with reference liquid judgment data obtained from a preset database. This reference liquid judgment data includes the reference judgment grayscale value and the reference judgment echo intensity. If any liquid interference judgment data is not less than the corresponding reference liquid judgment data, ultrasound imaging parameter optimization is performed; otherwise, no additional processing is performed. The specific steps of ultrasound imaging parameter optimization are as follows: The difference between the liquid interference judgment data and the corresponding reference liquid judgment data is quantified to obtain the corresponding liquid interference difference quantization value. An imaging parameter optimization ratio group is obtained based on the liquid interference difference quantization value. The imaging parameters are optimized and compensated according to the imaging parameter optimization ratio group to obtain the corresponding imaging parameters to be imaged. A rescan is performed based on the imaging parameters to be imaged. The imaging parameter optimization ratio group includes the probe frequency adjustment ratio and the echo gain adjustment ratio. The imaging parameters include the probe frequency and the echo gain.

[0013] Optionally, the specific steps for tension feedback on the scar region of the resting uterine myocyte image are as follows: Step 1: Obtain the color identification data of the scar region of the resting uterine myocyte image, input the color identification data into the image elasticity quantitative value model, and output the corresponding image elasticity quantitative value, which is recorded as the resting image elasticity quantitative value; Step 2: Transmit the resting image elasticity quantitative value of the scar region and the ultrasound elasticity image of the resting uterine myocyte image to the preset medical staff terminal.

[0014] Optionally, the specific method for obtaining the image elasticity quantitative value model is as follows: Color identifier data of the corresponding uterine myocyte image is obtained and normalized. The color identifier data includes RGB values, color area, and elastic modulus. The colors of the uterine myocyte image are classified and numbered according to the RGB values. Simultaneously, corresponding color identifier analysis parameters are obtained from a preset database. These parameters include color identifier analysis proportion and color category analysis weight. The color identifier analysis proportion includes RGB value analysis proportion, area analysis proportion, and elastic modulus analysis proportion. The color identifier data and the corresponding color identifier analysis proportion are weighted and coupled to obtain the initial quantized value of image elasticity. The initial quantized value of elasticity for each type of RGB color is accumulated and summed with the corresponding color category analysis weight, and then the mean is calculated to obtain the image elasticity quantitative value model. This model is used to quantify the tension characteristics of the corresponding image region through the elasticity map representation of the ultrasound elasticity image.

[0015] Optionally, image tension performance is determined based on images of contracting uterine myocytes, and corresponding tension analysis optimization measures are taken to obtain the corresponding contracting uterine myocyte tension analysis results. The specific steps are as follows: H1, when the tension analysis mode is the contraction state analysis mode, the ultrasound imaging frequency is adjusted to the maximum imaging frequency; H2, the color identification data of the contracting uterine myocyte images within a preset time period is obtained and input into the image elasticity quantitative value model, and the corresponding image elasticity quantitative value is output, which is recorded as the contraction image elasticity quantitative value; H3, the contraction image elasticity quantitative value within the preset time period is averaged to obtain the corresponding average contraction image elasticity quantitative value; H4, the average contraction image... The elasticity quantitative value of the image is compared with the elasticity quantitative value of the reference uterine contraction image obtained from the preset database. Corresponding image monitoring and early warning measures are taken and corresponding judgment results are obtained. If the average elasticity quantitative value of the uterine contraction image is not less than the elasticity quantitative value of the reference uterine contraction image, the real-time demand level of uterine contraction tension monitoring is recorded as Level 1 demand; otherwise, it is Level 2 demand. H5, According to the judgment result of the real-time demand level of uterine contraction tension monitoring, corresponding imaging frequency adjustment measures are taken. H6, The uterine contraction myocyte image is divided to obtain the corresponding uterine contraction scar map domain, and scar priority feedback is given to the uterine contraction scar map domain. Scar priority feedback means that the analysis results of the uterine contraction scar map domain are given priority feedback.

[0016] Optionally, the specific process of taking corresponding image monitoring and early warning measures is as follows: when the elasticity value of the uterine contraction image is not less than the elasticity value of the reference uterine contraction image, a first-level early warning is issued. The first-level early warning indicates that the uterine contraction tension of the object to be analyzed and the preset medical staff is abnormal through sound prompts; when the number of first-level early warnings exceeds the preset number, a second-level early warning is issued. The second-level early warning includes high-frequency sound warnings and display warnings.

[0017] Optionally, based on the determination of the real-time requirement level for uterine contraction tension monitoring, corresponding imaging frequency adjustment measures are taken. The specific process is as follows: If there are consecutive preset number of preset time periods with a real-time requirement level of uterine contraction tension monitoring of Level 2, then the difference between the average elasticity value of the uterine contraction image and the corresponding reference elasticity value of the uterine contraction image for all preset time periods is quantified, and then the average difference value is calculated to obtain the corresponding average difference value; the imaging frequency reduction factor is obtained based on the average difference value, and the ultrasound imaging frequency is adjusted by the imaging frequency reduction factor; if the real-time requirement level for uterine contraction tension monitoring for a preset time period is Level 1, then the ultrasound imaging frequency is adjusted back to the maximum imaging frequency value.

[0018] Optionally, scar-priority feedback is performed on the uterine contraction scar image domain. The specific process is as follows: the color identification data of the uterine contraction scar image domain is input into the image elasticity quantitative value model, and the corresponding image elasticity quantitative value is output and recorded as the uterine contraction scar image elasticity quantitative value; the uterine contraction scar elasticity quantitative value sequence is obtained by statistically analyzing the uterine contraction scar image elasticity quantitative values ​​output within a preset time period in chronological order; the uterine contraction scar elasticity quantitative value sequence corresponding to the uterine contraction myocyte images within the preset time period is preferentially transmitted to the preset medical staff terminal.

[0019] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0020] 1. By acquiring the tension analysis mode of the object to be analyzed, if it is the resting state analysis mode, the resting uterine myocyte image is obtained and the effectiveness of the ultrasound scan is evaluated to determine whether to rescan. Based on the judgment result, the corresponding uterine myocyte tension analysis result is obtained. If it is the uterine contraction state analysis mode, the uterine contraction uterine myocyte image is obtained and the image tension performance is judged. Then, tension analysis optimization measures are taken to obtain the uterine contraction uterine myocyte tension analysis result. Finally, the uterine myocyte tension analysis result is transmitted to the medical staff terminal, thereby providing the medical staff with more detailed tension analysis results, thus improving the reliability of the uterine myocyte tension analysis result and effectively solving the problem of unstable reliability of uterine myocyte tension analysis results caused by the difference in ultrasound probe scanning in the existing technology.

[0021] 2. By acquiring ultrasound detection and evaluation data of resting uterine myocyte images and obtaining ultrasound evaluation parameters from a preset database, the echo intensity and image grayscale value are then subjected to range deviation quantization calculations with the corresponding ultrasound evaluation reference values ​​to obtain the echo intensity deviation and grayscale value deviation. Simultaneously, the elastic modulus, attenuation coefficient, and signal-to-noise ratio are subjected to deviation quantization calculations with the corresponding ultrasound evaluation reference values ​​to obtain the elastic modulus deviation value, attenuation coefficient deviation value, and signal-to-noise ratio deviation value. Finally, by weighting the above-obtained data with the corresponding ultrasound evaluation influence weights, the ultrasound detection validity judgment value is obtained, thereby more accurately quantifying the reliability of resting uterine myocyte images and thus achieving a more accurate determination of the validity of resting uterine myocyte images.

[0022] 3. By acquiring color identification data of the corresponding uterine myocyte images and performing data normalization, and classifying and numbering the colors of the uterine myocyte images according to the RGB values, color identification analysis parameters are obtained from a preset database. Then, the color identification data and the corresponding color identification analysis proportions are weighted and coupled to obtain the initial quantization value of image elasticity. Finally, the initial quantization value of elasticity of each color RGB is calculated with the corresponding color category analysis proportion to obtain the image elasticity quantification model. This more accurately quantifies the tension characteristics of the corresponding image region represented by the elasticity map of the ultrasound elasticity image, thereby achieving a more accurate feedback of the tension characteristics of the uterine myocyte images. Attached Figure Description

[0023] Figure 1 A flowchart of a method for analyzing uterine myocyte tension based on images of uterine myocyte activity provided in an embodiment of the present invention;

[0024] Figure 2 A flowchart illustrating the scanning determination process in the uterine myocyte tension analysis method based on uterine myocyte activity images provided in this embodiment of the invention;

[0025] Figure 3 A flowchart illustrating the determination of image tension characteristics in the uterine myocyte tension analysis method based on uterine myocyte activity images provided in this embodiment of the invention. Detailed Implementation

[0026] This invention provides a method for analyzing uterine myocyte tension based on images of uterine myocyte activity, solving the problem of unstable reliability of uterine myocyte tension analysis results caused by differences in ultrasound probe scanning in existing technologies. An initial judgment image is obtained through an initial scan. Based on the initial judgment image, the tension analysis state is determined, and the tension analysis mode of the object to be analyzed is selected. If the tension analysis mode is a resting state analysis mode, a resting uterine myocyte image is obtained, and the effectiveness of the ultrasound scan is evaluated to determine whether a rescan is needed. Based on this determination result, the corresponding uterine myocyte tension analysis result is obtained. If the tension analysis mode is a uterine contraction state analysis mode, the ultrasound imaging frequency is adjusted to its maximum value, and the color identification data of the uterine contraction uterine myocyte images within a preset time period is obtained and input into the image elasticity quantitative value model. The corresponding image elasticity quantitative value is output, denoted as uterine contraction. The contraction tension quantitative value is calculated by averaging the contraction tension quantitative values ​​over a preset time period. This average contraction tension quantitative value is then compared with a reference contraction tension quantitative value obtained from a preset database. Corresponding image monitoring and early warning measures are implemented, and a judgment result is obtained. If the average contraction tension quantitative value is not less than the reference contraction tension quantitative value, the real-time requirement level for contraction tension monitoring is set as Level 1; otherwise, it is set as Level 2. Based on the judgment result of the real-time requirement level for contraction tension monitoring, corresponding imaging frequency adjustment measures are implemented, and the contraction myometrial cell image is divided to obtain the corresponding contraction scar region for scar-priority feedback. Finally, the obtained myometrial tension analysis results are transmitted to a preset medical staff terminal, improving the reliability of the myometrial tension analysis results.

[0027] The technical solution in this invention aims to address the problem of unstable reliability of uterine myocyte tension analysis results due to differences in ultrasound probe scanning. The overall approach is as follows:

[0028] By acquiring the tension analysis mode, if the tension analysis mode is the resting state analysis mode, the image of the resting uterine myocytes is obtained and the corresponding uterine myocyte tension analysis result is obtained; if the tension analysis mode is the uterine contraction state analysis mode, the image of the uterine contraction uterine myocytes is obtained and the uterine contraction uterine myocyte tension analysis result is obtained. Finally, the obtained uterine myocyte tension analysis result is transmitted to the preset medical staff terminal, which achieves the effect of improving the reliability of the uterine myocyte tension analysis result.

[0029] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0030] like Figure 1The diagram shows a flowchart of a method for analyzing uterine myocyte tension based on images of uterine myocyte activity provided in an embodiment of the present invention. The method includes the following steps:

[0031] An initial judgment image is obtained through an initial scan. Based on the initial judgment image, the tension analysis state is determined and the tension analysis mode of the object to be analyzed is selected. The tension analysis modes include resting state analysis mode and uterine contraction state analysis mode.

[0032] It should be added that the specific process for determining the tension analysis state based on the initial judgment image is as follows: obtain the ultrasonic hardness value of the initial judgment image, compare the ultrasonic hardness value with the state boundary value obtained from the preset database, if the ultrasonic hardness value is greater than the state boundary value, then select the tension analysis mode of the object to be analyzed as the uterine contraction state analysis mode, otherwise select the resting state analysis mode; the state boundary value is preset and stored in the preset database by the preset staff, and the ultrasonic hardness value is usually expressed in terms of elastic modulus (unit such as kPa).

[0033] If the tension analysis mode is the resting state analysis mode, ultrasound elastography is performed to obtain the corresponding resting uterine myocyte image. The validity of the ultrasound scan is evaluated based on the resting uterine myocyte image to determine whether to rescan. If rescan, the validity of the ultrasound scan is evaluated based on the resting uterine myocyte image obtained by the rescan, and the tension analysis result of the resting uterine myocyte is obtained based on the resting uterine myocyte image that meets the validity conditions. Otherwise, the tension analysis result of the uterine myocyte is obtained directly based on the resting uterine myocyte image.

[0034] If the tension analysis mode is the uterine contraction state analysis mode, then ultrasound elastography is performed to obtain the corresponding uterine contraction myocyte images. Based on the uterine contraction myocyte images, the image tension performance is determined, and corresponding tension analysis optimization measures are taken to obtain the corresponding uterine contraction myocyte tension analysis results.

[0035] The obtained uterine myocyte tension analysis results are transmitted to the preset medical staff terminal. The uterine myocyte tension analysis results include resting uterine myocyte tension analysis results and uterine contraction uterine myocyte tension analysis results. The uterine myocyte tension analysis results represent a collection of uterine myocyte images, elastograms, and uterine myocyte tension analysis data. The uterine myocyte tension analysis data includes, but is not limited to, ultrasound detection evaluation data, ultrasound detection validity judgment values, liquid interference judgment data, color identification data, image elasticity quantitative values, and uterine contraction scar elasticity quantitative value sequences.

[0036] Specifically, the results of uterine myocyte tension analysis include resting image elasticity quantitative values ​​of the scar region, resting uterine myocyte images and their ultrasound elasticity images, or uterine contraction scar elasticity quantitative value sequences, uterine contraction myocyte images and their ultrasound elasticity images.

[0037] In this embodiment, as the uterus enlarges during pregnancy, the uterine muscle fibers stretch and bear increased pressure. The uterine scar often cannot withstand high-intensity tension, leading to uterine rupture in late pregnancy. Clinically, cesarean section is usually performed at 39 weeks of gestation to terminate pregnancy, minimizing the risk of uterine muscle fiber tension exceeding its maximum pressure tolerance during contractions or further uterine enlargement, ultimately resulting in uterine rupture. However, some women with uterine scars experience uterine rupture before elective cesarean section due to thin uterine muscle layers or low tension tolerance of uterine muscle fibers. Therefore, it is necessary to examine the uterine muscle cells of the subjects under analysis. Currently, ultrasound is used to obtain corresponding ultrasound elastography images for tension analysis. However, during ultrasound elastography, differences in probe operation by medical personnel may reduce the reliability of uterine muscle cell tension analysis results. By analyzing the tension of the uterus under two different states and implementing different optimization measures, the accuracy of the uterine muscle cell images used for tension analysis is ensured, thereby improving the reliability of the uterine muscle cell tension analysis results.

[0038] It should be added that before designing the uterine myocyte tension analysis method based on uterine myocyte activity images, a preset database was established by the preset personnel to store various set data. The preset database includes, but is not limited to, ultrasound detection and evaluation thresholds, ultrasound evaluation parameters, reference fluid judgment data, color identification analysis parameters, and reference uterine contraction image elasticity values. Among them, various values ​​are directly set by the preset professionals. For example, the ultrasound detection and evaluation threshold is obtained by the preset staff by substituting the ultrasound detection and evaluation data corresponding to qualified ultrasound elastic images generated in the historical database into the specific constraint expression of the ultrasound detection validity judgment value, and then performing mean calculation on the dataset to obtain the ultrasound detection and evaluation threshold, which is then stored in the preset database in advance.

[0039] It's important to explain that ultrasound elastography assesses tissue stiffness or elasticity by measuring its response to external forces. In detecting uterine muscle fiber tension, ultrasound elastography primarily utilizes the propagation characteristics of ultrasound waves to reflect changes in tissue stiffness. Ultrasound elastography images the tissue's response to external forces (such as vibration or pressure). Stiffer tissues (such as fibrotic scar tissue) typically exhibit less deformation under external forces, while softer tissues (such as normal uterine muscle fibers) undergo greater deformation. Ultrasound elastography uses this principle to assess tissue elasticity or stiffness; it acquires reflected waves through an ultrasound probe, recording the time difference, wave velocity, and degree of deformation. The information recorded by the probe is converted into an elasticity image, showing the distribution of stiffness (or rigidity) in different regions. Based on the difference in wave propagation speed, image processing software generates an elasticity map, typically displaying stiffer areas as brighter or redder, and softer areas as darker or bluer. Thus, healthcare professionals can observe the stiffness distribution of uterine muscle fibers in the image and subsequently assess its tension state.

[0040] like Figure 2 The diagram shows a flowchart of the scanning determination process in the uterine myocyte tension analysis method based on uterine myocyte activity images provided in this embodiment of the invention. The specific logic is as follows: An ultrasound scan validity assessment is performed on the acquired resting uterine myocyte image to obtain an ultrasound detection validity determination value. If the ultrasound detection validity determination value is not less than the ultrasound detection assessment threshold obtained from a preset database, the resting uterine myocyte image is considered qualified, and the image is divided. If the ultrasound detection validity determination value is less than the ultrasound detection assessment threshold obtained from the preset database, a preset medical staff is prompted to change the scanning area and rescan, and a liquid interference determination is performed. Based on the resting uterine myocyte image, corresponding liquid interference determination data is obtained. The liquid interference determination data is compared with reference liquid determination data. If any liquid interference determination data is not less than the corresponding reference liquid determination data, ultrasound imaging parameters are optimized; otherwise, no additional processing is performed.

[0041] It is important to understand that the specific steps for optimizing ultrasound imaging parameters are as follows: The difference between the liquid interference judgment data and the corresponding reference liquid judgment data is quantified to obtain the corresponding liquid interference difference quantification value; an imaging parameter optimization ratio group is obtained based on the liquid interference difference quantification value; the imaging parameters are optimized and compensated according to the imaging parameter optimization ratio group to obtain the corresponding imaging parameters; a re-scan is performed based on the imaging parameters to obtain qualified resting myocyte images, and the resting myocyte images are divided; among these divisions, scar and non-scar regions are obtained, and tension feedback is performed on the scar region of the resting myocyte images; through the above process, not only is the accuracy of ultrasound examination improved, but also the accuracy and reliability of tension analysis of myocyte images are improved.

[0042] Optionally, the effectiveness of ultrasound scanning can be assessed based on resting uterine myocyte images to determine whether a rescan should be performed. The specific steps are as follows:

[0043] K1 is used to evaluate the effectiveness of ultrasound scanning of the acquired resting uterine myocyte images to obtain an ultrasound detection effectiveness judgment value, which is used to determine the effectiveness of the uterine myocyte images obtained by the current ultrasound scan.

[0044] K2 compares the ultrasound detection validity judgment value with the ultrasound detection evaluation threshold obtained from the preset database: if the ultrasound detection validity judgment value is not less than the ultrasound detection evaluation threshold obtained from the preset database, it means that the resting uterine myocyte image is qualified and K4 is executed; if the ultrasound detection validity judgment value is less than the ultrasound detection evaluation threshold obtained from the preset database, it prompts the preset medical staff to change the scanning area for rescanning and K3 is executed.

[0045] K3 determines whether to optimize ultrasound imaging parameters based on liquid interference data, obtains qualified images of resting uterine myocytes, and then executes K4.

[0046] K4 divides the resting myocyte images into scar and non-scar regions based on the color identifiers of qualified resting myocyte images. It then performs tension feedback on the scar region of the resting myocyte images, which means that the tension of the scar region in the resting myocyte images is fed back to the preset medical staff.

[0047] It's important to explain that in ultrasound elastography, the delineation of scar areas typically relies on color coding, using different color values ​​to represent tissue areas of varying hardness. Ultrasound elastography (such as ultrasound elastography or strain imaging) can display the hardness of tissue; areas with higher hardness (such as scar tissue) are usually represented by brighter or darker colors, while areas with lower hardness (such as healthy tissue) are represented by darker or lighter colors.

[0048] In this embodiment, the effectiveness assessment of ultrasound scanning ensured that the image quality met the expected standards, thus providing reliable basic data for further analysis. Liquid interference detection reduced the number of uterine myocyte images that did not meet the expected standards from entering subsequent analysis, ensuring the accuracy of the final results. Furthermore, by optimizing scanning parameters, the scanning quality and imaging clarity were improved, guaranteeing data accuracy. This not only helps medical staff quickly identify scar areas but also provides specific tension feedback at the scar site, offering valuable information for subsequent treatment decisions. Through the above steps of effectiveness assessment, parameter optimization, region division, and tension feedback of ultrasound images, not only was the accuracy of ultrasound examination improved, but more precise data support was also provided for subsequent treatment.

[0049] Optionally, the specific process for obtaining the ultrasound detection validity determination value is as follows:

[0050] First, ultrasound detection and evaluation data of resting uterine myocytes are obtained. The ultrasound detection and evaluation data includes echo intensity, image gray value, elastic modulus, attenuation coefficient and signal-to-noise ratio.

[0051] It should be added that echo intensity is usually calculated by the built-in processing system of the ultrasound equipment. Specifically, it is obtained by converting the reflected signal into grayscale values ​​and displaying them on the image. The image grayscale values ​​are calculated in real time by the ultrasound equipment based on the intensity of the reflected echo signal and displayed on the monitor at different brightness levels. The higher the image grayscale value, the stronger the reflection, which usually represents hard tissue (such as bones and muscles). The lower the image grayscale value, the weaker the reflection, which usually represents soft tissue or fluid (such as amniotic fluid). The degree of tissue deformation is measured and an image is generated by the elastic imaging mode of the ultrasound equipment (such as sound wave frequency change, strain imaging, etc.). Hard tissue will show a higher elastic modulus, while soft tissue will show a lower elastic modulus. The attenuation coefficient is usually calculated by the ultrasound equipment by measuring the intensity change of ultrasound waves passing through the tissue. Specifically, it can be calculated by transmitting and receiving ultrasound signals of different frequencies. The ratio of effective signal to noise signal is calculated by the ultrasound equipment.

[0052] Simultaneously, ultrasonic evaluation parameters are obtained from a preset database. These parameters include ultrasonic evaluation reference values ​​and ultrasonic evaluation influence weights. The ultrasonic evaluation reference values ​​include echo intensity reference range, grayscale value reference range, minimum elastic modulus limit value, minimum attenuation coefficient critical value, and minimum signal-to-noise ratio classification value. The echo intensity reference range represents the range between the maximum and minimum echo intensity values, and the grayscale value reference range represents the range between the minimum and maximum grayscale values. The ultrasonic evaluation influence weights include the influence weights of echo intensity, grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio.

[0053] Specifically, the ultrasound assessment influence weight represents the degree of influence of ultrasound testing and assessment data on the ultrasound testing validity determination value. Each ultrasound testing and assessment data point has a unique mapping relationship with its corresponding ultrasound assessment influence weight, and the value ranges from 0 to 1. For example, by constructing a mapping set between ultrasound testing and assessment data and a preset ultrasound assessment influence weight, real-time echo intensity, image grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio are input into the mapping set to obtain the corresponding echo intensity influence weight, grayscale value influence weight, elastic modulus influence weight, attenuation coefficient influence weight, and signal-to-noise ratio influence weight. These weights represent the degree of influence of echo intensity, image grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio on the ultrasound testing validity determination value, and the sum of these five values ​​is 1.

[0054] Specifically, the ultrasound evaluation reference values ​​are obtained from a preset database, which are pre-set and stored in the preset database by preset staff based on the specific requirements of ultrasound imaging.

[0055] Next, the echo intensity is compared with the corresponding echo intensity reference range by range deviation quantization to obtain the echo intensity deviation.

[0056] It should be added that the specific expression for the echo intensity deviation is as follows:

[0057]

[0058] Wherein, EI represents the echo intensity of the resting uterine myocyte image, EI_max represents the maximum echo intensity, EI_min represents the minimum echo intensity, and EI_i represents the echo intensity deviation of the resting uterine myocyte image.

[0059] Furthermore, range deviation quantization is performed on the image grayscale value and the corresponding grayscale value reference range to obtain the grayscale value deviation.

[0060] It should be added that the specific expression for the grayscale value deviation is as follows:

[0061]

[0062] Wherein, GV represents the image grayscale value of the resting uterine myocyte image, GV_min represents the minimum grayscale value, GV_max represents the maximum grayscale value, and GV_i represents the grayscale value deviation of the resting uterine myocyte image.

[0063] Then, the deviation of the elastic modulus, attenuation coefficient, and signal-to-noise ratio from the corresponding ultrasonic evaluation reference values ​​is quantified to obtain the corresponding deviation values ​​of elastic modulus, attenuation coefficient, and signal-to-noise ratio.

[0064] It should be added that the specific expression for the degree of deviation of the elastic modulus is as follows:

[0065]

[0066] Wherein, EM represents the elastic modulus of a resting uterine myocyte image. min EM_i represents the minimum elastic modulus limit value, and EM_i represents the degree of deviation of the elastic modulus from the resting uterine myocyte image.

[0067] It should be added that the specific expression for the deviation value of the attenuation coefficient is as follows:

[0068]

[0069] Where AC represents the attenuation coefficient of the resting uterine myocyte image, AC min denoted by , the minimum attenuation coefficient threshold, and AC_i represents the degree of deviation of the attenuation coefficient from the resting uterine myocyte image.

[0070] It should be added that the specific expression for the signal-to-noise ratio deviation value is as follows:

[0071]

[0072] Wherein, SNR represents the signal-to-noise ratio of a resting uterine myocyte image. min SNR_i represents the minimum signal-to-noise ratio (SNR) threshold value, and SNR_i represents the degree of SNR deviation of the resting uterine myocyte image.

[0073] Finally, by weighting and coupling the echo intensity deviation, gray value deviation, elastic modulus deviation, attenuation coefficient deviation, and signal-to-noise ratio deviation with the corresponding ultrasound evaluation influence weights, an ultrasound detection validity judgment value is obtained. The ultrasound detection validity judgment value is used to determine the reliability of the resting uterine myocyte image obtained by ultrasound elastography.

[0074] The specific limiting expression for the validity judgment value of ultrasound detection is as follows:

[0075] EUT = EI_i × θ ei+GV_i×θ gv +EM_i×θ em +AC_i×θ ac +SNR_i×θ snr ;

[0076] In the formula, θ ei θ indicates that echo intensity affects the specific gravity. gv θ represents the proportion of grayscale value's influence. em θ indicates that the elastic modulus affects the specific gravity. ac θ represents the effect of the attenuation coefficient on the weight. snr The signal-to-noise ratio (SNR) influence is indicated by EUT, which represents the validity assessment value for ultrasound detection of resting uterine myocyte images.

[0077] In this embodiment, the algorithm combines the deviations in echo intensity, grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio with the corresponding weights in ultrasound evaluation to obtain an ultrasound detection validity judgment value. As the deviations in echo intensity, grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio increase, the corresponding ultrasound detection validity judgment value also increases, indicating a lower detection validity of the current ultrasound scanned uterine myocyte image; conversely, a lower value indicates a higher detection validity. Determining the validity of the uterine myocyte image using the ultrasound detection validity judgment value helps improve the quality of the ultrasound-improved uterine myocyte image, thereby increasing its reliability and ensuring the stability of the generated uterine myocyte image quality.

[0078] Optionally, the decision on whether to optimize ultrasound imaging parameters is based on liquid interference data. The specific process is as follows:

[0079] J1, based on resting uterine myocyte images, obtains corresponding liquid interference determination data, which includes the average gray value and the average echo intensity of the image.

[0080] J2 compares the liquid interference determination data with reference liquid determination data obtained from a preset database. The reference liquid determination data includes reference determination grayscale values ​​and reference determination echo intensity.

[0081] It should be explained that the reference liquid determination data is preset by designated personnel and stored in a preset database.

[0082] J3. If any liquid interference judgment data is not less than the corresponding reference liquid judgment data, then the ultrasound imaging parameters are optimized; otherwise, no additional processing is performed.

[0083] The specific steps for optimizing ultrasound imaging parameters are as follows:

[0084] First, the difference between the liquid interference judgment data and the corresponding reference liquid judgment data is quantified to obtain the corresponding liquid interference difference quantification value.

[0085] Specifically, the liquid interference judgment data that is not less than the corresponding reference liquid judgment data is subjected to difference quantization. Difference quantization means that the result of the difference calculation between the liquid interference judgment data and the reference liquid judgment data is compared with the reference liquid judgment data.

[0086] Next, an imaging parameter optimization ratio group is obtained based on the liquid interference difference quantization value mapping. The imaging parameters are then optimized and compensated according to the imaging parameter optimization ratio group to obtain the corresponding imaging parameters. The scanning is then performed again based on the imaging parameters. The imaging parameter optimization ratio group includes the probe frequency adjustment ratio and the echo gain adjustment ratio. The imaging parameters include the probe frequency and the echo gain.

[0087] Specifically, a mapping set of liquid interference difference quantification values ​​and imaging parameter optimization ratio groups is pre-constructed in a preset database. The liquid interference difference quantification values ​​obtained in real time are input into the mapping set, and the corresponding imaging parameter optimization ratio groups are output. This mapping set represents the set of mapping relationships between liquid interference difference quantification values ​​and imaging parameter optimization ratio groups.

[0088] Furthermore, the optimization compensation operation represents the product operation between the imaging parameter optimization ratio group and the corresponding imaging parameter.

[0089] In this embodiment, quantifying the difference in liquid interference helps to more accurately reflect the degree of interference of uterine fluid on ultrasound imaging and provides a basis for optimization decisions. At the same time, by mapping and optimizing the ratio group, it is helpful to dynamically adjust the imaging parameters according to the degree of interference, thereby improving the imaging quality. Furthermore, the optimized imaging parameters help to better eliminate liquid interference, thereby improving the clarity and accuracy of uterine myocyte images. Through the above process, liquid interference can be reduced more effectively in ultrasound examination, thereby optimizing the quality of uterine myocyte images and ensuring the accuracy of uterine myocyte image information and the reliability of the corresponding tension analysis.

[0090] Optionally, the specific steps for tension feedback on the scar region of resting uterine myocyte images are as follows:

[0091] Step 1: Obtain the color label data of the scar region of the resting uterine myocyte image, input the color label data into the image elasticity quantitative value model, and output the corresponding image elasticity quantitative value, which is recorded as the resting image elasticity quantitative value.

[0092] Step 2: Transmit the resting image elasticity values ​​of the scar region and the ultrasound elasticity images of the resting uterine myocytes to the preset medical staff terminal.

[0093] In this embodiment, by inputting the color-coded data of the scar region of the resting uterine myocyte image into the image elasticity quantification model, it is beneficial to obtain more accurate resting image elasticity quantification values. This helps to more accurately analyze and quantify the elastic characteristics of uterine myocytes in the resting state, thereby providing more accurate data support for subsequent feedback. Furthermore, by combining the elasticity quantification values ​​of the scar region with the ultrasound image, it is beneficial to monitor the elasticity status of resting uterine myocytes more comprehensively and accurately, thereby helping medical staff to more efficiently assess the corresponding tension characteristics.

[0094] The specific method for obtaining the image elastic force quantitative model is as follows:

[0095] The first step is to obtain the color identification data of the corresponding uterine myocyte image and perform data normalization processing. The color identification data includes the RGB values ​​of the color, the area of ​​the color region, and the elastic modulus.

[0096] It should be added that loading the uterine myocyte image and obtaining its RGB values ​​to get the corresponding color RGB values ​​can usually be done by using an image processing library such as OpenCV to read the image and store it as a NumPy array; by using a preset threshold to extract specific RGB values, by specifying the range of RGB values ​​to find which regions in the uterine myocyte image match the target color, the corresponding RGB regions are extracted, and the area of ​​the corresponding color region is calculated using the number of pixels in the uterine myocyte image.

[0097] The second step is to classify and number the colors of the uterine myocyte images according to the RGB values, and at the same time, obtain the corresponding color identification analysis parameters from the preset database. The color identification analysis parameters include the color identification analysis ratio and the color category analysis weight. The color identification analysis ratio includes the RGB value analysis ratio, the region area analysis ratio, and the elastic modulus analysis ratio.

[0098] Specifically, the color identifier analysis proportion represents the degree of influence of color identifier data on the initial quantization value of image elasticity. Each color identifier data has a unique mapping relationship with its corresponding color category analysis proportion, and the value ranges from 0 to 1. For example, by constructing a mapping set between color identifier data and preset color category analysis proportions, the real-time color RGB values, color area, and elastic modulus are input into the mapping set to obtain the corresponding RGB value analysis proportion, area analysis proportion, and elastic modulus analysis proportion, which respectively represent the degree of influence of color RGB values, color area, and elastic modulus on the initial quantization value of image elasticity, and the sum of the three is 1.

[0099] Specifically, the color category analysis weight represents the degree of influence of each color RGB value on the image elasticity quantitative model. Each color RGB value has a unique mapping relationship with its corresponding color category analysis weight, and the value ranges from 0 to 1. For example, a mapping set of each color RGB value and a preset color category analysis weight is constructed. Real-time color RGB values ​​are input into the mapping set to obtain the corresponding color category analysis weights, each representing the degree of influence of each color RGB value on the image elasticity quantitative model, and the sum of the color category analysis weights corresponding to each color RGB value is 1.

[0100] The third step involves weighting and coupling the color identifier data with the corresponding color identifier analysis proportion to obtain the initial quantization value of image elasticity.

[0101] The fourth step involves summing the initial quantized elastic force values ​​of various RGB colors and their corresponding color category analysis weights, and then performing an average calculation to obtain the image elastic force quantified value model. This model is used to quantify the tension characteristics of the corresponding image region through the elasticity map representation of the ultrasonic elastic image.

[0102] The specific constraint expression for the image elasticity quantitative model is as follows:

[0103]

[0104] In the formula, n represents the color RGB category number, n = 1, 2, ..., N, and N represents the total number of color RGB categories, C_RGB n CA represents the RGB values ​​of the nth color class. n A_EM represents the area of ​​the RGB color region of the nth color class. n Let α_rgb represent the elastic modulus of the nth color (RGB), β_area represent the proportion of RGB value analysis, and γ_ela represent the proportion of area analysis. represents the color category analysis weight of the nth color (RGB), and EQV represents the image elasticity value.

[0105] In this embodiment, the algorithm combines color identifier data and color identifier analysis parameters to obtain the corresponding image elasticity quantitative value. In the formula, a larger RGB value indicates a higher degree of elasticity and potentially larger tension feature data; a larger color area indicates a higher proportion of RGB in the image, potentially a larger tension range, and thus a larger image elasticity quantitative value; a larger elastic modulus indicates a higher degree of elasticity in the corresponding image area, and thus a larger image elasticity quantitative value. By analyzing the image elasticity quantitative value, not only are the tension features of the corresponding image area comprehensively quantified, but the tension data of the uterine myocyte image is also fed back to the pre-set medical personnel more accurately, thereby ensuring the accuracy of the uterine myocyte tension analysis.

[0106] like Figure 3 The flowchart shown is a process for determining image tension performance in the uterine myocyte tension analysis method based on uterine myocyte activity images provided in this embodiment of the invention. The specific logic is as follows: When the tension analysis mode is the uterine contraction state analysis mode, the ultrasound imaging frequency is adjusted to the maximum value of the imaging frequency, and then the image elasticity quantitative value within a preset time period is obtained and recorded as the uterine contraction image elasticity quantitative value. Then, based on the uterine contraction image elasticity quantitative value within the preset time period, the corresponding average uterine contraction image elasticity quantitative value is obtained. The average uterine contraction image elasticity quantitative value is compared with the reference uterine contraction image elasticity quantitative value. If the average uterine contraction image elasticity quantitative value is not less than the reference uterine contraction image elasticity quantitative value, the real-time requirement level of uterine contraction state tension monitoring is recorded as a first-level requirement; otherwise, it is a second-level requirement. Then, according to the determination result of the real-time requirement level of uterine contraction state tension monitoring, the corresponding imaging frequency adjustment measures are taken. The uterine myocyte images of uterine contraction are divided to obtain the corresponding uterine contraction scar region for priority scar feedback. Through the above process, not only is the real-time performance and sensitivity of uterine contraction monitoring improved, but also, by prioritizing the feedback of scar areas, it helps to promptly detect possible scar problems, thereby helping the pre-set medical staff to make more accurate decisions.

[0107] It is important to understand that the determination of image tension based on images of uterine contractions and the implementation of corresponding tension analysis optimization measures are as follows:

[0108] H1, when the tension analysis mode is obtained as the uterine contraction state analysis mode, the ultrasound imaging frequency is adjusted to the maximum imaging frequency; where the maximum imaging frequency represents the highest imaging frequency supported by the current ultrasound imaging equipment.

[0109] H2, obtain the color identification data of uterine contraction myocyte images within a preset time period, input it into the image elasticity quantitative value model, and output the corresponding image elasticity quantitative value, which is recorded as the uterine contraction image elasticity quantitative value.

[0110] H3 calculates the average elasticity value of uterine contraction images by averaging the elasticity values ​​within a preset time period.

[0111] H4 compares the average elasticity value of the uterine contraction image with the reference elasticity value of the uterine contraction image obtained from the preset database, takes corresponding image monitoring and early warning measures, and obtains the corresponding judgment result. If the average elasticity value of the uterine contraction image is not less than the reference elasticity value of the uterine contraction image, the real-time requirement level of uterine contraction tension monitoring is recorded as Level 1 requirement; otherwise, it is Level 2 requirement.

[0112] Specifically, the elasticity values ​​of the reference uterine contraction images are preset by staff and stored in a preset database.

[0113] Secondly, the higher the level of real-time requirement for monitoring uterine contraction tension, the lower the real-time requirement for monitoring uterine contraction tension; for example, level one requirement is higher than level two requirement.

[0114] H5, based on the determination of the real-time requirement level for uterine contraction tension monitoring, corresponding imaging frequency adjustment measures are taken.

[0115] H6 divides the images of uterine contraction myocytes to obtain the corresponding uterine contraction scar regions, and performs scar-priority feedback on the uterine contraction scar regions. Scar-priority feedback means that the analysis results of the uterine contraction scar regions are given priority feedback.

[0116] In this embodiment, adjusting the ultrasound imaging frequency to its maximum value helps ensure more accurate imaging under high tension, allowing for a clearer presentation of the details of uterine myocytes. Furthermore, the combination of color coding and elasticity quantification helps to more accurately quantify the tension of myocytes during uterine contractions, thus providing strong analytical support. Simultaneously, automated early warning measures can respond promptly to different tension states, improving the real-time nature and sensitivity of uterine contraction monitoring. Moreover, prioritizing feedback on scar areas helps to promptly detect potential scar problems. Especially during uterine contractions, timely feedback on scar formation or changes helps pre-planned medical staff make more accurate decisions.

[0117] Optionally, the specific process of taking corresponding image monitoring and early warning measures is as follows: when the elasticity value of the uterine contraction image is not less than the elasticity value of the reference uterine contraction image, a first-level early warning is issued. The first-level early warning indicates that the uterine contraction tension of the object to be analyzed and the preset medical staff is abnormal through sound prompts; when the number of first-level early warnings exceeds the preset number, a second-level early warning is issued. The second-level early warning includes high-frequency sound warnings and display warnings.

[0118] In this embodiment, the sound prompts can quickly alert the pre-selected medical staff to the drastic changes in uterine contraction tension, ensuring timely intervention and providing clear audible feedback so that they can quickly recognize the changes in uterine muscle cell tension and make timely judgments. In addition, the dual reminders of high-frequency sound warnings and visual warnings can more effectively attract the attention of the pre-selected medical staff, preventing them from ignoring the drastic changes in uterine contraction status. At the same time, the combination of sound and visual prompts ensures that the pre-selected medical staff can receive warnings through different senses, adapting to different work environments and medical scenarios.

[0119] Optionally, based on the determination of the real-time requirement level for uterine contraction tension monitoring, corresponding imaging frequency adjustment measures can be taken. The specific process is as follows:

[0120] V1, if there is a continuous preset number of preset time periods for monitoring the real-time tension of uterine contractions, and the requirement level is level two, then the difference between the average elasticity value of the uterine contraction image and the corresponding reference elasticity value of the uterine contraction image for all preset time periods is quantified, and then the mean is calculated to obtain the corresponding average difference value.

[0121] Among them, differential quantification represents the ratio of the difference between the average elasticity value of the uterine contraction image and the corresponding elasticity value of the reference uterine contraction image to the elasticity value of the reference uterine contraction image.

[0122] V2, based on the average difference value mapping, obtains the imaging frequency reduction factor, and adjusts the ultrasound imaging frequency by the imaging frequency reduction factor.

[0123] Specifically, adjusting the ultrasound imaging frequency by reducing the imaging frequency by a factor means multiplying the reduction factor of the imaging frequency with the ultrasound imaging frequency to obtain the corresponding ultrasound imaging frequency for ultrasound imaging.

[0124] V3: If the real-time requirement level for monitoring uterine contraction tension during a preset time period is Level 1, the ultrasound imaging frequency will be adjusted back to its maximum value.

[0125] In this embodiment, the highest imaging frequency can present the details of uterine contraction status more clearly and in real time, avoiding the omission of any key pathological changes and improving the accuracy of diagnosis. Furthermore, automatically adjusting the imaging parameters according to changes in different demand levels helps to adapt to different clinical situations. By dynamically adjusting the imaging frequency according to the real-time demand level of uterine contraction tension monitoring, not only can the quality and real-time performance of uterine contraction images be guaranteed, but computing resources can also be saved to improve the efficiency of equipment use.

[0126] Optionally, scar-priority feedback is performed on the uterine contraction scar image domain. The specific process is as follows: the color identification data of the uterine contraction scar image domain is input into the image elasticity quantitative value model, and the corresponding image elasticity quantitative value is output and recorded as the uterine contraction scar image elasticity quantitative value; the uterine contraction scar elasticity quantitative value sequence is obtained by statistically analyzing the uterine contraction scar image elasticity quantitative values ​​output within a preset time period in chronological order; the uterine contraction scar elasticity quantitative value sequence corresponding to the uterine contraction myocyte images within the preset time period is preferentially transmitted to the preset medical staff terminal.

[0127] In this embodiment, the color-coded data is first converted into corresponding elasticity values, which more accurately reflects the actual condition of the uterine contraction scar and ensures more accurate monitoring. Furthermore, the feedback to the scar region is quantified, allowing medical staff to more clearly see the changing trends of the uterine contraction scar and make timely judgments. Simultaneously, the sorted elasticity value sequence helps to dynamically track changes in the uterine contraction scar over time. By prioritizing the transmission of the elasticity value sequence of the scar image, it ensures that medical staff receive uterine contraction scar-related data first during real-time monitoring, thus providing more real-time data support for subsequent decisions by the pre-set medical staff.

[0128] In summary, this invention obtains the tension analysis mode of the object to be analyzed. If it is a resting state analysis mode, a resting uterine myocyte image is obtained, and the effectiveness of the ultrasound scan is evaluated to determine whether to rescan. Based on the evaluation result, the corresponding uterine myocyte tension analysis result is obtained. If it is a uterine contraction state analysis mode, a uterine contraction uterine myocyte image is obtained, and the image tension performance is determined. Then, tension analysis optimization measures are taken to obtain the uterine contraction uterine myocyte tension analysis result. Finally, the uterine myocyte tension analysis result is transmitted to the medical staff's terminal, thereby providing the medical staff with more detailed tension analysis results and improving the reliability of the uterine myocyte tension analysis result. This effectively solves the problem of unstable reliability of uterine myocyte tension analysis results caused by differences in ultrasound probe scanning in the prior art.

[0129] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0131] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0134] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for analyzing uterine myocyte tension based on images of uterine myocyte activity, characterized in that, Includes the following steps: An initial judgment image is obtained through an initial scan. Based on the initial judgment image, a tension analysis state determination is performed to select the tension analysis mode of the object to be analyzed. The tension analysis mode includes a resting state analysis mode and a uterine contraction state analysis mode. If the tension analysis mode is the resting state analysis mode, then ultrasound elastography is performed to obtain the corresponding resting uterine myocyte image. The effectiveness of the ultrasound scan is evaluated based on the resting uterine myocyte image to determine whether to rescan. If rescan, the effectiveness of the ultrasound scan is evaluated based on the resting uterine myocyte image obtained by the rescan. The resting uterine myocyte tension analysis result is obtained based on the resting uterine myocyte image that meets the scan effectiveness conditions. Otherwise, the uterine myocyte tension analysis result is obtained directly based on the resting uterine myocyte image. If the tension analysis mode is the uterine contraction state analysis mode, then ultrasound elastography scan is performed to obtain the corresponding uterine contraction myocyte images. Based on the uterine contraction myocyte images, the image tension performance is determined, and corresponding tension analysis optimization measures are taken to obtain the corresponding uterine contraction myocyte tension analysis results. The process involves determining the image tension based on images of uterine contraction myocytes and implementing corresponding tension analysis optimization measures to obtain the corresponding uterine contraction myocyte tension analysis results. The specific steps are as follows: H1, when the tension analysis mode is obtained as the uterine contraction state analysis mode, adjust the ultrasound imaging frequency to the maximum value of the imaging frequency. H2, obtain the color identification data of the uterine contraction myocyte images within a preset time period, input it into the image elasticity quantitative value model, and output the corresponding image elasticity quantitative value, which is recorded as the uterine contraction image elasticity quantitative value; H3, calculates the average elasticity value of the contraction image within a preset time period by averaging the elasticity values ​​of the contraction image. H4 compares the average elasticity value of the uterine contraction image with the reference elasticity value of the uterine contraction image obtained from the preset database, takes corresponding image monitoring and early warning measures, and obtains the corresponding judgment result. If the average elasticity value of the uterine contraction image is not less than the elasticity value of the reference uterine contraction image, the real-time requirement level of uterine contraction tension monitoring is recorded as Level 1 requirement; otherwise, it is Level 2 requirement. H5, based on the determination of the real-time requirement level for uterine contraction tension monitoring, take corresponding imaging frequency adjustment measures; H6, the images of uterine contraction myocytes are divided to obtain the corresponding uterine contraction scar regions, and scar priority feedback is performed on the uterine contraction scar regions. The scar priority feedback means that the analysis results of the uterine contraction scar regions are given priority feedback. The obtained uterine myocyte tension analysis results are transmitted to a preset medical staff terminal. The uterine myocyte tension analysis results include resting uterine myocyte tension analysis results and uterine contraction uterine myocyte tension analysis results. The uterine myocyte tension analysis results represent a collection of uterine myocyte images, elastograms, and uterine myocyte tension analysis data.

2. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 1, characterized in that, The specific steps for evaluating the effectiveness of ultrasound scanning based on resting uterine myocyte images to determine whether a rescan should be performed are as follows: K1, the ultrasound scan effectiveness evaluation is performed on the acquired resting uterine myocyte image to obtain the ultrasound detection effectiveness judgment value, which is used to determine the effectiveness of the uterine myocyte image of the current ultrasound scan. K2, if the ultrasound detection validity judgment value is not less than the ultrasound detection evaluation threshold obtained from the preset database, it means that the resting uterine myocyte image is qualified and K4 is executed. If the ultrasound detection validity judgment value is less than the ultrasound detection evaluation threshold obtained from the preset database, the preset medical staff is prompted to change the scanning area for rescanning and K3 is executed. K3, based on the liquid interference determination data, determines whether to optimize the ultrasound imaging parameters, obtains a qualified resting uterine myocyte image and executes K4. The liquid interference determination data includes the average gray value of the image and the average echo intensity of the image. K4. Based on the color identifier of qualified resting myocyte images, the resting myocyte images are divided into scar regions and non-scar regions. Tension feedback is then performed on the scar regions of the resting myocyte images. The tension feedback means that the tension status of the scar regions in the resting myocyte images is fed back to the preset medical staff.

3. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 2, characterized in that, The specific process for obtaining the ultrasound detection validity determination value is as follows: Ultrasound detection and evaluation data of resting uterine myocytes are obtained, including echo intensity, image gray value, elastic modulus, attenuation coefficient and signal-to-noise ratio; Ultrasonic evaluation parameters are obtained from a preset database. These parameters include ultrasonic evaluation reference values ​​and ultrasonic evaluation influence weights. The ultrasonic evaluation reference values ​​include echo intensity reference range, gray value reference range, minimum elastic modulus limit value, minimum attenuation coefficient critical value, and minimum signal-to-noise ratio classification value. The ultrasonic evaluation influence weights include echo intensity influence weight, gray value influence weight, elastic modulus influence weight, attenuation coefficient influence weight, and signal-to-noise ratio influence weight. The echo intensity is quantized by performing range deviation calculation on the corresponding echo intensity reference range to obtain the echo intensity deviation. The grayscale value of the image is subjected to range deviation quantization operation with the corresponding grayscale value reference range to obtain the grayscale value deviation amount; The deviation of the elastic modulus, attenuation coefficient and signal-to-noise ratio from the corresponding ultrasonic evaluation reference values ​​is quantified to obtain the corresponding deviation values ​​of elastic modulus, attenuation coefficient and signal-to-noise ratio. By coupling the deviations in echo intensity, grayscale value, elastic modulus, attenuation coefficient, and signal-to-noise ratio with the corresponding weights of ultrasound evaluation, an ultrasound detection validity determination value is obtained. This ultrasound detection validity determination value is used to determine the reliability of the resting uterine myocyte image obtained by ultrasound elastography.

4. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 2, characterized in that, The specific process for determining whether to optimize ultrasound imaging parameters based on liquid interference data is as follows: Obtain corresponding liquid interference determination data based on resting uterine myocyte images; The liquid interference determination data is compared with reference liquid determination data obtained from a preset database, wherein the reference liquid determination data includes reference determination grayscale value and reference determination echo intensity; If any liquid interference judgment data is not less than the corresponding reference liquid judgment data, then the ultrasound imaging parameters are optimized; otherwise, no additional processing is performed. The specific steps for optimizing the ultrasound imaging parameters are as follows: The difference between the liquid interference judgment data and the corresponding reference liquid judgment data is quantified to obtain the corresponding liquid interference difference quantification value. An optimized ratio group of imaging parameters is obtained by mapping the difference in liquid interference values. The imaging parameters are then optimized and compensated according to the optimized ratio group to obtain the corresponding imaging parameters. The scanning is then performed again based on the imaging parameters. The optimized ratio group of imaging parameters includes the probe frequency adjustment ratio and the echo gain adjustment ratio. The imaging parameters include the probe frequency and the echo gain.

5. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 2, characterized in that, The specific steps for applying tension feedback to the scar region of resting uterine myocyte images are as follows: Step 1: Obtain the color identification data of the scar region of the resting uterine myocyte image, input the color identification data into the image elasticity quantitative value model, and output the corresponding image elasticity quantitative value, which is recorded as the resting image elasticity quantitative value. Step 2: Transmit the resting image elasticity values ​​of the scar region and the ultrasound elasticity images of the resting uterine myocytes to the preset medical staff terminal.

6. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 5, characterized in that, The specific method for obtaining the image elasticity quantitative model is as follows: The color identification data of the corresponding uterine myocyte image is obtained and normalized. The color identification data includes color RGB values, color area area and elastic modulus. The colors of the uterine myocyte images are classified and numbered according to the RGB values. At the same time, the corresponding color identification analysis parameters are obtained from the preset database. The color identification analysis parameters include the color identification analysis ratio and the color category analysis weight. The color identification analysis ratio includes the RGB value analysis ratio, the region area analysis ratio, and the elastic modulus analysis ratio. After weighting the color identifier data and coupling it with the corresponding color identifier analysis ratio, the initial quantization value of image elasticity is obtained. The initial quantized elastic force values ​​of various RGB colors are accumulated and summed with the corresponding color category analysis weights, and then the mean is calculated to obtain the image elastic force quantified value model. The image elastic force quantified value model is used to quantify the tension characteristics of the corresponding image region through the elasticity map of the ultrasonic elastic image.

7. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 1, characterized in that, The specific process for taking corresponding image monitoring and early warning measures is as follows: When the elasticity value of the uterine contraction image is not less than the elasticity value of the reference uterine contraction image, a Level 1 warning is issued. The Level 1 warning indicates that the abnormal change in uterine contraction tension is indicated by sound to the object to be analyzed and the preset medical staff. When the number of Level 1 warnings exceeds the preset number, a Level 2 warning will be issued, which includes a high-frequency audible warning and a visual warning.

8. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 1, characterized in that, The specific process for adjusting the imaging frequency based on the determination of the real-time requirement level for uterine contraction tension monitoring is as follows: If there is a continuous preset number of preset time periods for monitoring the contraction tension, and the real-time requirement level is level two, then the difference between the average contraction image elasticity quantitative value and the corresponding reference contraction image elasticity quantitative value of all preset time periods is quantified, and then the mean is calculated to obtain the corresponding average difference value. The imaging frequency reduction factor is obtained by mapping the average difference value, and the ultrasound imaging frequency is adjusted by the imaging frequency reduction factor. If the real-time requirement for monitoring uterine contraction tension during a preset time period is Level 1, the ultrasound imaging frequency will be adjusted back to its maximum value.

9. The method for analyzing uterine myocyte tension based on uterine myocyte activity images as described in claim 1, characterized in that, The specific process for prioritizing scar feedback on the uterine contraction scar region is as follows: The color identification data of the uterine contraction scar region is input into the image elasticity quantitative value model, and the corresponding image elasticity quantitative value is output, which is recorded as the uterine contraction scar image elasticity quantitative value. The elasticity values ​​of uterine contraction scars are obtained by statistically analyzing the elasticity values ​​of the images of uterine contraction scars output within a preset time period in chronological order. The sequence of quantitative values ​​of uterine contraction scar elasticity corresponding to the images of uterine myocytes during a preset time period is preferentially transmitted to the preset medical staff terminal.

Images