Pubic symphysis measurement method and device, computer device and storage medium

Abstract

The application relates to the technical field of ultrasonic imaging, and discloses a pubic symphysis measurement method and device, computer equipment and a storage medium, the method comprising the following steps: acquiring a target ultrasonic image meeting pubic symphysis measurement requirements; performing image segmentation on the target ultrasonic image to generate a segmented image containing a pubic symphysis region, wherein the pubic symphysis region comprises a separated first region and a second region; positioning a first end point of the pubic symphysis in the first region and a second end point of the pubic symphysis in the second region; and taking the interval between the first end point and the second end point as a pubic symphysis interval. The application can automatically measure the pubic symphysis interval, has high measurement efficiency, can more accurately extract the pubic symphysis region, and guarantees the accuracy of pubic symphysis measurement results.

Description

Technical Field

[0001] This invention relates to the field of ultrasound imaging technology, and more specifically to a method, apparatus, computer equipment, and storage medium for measuring the pubic symphysis. Background Technology

[0002] Measuring the distance between the pubic symphysis helps to assess the separation status of the two pubic symphysis and understand the stability of the pubic symphysis.

[0003] Current technology for measuring the pubic symphysis is limited to manual measurement. Clinicians and other users scan the lower abdomen of the subject (e.g., a patient) with an ultrasound probe to obtain an ultrasound image of the pubic symphysis. They then locate the widest part of the pubic symphysis in the ultrasound image, specifically the point where the pubic ramus curves parallel to the surrounding surface. This manual measurement method is not only inefficient but also relies on user subjectivity, easily leading to inaccurate measurements. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment and storage medium for measuring the pubic symphysis, so as to solve the problem of inaccurate measurement of the pubic symphysis distance.

[0005] In a first aspect, the present invention provides a method for measuring the pubic symphysis, comprising:

[0006] Acquire target ultrasound images that meet the requirements for pubic symphysis measurement;

[0007] The target ultrasound image is segmented to generate a segmented image containing the pubic symphysis region, which includes a separated first region and a second region.

[0008] Locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region;

[0009] The distance between the first endpoint and the second endpoint is taken as the pubic symphysis distance.

[0010] In some optional implementations, acquiring the target ultrasound image that meets the requirements for pubic symphysis measurement includes:

[0011] Acquire the ultrasound image to be determined;

[0012] Determine whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement;

[0013] If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, a target ultrasound image is generated based on the ultrasound image to be determined.

[0014] In some optional implementations, determining whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement includes:

[0015] Identify the bony regions related to bony structures in the ultrasound images to be determined;

[0016] The similarity between the bony region image and the standard ultrasound image containing the pubic symphysis is determined by comparing their features.

[0017] If the similarity is greater than a preset threshold, the ultrasound image to be determined is determined to meet the requirements for pubic symphysis measurement.

[0018] In some optional implementations, determining whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement includes:

[0019] The image quality of the ultrasound image to be determined is determined based on a deep learning-based target detection model, and it is then determined whether the image quality of the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0020] In some alternative implementations, the method further includes:

[0021] If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, first information indicating that the ultrasound image to be determined meets the requirements for pubic symphysis measurement is displayed;

[0022] And / or, if the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement, display second information indicating that the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement.

[0023] In some optional implementations, the step of segmenting the target ultrasound image to generate a segmented image containing the pubic symphysis region includes:

[0024] The target ultrasound image is subjected to shape prediction and image segmentation to determine a mask image corresponding to the location of the pubic symphysis region. The shape prediction is used to remove regions that do not match the shape of the pubic symphysis.

[0025] The mask image is post-processed to generate a segmented image containing two segmented regions. One segmented region in the segmented image is the first region of the pubic symphysis region, and the other segmented region is the second region of the pubic symphysis region.

[0026] In some optional implementations, the step of performing shape prediction and image segmentation on the target ultrasound image to determine a mask image corresponding to the location of the pubic symphysis region includes:

[0027] The pubic symphysis region in the target ultrasound image is located using a deep learning image segmentation model. Shape prediction and image segmentation are performed on the target within the pubic symphysis region to generate a mask image corresponding to the location of the pubic symphysis region.

[0028] In some optional implementations, the post-processing of the mask image to generate a segmented image containing two segmented regions includes:

[0029] If the number of segmented regions in the mask image exceeds 2, perform a region search on the mask image and retain the two segmented regions with the largest areas.

[0030] Morphological processing and / or edge smoothing are performed on the preserved segmented regions to obtain a segmented image containing two segmented regions.

[0031] In some alternative implementations, locating the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region includes:

[0032] The endpoint in the first region that is closest to the second region is taken as the first endpoint of the pubic symphysis, and the endpoint in the second region that is closest to the first region is taken as the second endpoint of the pubic symphysis.

[0033] In some alternative implementations, the method further includes:

[0034] The numerical value of the pubic symphysis distance is displayed, and the first endpoint, the second endpoint, and the line segment between the first endpoint and the second endpoint are marked and displayed in the target ultrasound image.

[0035] In a second aspect, the present invention provides a pubic symphysis measuring device, comprising:

[0036] The acquisition module is used to acquire target ultrasound images that meet the requirements for pubic symphysis measurement;

[0037] The processing module is used to perform image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region, wherein the pubic symphysis region includes a separated first region and a second region;

[0038] The positioning module is used to locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region; and to use the distance between the first endpoint and the second endpoint as the pubic symphysis distance.

[0039] Thirdly, the present invention provides an ultrasonic device, including: a processor, an ultrasonic probe, and a display;

[0040] The processor is communicatively connected to the ultrasound probe and the display, and the processor is used to execute the pubic symphysis measurement method of the first aspect or any corresponding embodiment described above.

[0041] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the pubic symphysis measurement method of the first aspect or any corresponding embodiment thereof.

[0042] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the pubic symphysis measurement method of the first aspect or any corresponding embodiment thereof.

[0043] This invention, when measuring the pubic symphysis distance, performs image segmentation on a target ultrasound image that meets the measurement requirements to extract the pubic symphysis region containing two separate areas. The endpoints of each region are then determined, and the distance between these two endpoints is taken as the pubic symphysis distance. This method can automatically measure the pubic symphysis distance without manual intervention, resulting in high measurement efficiency and effectively avoiding the influence of operator subjectivity. Furthermore, using a high-quality target ultrasound image as the basis for measurement and performing image segmentation not only reduces the impact of artifacts but also accurately extracts the pubic symphysis region, ensuring the accuracy of the measurement results. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating the pubic symphysis measurement method according to an embodiment of the present invention;

[0046] Figure 2 This is a flowchart illustrating a method for measuring the pubic symphysis according to an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram illustrating the evaluation effect of ultrasound images according to an embodiment of the present invention;

[0048] Figure 4 This is an illustration of the effect of automatic measurement of pubic symphysis distance according to an embodiment of the present invention;

[0049] Figure 5This is a schematic flowchart of an automatic measurement of the pubic symphysis distance according to an embodiment of the present invention;

[0050] Figure 6 This is a structural block diagram of the pubic symphysis measuring device according to an embodiment of the present invention;

[0051] Figure 7 This is a schematic diagram of the hardware structure of the ultrasound device according to an embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] The pubic symphysis is a pubic disc connecting the two pubic symphysis surfaces via fibrocartilage; the symphysial surface refers to the elliptical rough surface on the inner side of the junction of the superior and inferior pubic rami.

[0054] During pregnancy, the pelvic diameter changes as the fetus grows and develops. To ensure the fetus can pass smoothly through the pelvis, a slight separation of the pubic symphysis may occur. This separation temporarily increases the pelvic diameter to facilitate delivery. However, the essence of pubic symphysis separation is displacement at the fibrocartilaginous junction of the two pubic bones at the front of the pelvis, resulting in a widened distance between the pubic symphysis and vertical misalignment. This can lead to difficulty in raising the lower limbs and is classified as a soft tissue injury, clinically known as pubic symphysis misalignment. Measuring the distance between the pubic symphysis bones can effectively assess the degree of separation.

[0055] Current manual measurement methods are inefficient; when locating the measurement location, they rely on the experience of doctors and other operators, which introduces a certain degree of subjectivity; and the pubic symphysis is prone to misjudgment during scanning due to artifacts, blurred images, and the presence of multiple bony structures in the same image, which can easily lead to significant errors in measurement results due to subjective bias.

[0056] This invention provides a method for measuring the pubic symphysis. By segmenting an ultrasound image containing the pubic symphysis, the pubic symphysis region is determined, and the two endpoints representing the pubic symphysis distance can be located. By calculating the distance between the two endpoints, the pubic symphysis distance can be automatically measured. This method has high measurement efficiency, reduces the influence of operator subjectivity, and ensures measurement accuracy.

[0057] According to an embodiment of the present invention, a method for measuring the pubic symphysis is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0058] This embodiment provides a method for measuring the pubic symphysis, which can be applied to the processor of an ultrasound device. Figure 1 This is a flowchart of a pubic symphysis measurement method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps.

[0059] Step S101: Obtain the target ultrasound image that meets the requirements for pubic symphysis measurement.

[0060] In this embodiment, when it is necessary to measure the pubic symphysis distance, an ultrasound image that meets the preset pubic symphysis measurement requirements can be obtained. For ease of distinction and description, this ultrasound image is referred to as the target ultrasound image.

[0061] To meet the requirements for pubic symphysis measurement, the target ultrasound image needs to include the pubic symphysis region. For example, the target ultrasound image could be a pubic symphysis ultrasound image obtained from an abdominal scan. Furthermore, the target ultrasound image also needs to be capable of pubic symphysis measurement, i.e., capable of measuring the distance between the pubic symphysis bones; for example, the target ultrasound image should be able to show the gap between the pubic symphysis bones.

[0062] In this embodiment, when it is necessary to measure the pubic symphysis distance, the operator using the ultrasound equipment can actively provide the target ultrasound image so that the pubic symphysis distance can be measured based on the target ultrasound image. This embodiment does not limit the method of acquiring the target ultrasound image.

[0063] Step S102: Perform image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region, which includes a separated first region and a second region.

[0064] In this embodiment, the target ultrasound image is segmented to identify the region corresponding to the pubic symphysis, i.e., the pubic symphysis region, thereby obtaining an image containing the pubic symphysis region, i.e., a segmented image.

[0065] For a target ultrasound image that meets the requirements for pubic symphysis measurement, the pubic symphysis consists of two separate parts. After image segmentation, the regions corresponding to the two parts can be identified, namely the first region and the second region. The first region and the second region are separate, that is, they are not connected.

[0066] Generally, the pubic symphysis includes the left pubic symphysis and the right pubic symphysis. In the target ultrasound image, the left and right regions can be extracted. The left region corresponds to the left pubic symphysis, and the right region corresponds to the right pubic symphysis.

[0067] Image segmentation of the target ultrasound image can be performed using traditional methods, such as the Otsu method (also known as the Otsu method) or the watershed method; alternatively, image segmentation can be achieved using artificial intelligence algorithms, such as the U-Net segmentation model based on deep learning, to segment the target ultrasound image and obtain the segmentation result of the pubic symphysis.

[0068] Step S103: Locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region.

[0069] In this embodiment, the first region is a portion of the pubic symphysis. Based on the contour of the first region, an endpoint of the pubic symphysis, namely the first endpoint, can be determined; the first endpoint is a feature point of the pubic symphysis surface in the first region. Similarly, a second endpoint can be determined from the second region, which is a feature point of the pubic symphysis surface in the second region.

[0070] Among them, the first endpoint and the second endpoint can be located based on feature point detection and other methods.

[0071] In this embodiment, the segmented image may include only the first and second regions of the pubic symphysis, which can reduce interference from other regions and more accurately locate the endpoints of each region for more precise measurement.

[0072] Step S104: The distance between the first endpoint and the second endpoint is taken as the pubic symphysis distance.

[0073] In this embodiment, after determining the two endpoints of the pubic symphysis (i.e., the first endpoint and the second endpoint), the distance between the two endpoints can be calculated. This distance is the pubic symphysis distance, and the state of the subject's pubic symphysis can be assessed based on this pubic symphysis distance.

[0074] For example, the pubic symphysis distance can be output so that doctors can perform subsequent operations based on the automatically measured pubic symphysis distance.

[0075] The pubic symphysis measurement method provided in this embodiment, when it is necessary to measure the pubic symphysis distance, performs image segmentation on the target ultrasound image that meets the requirements for pubic symphysis measurement to extract the pubic symphysis region containing two separate areas, and then determines the endpoints of each region. The distance between these two endpoints can be used as the pubic symphysis distance. This method can automatically measure the pubic symphysis distance without manual intervention by the user, which not only has high measurement efficiency but also effectively avoids the influence of the operator's subjective factors. Furthermore, using a high-quality target ultrasound image as the basis for measurement and performing image segmentation processing can not only reduce the influence of artifacts but also accurately extract the pubic symphysis region, ensuring the accuracy of the pubic symphysis measurement results.

[0076] This embodiment provides a method for measuring the pubic symphysis, which can be applied to the processor of an ultrasound device. Figure 2 This is a flowchart of a pubic symphysis measurement method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps.

[0077] Step S201: Obtain the target ultrasound image that meets the requirements for pubic symphysis measurement.

[0078] Please see details Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0079] In some optional implementations, the above step S201 "acquiring a target ultrasound image that meets the requirements for pubic symphysis measurement" may include the following steps A1 to A3.

[0080] Step A1: Obtain the ultrasound image to be determined.

[0081] In this embodiment, when it is necessary to measure the pubic symphysis distance, the user can provide one or more ultrasound images that need to be judged to meet the requirements for pubic symphysis measurement, i.e., undetermined ultrasound images. Then the system can automatically judge each undetermined ultrasound image to extract the target ultrasound image that meets the requirements for pubic symphysis measurement.

[0082] The ultrasound image to be determined can be a real-time acquired ultrasound image. For example, when using an ultrasound device, a user can activate the abdominal measurement mode, including selecting the corresponding probe, thereby entering the corresponding examination preset mode and scanning the abdomen to acquire multiple frames of ultrasound images of the pubic symphysis; these ultrasound images can all be used as the ultrasound image to be determined.

[0083] Alternatively, users can input an ultrasound video containing multiple frames of ultrasound images. This ultrasound video can be a previously acquired ultrasound video stored locally, and each frame of ultrasound image can also be used as a pending ultrasound image.

[0084] Step A2: Determine whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0085] Step A3: If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, generate the target ultrasound image based on the ultrasound image to be determined.

[0086] In this embodiment, for the acquired ultrasound image to be determined, it can be automatically determined whether the ultrasound image to be determined meets the pubic symphysis measurement requirements based on the preset pubic symphysis measurement requirements; if it meets the pubic symphysis measurement requirements, a target ultrasound image can be generated based on the ultrasound image to be determined, for example, the ultrasound image to be determined can be used as the target ultrasound image.

[0087] For example, the ultrasound image to be determined can be traversed based on traditional feature extraction algorithms. Based on features such as pixel changes or pixel continuity, it can be determined whether there are artifacts in the ultrasound image to be determined, and whether there is a pubic symphysis that meets the measurement requirements (e.g., the pubic symphysis is separated). Furthermore, it can minimize the interference of bony structures other than the pubic symphysis and preferentially select ultrasound images to be determined that do not contain other bony structures as target ultrasound images.

[0088] It is understandable that if there are multiple ultrasound images that meet the requirements for pubic symphysis measurement, these ultrasound images can be used as target ultrasound images, and the pubic symphysis distance can be automatically measured through subsequent steps.

[0089] Optionally, step A2, "determining whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement," may include steps A21 to A23.

[0090] Step A21: Identify the bony regions related to bony structures in the ultrasound images to be determined.

[0091] Step A22: Compare the features of the bony region image with a standard ultrasound image containing the pubic symphysis to determine the similarity between the bony region image and the standard ultrasound image.

[0092] Step A23: If the similarity is greater than a preset threshold, determine that the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0093] Different operators may have different acquisition habits during ultrasound image acquisition, such as different adjustments to depth and magnification / reduction, resulting in useless distal information in the acquired ultrasound images. To improve the quality assessment of the ultrasound images to be determined, only a portion of the images can be selected, and this portion can be used to assess whether the ultrasound images meet the requirements for pubic symphysis measurement.

[0094] Specifically, a standard ultrasound image containing the pubic symphysis is pre-set. This standard ultrasound image is a standard image used for pubic symphysis measurement and meets the measurement requirements. For the ultrasound image to be processed, bony regions related to bony structures are identified within the ultrasound image. Since the pubic symphysis is a bony structure, this bony region image can include the pubic symphysis. Furthermore, by comparing the features of the two, their similarity can be determined. If the similarity is greater than a preset threshold, it indicates that the bony region image is close to the standard ultrasound image and likely also meets the pubic symphysis measurement requirements. Therefore, the corresponding ultrasound image to be processed meets the pubic symphysis measurement requirements and can be used as the target ultrasound image.

[0095] The standard ultrasound image can be a cross-sectional image that meets the requirements for pubic symphysis measurement, such as a long-axis cross-sectional image of the pubic symphysis. Correspondingly, for the ultrasound image to be determined for symphysis spacing measurement, the cross-section must be a standard pubic symphysis plane. For the ultrasound image to be determined, multiple features in the image (e.g., the bony region within it) can be compared with the features of the standard ultrasound image corresponding to the standard measurement cross-section, such as whether artifacts appear in the pubic symphysis. When many features in the ultrasound image to be determined match the features of the standard cross-section, it can be considered to meet the requirements for pubic symphysis measurement.

[0096] Alternatively, quality assessment can be based on artificial intelligence algorithms. Specifically, step A2, "determining whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement," may include step A24.

[0097] Step A24: Determine the image quality of the ultrasound image to be determined based on the deep learning target detection model, and determine whether the image quality of the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0098] In this embodiment, a target detection model based on deep learning can be pre-constructed. After acquiring the ultrasound image to be determined, the quality of the ultrasound image to be determined can be evaluated based on the target detection model. The target detection model determines the image quality of the ultrasound image to be determined and judges whether the image quality meets the requirements for pubic symphysis measurement.

[0099] For example, a target detection model can determine the image quality score of the ultrasound image to be measured. The higher the image quality score, the more it meets the requirements for pubic symphysis measurement. Alternatively, the target detection model can also extract standard image features of a standard ultrasound image of the pubic symphysis (e.g., whether there are artifacts at the endpoints of the pubic symphysis). By comparing the image with these standard image features, it can be determined whether the image quality of the ultrasound image to be measured meets the requirements for pubic symphysis measurement.

[0100] The object detection model can be determined based on actual needs. For example, the object detection model can be FastRCNN (Fast Region Convolutional Neural Networks), etc., but this embodiment does not limit it.

[0101] Optionally, after step A2 "determining whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement", the method may further include step A4 and / or step A5.

[0102] Step A4: If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, display the first information indicating that the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0103] Step A5: If the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement, display second information indicating that the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement.

[0104] In this embodiment, in order to inform the user in a timely manner whether the quality of each pending ultrasound image meets the requirements, especially during real-time scanning, after determining whether the pending ultrasound image meets the requirements for pubic symphysis measurement, corresponding information, namely the first information or the second information, is also displayed to remind the user, thereby guiding the user to scan and obtain a correct and clear pubic symphysis ultrasound image, i.e., the target ultrasound image.

[0105] For example, based on the pubic symphysis structure, the two-dimensional ultrasound features displayed by the corresponding ultrasound probe placed in different positions or directions can be used to employ artificial intelligence algorithms / traditional algorithms (such as deep learning-based target detection algorithms or traditional matching algorithms) to provide real-time feedback on whether the current section meets the measurement requirements of the pubic symphysis based on the real-time input ultrasound image of the pubic symphysis (i.e., the ultrasound image to be determined), and to provide reminders with explicit information such as text content and icons in specific colors.

[0106] Figure 3 A schematic diagram illustrating the evaluation results of four pending ultrasound images is shown. (For example...) Figure 3 As shown, for ultrasound images of unknown origin, useless distal information may exist when displayed on the screen, such as the surrounding black area in the figure. This information is useless for quality assessment; therefore, only the bony region image is extracted. Figure 3 The area indicated by the blue box is used for image quality assessment. This method requires less processing time and is less susceptible to background interference from the ultrasound image.

[0107] Furthermore, quality assessment can be performed in real time during the real-time scanning of ultrasound images. For example... Figure 3As shown, if the currently scanned ultrasound image meets the requirements for pubic symphysis measurement, it will prompt "Measurement can proceed" and automatically enter the measurement mode to automatically measure the pubic symphysis distance; if other sections do not meet the requirements, it can directly prompt "Does not meet measurement requirements" in red font, thereby guiding the user to change the section in order to obtain a high-quality pubic symphysis ultrasound image.

[0108] In this embodiment, the system can automatically evaluate the user-provided ultrasound images to select those that meet the requirements for pubic symphysis measurement. This requires no human intervention and can quickly and effectively help users confirm whether their input data meets the measurement standards, improving measurement effectiveness. It is suitable for situations with multiple ultrasound images. Quality assessment based on bony region images effectively avoids interference from invalid areas, ensuring the accuracy of the quality assessment. By displaying whether each ultrasound image meets the pubic symphysis measurement requirements, the system can promptly remind the user and guide them to skip non-compliant images, thereby enabling the scanning of correct and clearer pubic symphysis ultrasound images and improving detection efficiency.

[0109] Step S202: Perform image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region; the pubic symphysis region includes a separated first region and a second region.

[0110] Specifically, the above step S202, "performing image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region", includes steps S2021 to S2022.

[0111] Step S2021: Perform shape prediction and image segmentation on the target ultrasound image to determine the mask image corresponding to the location of the pubic symphysis region. Shape prediction is used to remove regions that do not match the shape of the pubic symphysis.

[0112] In this embodiment, in order to reduce the influence of other bony structures besides the pubic symphysis, shape prediction is also performed on the target ultrasound image. The shape of each bony structure in the target ultrasound image is determined by shape prediction, thereby identifying bony structure regions that do not match the shape of the pubic symphysis and identifying these regions. This makes the remaining region highly likely to be the pubic symphysis region, thereby reducing the influence of other bony structures.

[0113] Furthermore, through image segmentation processing, the region corresponding to the pubic symphysis in the target ultrasound image can be identified and represented as a mask, thus obtaining a corresponding mask image. The mask image contains only two types of pixels: one type with a pixel value of (255, 255, 255) and the other type with a pixel value of (0, 0, 0). For example, a mask image can be generated based on the location and size of the pubic symphysis. This mask image only contains pixels with a value of (255, 255, 255) at the pubic symphysis location, while the others serve as background with pixel values ​​of (0, 0, 0).

[0114] In this embodiment, the above step S2021, "performing shape prediction and image segmentation on the target ultrasound image to determine the mask image corresponding to the location of the pubic symphysis region," can specifically include: locating the pubic symphysis region in the target ultrasound image based on a deep learning image segmentation model, and performing shape prediction and image segmentation on the target within the pubic symphysis region to generate a mask image corresponding to the location of the pubic symphysis region.

[0115] Specifically, after determining the target ultrasound image, it can be automatically located near the pubic symphysis region using artificial intelligence algorithms. In this embodiment, an image segmentation model based on deep learning is pre-constructed. Based on this image segmentation model, the target ultrasound image is automatically located near the pubic symphysis region. Then, the image segmentation model can be used to predict the shape and segment the target within this region. For example, this image segmentation model is the U-net model (U-shaped network model).

[0116] Since the acquired target ultrasound images are easily affected by the operator's habits, resulting in different invalid features, using an image segmentation model to automatically locate the required feature region first, and then performing shape prediction and segmentation, can more accurately eliminate the influence of non-pubic symphysis bony structures, thereby obtaining the actual location and shape of the pubic symphysis more accurately.

[0117] In this embodiment, the target ultrasound image can be first shape-predicted, and regions that do not match the shape of the pubic symphysis can be removed. Then, the shape-predicted image can be segmented to obtain a mask image. Alternatively, the target ultrasound image can be segmented first to obtain a mask image, and then regions that do not match the pubic symphysis in the mask image can be identified and removed to obtain the final mask image. This embodiment does not limit the execution order of the two methods.

[0118] Optionally, after determining the target ultrasound image, preprocessing can be performed first, and then shape prediction and image segmentation can be performed on the preprocessed target ultrasound image.

[0119] For example, the preprocessing methods used may include: normalization, adaptive histogram equalization, standardization, adaptive histogram equalization algorithm, gamma correction, etc., which can be selected based on actual needs. This embodiment does not limit this.

[0120] Step S2022: Post-process the mask image to generate a segmented image containing two segmented regions. One segmented region in the segmented image is the first region of the pubic symphysis region, and the other segmented region is the second region of the pubic symphysis region.

[0121] In this embodiment, since the mask image may contain defects, post-processing of the mask image yields an image suitable for measuring the pubic symphysis distance, i.e., a segmented image. Because the pubic symphysis is divided into two parts at this point, the pubic symphysis region in the mask image also contains two regions. After post-processing the mask image, the resulting segmented image will contain two regions, i.e., segmented regions. It can be understood that one segmented region is the first region of the pubic symphysis region, and the other segmented region is the second region of the pubic symphysis region.

[0122] In some optional implementations, the above step S2022, "post-processing the mask image to generate a segmented image containing two segmented regions," specifically includes steps B1 to B2.

[0123] Step B1: If the number of segmented regions in the mask image exceeds 2, perform a region search on the mask image and retain the two segmented regions with the largest areas.

[0124] Step B2 involves performing morphological processing and / or edge smoothing on the preserved segmented regions to obtain a segmented image containing two segmented regions.

[0125] In this embodiment, the segmented regions in the mask image are connected regions. If the number of segmented regions in the mask image exceeds 2, it indicates that there is interference in the mask image. By performing region search on the mask image, the size of each segmented region can be determined, and then the two largest segmented regions are retained, namely, the largest and second largest segmented regions. The remaining isolated segmented regions have smaller areas and are generally noisy, so they can be removed, and finally a mask image containing only two segmented regions is obtained.

[0126] In this process, since the image segmentation result needs to include both pubic symphysis when measuring the distance between them, two segmentation regions are required. Furthermore, because the two pubic symphysis are located correspondingly, the segmentation region corresponding to the pubic symphysis can also be retained to avoid misjudgment.

[0127] For the segmented region corresponding to the pubic symphysis, further morphological processing and / or edge smoothing can be performed. For example, morphological processing includes, but is not limited to, seed filling, flood filling, and opening operations; edge smoothing can specifically use Gaussian filtering to appropriately smooth the segmentation results.

[0128] After post-processing, the final image that is beneficial for subsequent measurement of the pubic symphysis distance can be obtained, namely the segmented image. It can be understood that the segmented image is also a masked image.

[0129] In this embodiment, by post-processing the mask image, isolated regions unrelated to the pubic symphysis can be removed, and the pubic symphysis region can be made complete and smooth, which is beneficial for subsequent calculation of the pubic symphysis distance.

[0130] Step S203: Locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region.

[0131] Please see details Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0132] In some optional implementations, the above step S203, "locating the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region", may include: taking the endpoint in the first region that is closest to the second region as the first endpoint of the pubic symphysis and taking the endpoint in the second region that is closest to the first region as the second endpoint of the pubic symphysis.

[0133] In this embodiment, since the two regions of the pubic symphysis are located opposite each other, in order to simplify the location of the endpoints, the endpoint of the first region that is closest to the second region is taken as the first endpoint of the pubic symphysis, and correspondingly, the endpoint of the second region that is closest to the first region is taken as the second endpoint of the pubic symphysis.

[0134] For example, if the pubic symphysis includes the left pubic symphysis and the right pubic symphysis, the first region is the region corresponding to the left pubic symphysis and the second region is the region corresponding to the right pubic symphysis. Then the rightmost point of the first region can be taken as the first endpoint, i.e. the endpoint of the left pubic symphysis, and the leftmost point of the second region can be taken as the second endpoint, i.e. the endpoint of the right pubic symphysis.

[0135] In this embodiment, by automatically locating the endpoint of the pubic symphysis, errors caused by user subjectivity can be greatly reduced, providing users with more accurate measurement points and improving clinical work efficiency.

[0136] Step S204: The distance between the first endpoint and the second endpoint is taken as the pubic symphysis distance.

[0137] Please see details Figure 1Step S104 of the illustrated embodiment will not be described again here.

[0138] Step S205: Display the numerical value of the pubic symphysis distance, mark and display the first endpoint, the second endpoint, and the line segment between the first endpoint and the second endpoint in the target ultrasound image.

[0139] In this embodiment, after calculating the pubic symphysis distance, the pubic symphysis distance can be output. By displaying the value of the pubic symphysis distance, for example, by displaying the value of the pubic symphysis distance on the display screen of the ultrasound device, the user can be informed of the current pubic symphysis distance in a timely manner. This is especially convenient for users to know the pubic symphysis distance in real-time scanning scenarios.

[0140] Furthermore, the detected first and second endpoints are marked in the target ultrasound image, and the line segment between the first and second endpoints is also marked. This allows the diameter representing the pubic symphysis distance to be marked in the target ultrasound image, automatically indicating the location of the pubic symphysis endpoints. This makes it easier for users to intuitively locate the pubic symphysis distance and also allows them to verify whether the pubic symphysis distance automatically located by the algorithm is accurate.

[0141] Figure 4 This image shows a result of automatic measurement of the pubic symphysis distance. Figure 4 As shown, if the calculated pubic symphysis distance is 5.03 mm, it is displayed in the upper left corner of the ultrasound interface; and the identified pubic symphysis distance is marked in the ultrasound image.

[0142] Taking a user's actual scan of the pubic symphysis as an example, Figure 5 A schematic diagram of a process for automatically measuring the pubic symphysis distance is shown. Figure 5 As shown, the user selects an ultrasound probe capable of acquiring data from the pubic symphysis and scans the corresponding pubic symphysis section. The image quality can be predicted based on artificial intelligence / traditional methods to determine whether the currently acquired ultrasound image meets the requirements for pubic symphysis measurement. If it does not meet the requirements, a message will be displayed indicating that the section does not meet the requirements, instructing the user to continue scanning. If it meets the requirements, the currently acquired ultrasound image can be used as the target ultrasound image.

[0143] After preprocessing, image segmentation, and postprocessing of the target ultrasound image, a segmented image in the form of a mask can be obtained. Since it contains only two types of pixels, the key points of the pubic symphysis can be located relatively easily and accurately. That is, the endpoints of the left and right pubic symphysis can be accurately located. Then, the distance between the two endpoints is automatically calculated and displayed in the ultrasound interface.

[0144] The pubic symphysis measurement method provided in this embodiment can extract, segment, and measure the pubic symphysis distance, and display the measurement results on the ultrasound interface. By performing cross-sectional recognition and automatic segmentation of the pubic symphysis ultrasound image, the pubic symphysis can be accurately extracted in complex environments. Key points (i.e., the endpoints of the pubic symphysis, which are the optimal measurement points) are automatically located from the segmented pubic symphysis image, and the pubic symphysis distance is calculated. Finally, the parameters are displayed on the ultrasound interface in numerical and radial form. Compared to traditional pubic symphysis distance measurement methods, this embodiment can automatically measure the pubic symphysis distance with a single click, achieving efficient and convenient automatic measurement. This reduces errors from manually searching for pubic symphysis images and optimal measurement points, lowers dependence on the operator, improves the ease of operation of the equipment, standardizes measurements, and enhances clinical work efficiency. It can quickly achieve automatic measurement of the pubic symphysis distance, assisting users in assessing the pubic symphysis status of the subject.

[0145] This embodiment also provides a pubic symphysis measuring device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0146] This embodiment provides a pubic symphysis measuring device, such as... Figure 6 As shown, it includes:

[0147] The acquisition module 601 is used to acquire target ultrasound images that meet the requirements for pubic symphysis measurement;

[0148] Processing module 602 is used to perform image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region, wherein the pubic symphysis region includes a separated first region and a second region;

[0149] The positioning module 603 is used to locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region; and to use the distance between the first endpoint and the second endpoint as the pubic symphysis distance.

[0150] In some optional implementations, the acquisition module 601 acquires a target ultrasound image that meets the requirements for pubic symphysis measurement, including:

[0151] Acquire the ultrasound image to be determined;

[0152] Determine whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement;

[0153] If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, a target ultrasound image is generated based on the ultrasound image to be determined.

[0154] In some optional implementations, the acquisition module 601 determines whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement, including:

[0155] Identify the bony regions related to bony structures in the ultrasound images to be determined;

[0156] The similarity between the bony region image and the standard ultrasound image containing the pubic symphysis is determined by comparing their features.

[0157] If the similarity is greater than a preset threshold, the ultrasound image to be determined is determined to meet the requirements for pubic symphysis measurement.

[0158] In some optional implementations, the acquisition module 601 determines whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement, including:

[0159] The image quality of the ultrasound image to be determined is determined based on a deep learning-based target detection model, and it is then determined whether the image quality of the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

[0160] In some alternative embodiments, the device further includes an output module for:

[0161] If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, first information indicating that the ultrasound image to be determined meets the requirements for pubic symphysis measurement is displayed;

[0162] And / or, if the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement, display second information indicating that the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement.

[0163] In some optional embodiments, the processing module 602 performs image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region, including:

[0164] The target ultrasound image is subjected to shape prediction and image segmentation to determine a mask image corresponding to the location of the pubic symphysis region. The shape prediction is used to remove regions that do not match the shape of the pubic symphysis.

[0165] The mask image is post-processed to generate a segmented image containing two segmented regions. One segmented region in the segmented image is the first region of the pubic symphysis region, and the other segmented region is the second region of the pubic symphysis region.

[0166] In some optional implementations, the processing module 602 performs shape prediction and image segmentation on the target ultrasound image to determine a mask image corresponding to the location of the pubic symphysis region, including:

[0167] The pubic symphysis region in the target ultrasound image is located using a deep learning image segmentation model. Shape prediction and image segmentation are performed on the target within the pubic symphysis region to generate a mask image corresponding to the location of the pubic symphysis region.

[0168] In some optional implementations, the processing module 602 performs post-processing on the mask image to generate a segmented image containing two segmented regions, including:

[0169] If the number of segmented regions in the mask image exceeds 2, perform a region search on the mask image and retain the two segmented regions with the largest areas.

[0170] Morphological processing and / or edge smoothing are performed on the preserved segmented regions to obtain a segmented image containing two segmented regions.

[0171] In some optional implementations, the positioning module 603 positions the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region, including:

[0172] The endpoint in the first region that is closest to the second region is taken as the first endpoint of the pubic symphysis, and the endpoint in the second region that is closest to the first region is taken as the second endpoint of the pubic symphysis.

[0173] In some alternative embodiments, the device further includes an output module for:

[0174] The numerical value of the pubic symphysis distance is displayed, and the first endpoint, the second endpoint, and the line segment between the first endpoint and the second endpoint are marked and displayed in the target ultrasound image.

[0175] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0176] In this embodiment, the pubic symphysis measuring device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, including a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0177] This invention also provides an ultrasound device, which includes: a processor, an ultrasound probe, and a display; wherein the ultrasound probe is used to acquire ultrasound images, such as target ultrasound images;

[0178] The processor is communicatively connected to the ultrasound probe and the display, and displays the ultrasound images acquired by the ultrasound probe on the display; and the processor is used to implement the pubic symphysis measurement method provided in any of the above embodiments.

[0179] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an ultrasonic device provided in an optional embodiment of the present invention, such as... Figure 7 As shown, the ultrasound device 10 includes an ultrasound probe 11, a transmitting circuit 12, a receiving circuit 13, a processor 14, and a display 15. Furthermore, the ultrasound system may also include a transmit / receive selection switch 16 and a beamforming module 17. The transmitting circuit 12 and the receiving circuit 13 can be connected to the ultrasound probe 11 via the transmit / receive selection switch 16.

[0180] Specifically, the ultrasound probe 11 is used to generate shear waves that propagate within the target tissue of the target object; the transmitting circuit 12 is used to excite the ultrasound probe 11 to emit a first ultrasound wave toward the target tissue; the receiving circuit 13 is used to control the ultrasound probe 11 to receive the ultrasound echo returned by the target tissue to obtain a first echo signal of the first ultrasound wave; and the processor 14 is used to implement the pubic symphysis measurement method provided in any of the above embodiments.

[0181] The ultrasound probe 11 includes a transducer (not shown) composed of multiple array elements arranged in an array. The array elements are used to emit ultrasonic waves according to an excitation electrical signal, or to convert received ultrasonic waves into electrical signals. Therefore, each array element can be used to realize the mutual conversion between electrical pulse signals and ultrasonic waves, thereby enabling the emission of ultrasonic waves to the biological tissue of the target object, and also to receive the echo of ultrasonic waves reflected back from the tissue.

[0182] The transmitting circuit 12 is used to control the ultrasonic probe 11 to emit ultrasonic waves, for example, according to the control of the processor 14, to excite the ultrasonic probe 11 to emit ultrasonic waves toward the target object.

[0183] The receiving circuit 13 is used to control the ultrasonic probe 11 to receive the echo of ultrasonic waves. For example, the ultrasonic probe 11 receives the ultrasonic echo returned from the target object to obtain an ultrasonic echo signal, and can also process the ultrasonic echo signal. The receiving circuit 13 may include one or more amplifiers, analog-to-digital converters (ADCs), etc.

[0184] The display 15 is used for displaying or human-computer interaction, such as outputting visual information and receiving user input. The display 15 includes an input device and at least one display screen. The input device is used to receive user input and may be a keyboard, operation buttons, mouse, trackball, touchpad, etc., or may be a touch screen integrated with the display screen.

[0185] The ultrasound device 10 also includes a memory 18 for storing various types of data.

[0186] The ultrasound device 10 may also include a beamforming module 17. The beamforming module 17 is signal-connected to the receiving circuit 13 and is used to perform beamforming processing on the echo signal, including delay and weighted summation. Because the distance from the ultrasound receiving point in the tested tissue to the receiving array elements varies, the channel data of the same receiving point output by different receiving array elements has delay differences, requiring delay processing to align the phases and perform weighted summation on the different channel data of the same receiving point to obtain the beamformed ultrasound image data. The ultrasound image data output by the beamforming module 17 is also called radio frequency (RF) data. The beamforming module 17 performs focusing delay, weighted summation, and channel summation on the ultrasound echo data, and then sends it to the processor 14. The processor 14 performs signal detection, signal enhancement, data conversion, and logarithmic compression on the ultrasound echo signal to form an ultrasound image. The ultrasound image obtained by the processor 14 can be displayed on the display 15 or stored in the memory 18.

[0187] The processor 14 can be implemented as software, hardware, firmware, or any combination thereof, and can use one or more application-specific integrated circuits (ASICs), one or more general-purpose integrated circuits, one or more microprocessors, one or more programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 14 can control other components in the ultrasonic device 10 to perform the corresponding steps of the methods in the various embodiments of this specification.

[0188] The display 15 is connected to the processor 14. The display 15 can be a touch screen, an LCD screen, etc.; or, the display 15 can be an independent display such as an LCD screen or a television, separate from the ultrasound device 10; or, the display 15 can be the screen of an electronic device such as a smartphone or tablet, etc. The number of displays 15 can be one or more.

[0189] The display 15 can display the ultrasound images obtained by the processor 14. Furthermore, while displaying the ultrasound images, the display 15 can also provide a graphical user interface for human-computer interaction. One or more controlled objects can be set on the graphical interface, allowing the user to input operation commands via a human-computer interaction device to control these controlled objects and perform corresponding control operations. For example, icons can be displayed on the graphical interface, and the human-computer interaction device can be used to operate these icons to perform specific functions, such as drawing a region of interest bounding box on the ultrasound image.

[0190] Optionally, the ultrasound device 10 may also include other human-machine interface devices besides the display 15, which are connected to the processor 14. For example, the processor 14 can be connected to the human-machine interface device through an external input / output port, which can be a wireless communication module, a wired communication module, or a combination of both. The external input / output port can also be implemented based on bus protocols such as USB and CAN, and / or wired network protocols.

[0191] The human-computer interaction device may include an input device for detecting user input information. This input information may be, for example, control commands for the timing of ultrasound transmission / reception, operational input commands for drawing points, lines, or boxes on an ultrasound image, or other types of commands. The input device may include one or a combination of several of the following: a keyboard, mouse, scroll wheel, trackball, mobile input device (e.g., a mobile device with a touchscreen, a mobile phone, etc.), a multi-function knob, etc. The human-computer interaction device may also include an output device such as a printer.

[0192] The ultrasound device 10 also includes a memory 18 for storing various types of data. Specifically, the memory 18 stores instructions executed by the processor, received ultrasound echoes, ultrasound images, and so on. The memory 18 can be a flash memory card, solid-state memory, hard disk, etc. It can be volatile and / or non-volatile memory, removable memory and / or non-removable memory, etc.

[0193] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0194] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0195] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art, after understanding the content and principles of the present invention, may arbitrarily combine the specific implementations or technical features of each embodiment without departing from the principles and / or structure of the present invention, and may also make various modifications and changes in form and detail to the present invention, and may add or delete some modules as needed. Those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations should all be covered within the protection scope of the present invention.

Claims

1. A method for measuring the pubic symphysis, characterized in that, The method includes: Acquire target ultrasound images that meet the requirements for pubic symphysis measurement; The target ultrasound image is segmented to generate a segmented image containing the pubic symphysis region, which includes a separated first region and a second region. Locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region; The distance between the first endpoint and the second endpoint is taken as the pubic symphysis distance.

2. The method according to claim 1, characterized in that, The acquisition of the target ultrasound image that meets the requirements for pubic symphysis measurement includes: Acquire the ultrasound image to be determined; Determine whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement; If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, a target ultrasound image is generated based on the ultrasound image to be determined.

3. The method according to claim 2, characterized in that, The determination of whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement includes: Identify the bony regions related to bony structures in the ultrasound images to be determined; The similarity between the bony region image and the standard ultrasound image containing the pubic symphysis is determined by comparing their features. If the similarity is greater than a preset threshold, the ultrasound image to be determined is determined to meet the requirements for pubic symphysis measurement.

4. The method according to claim 2, characterized in that, The determination of whether the ultrasound image to be determined meets the requirements for pubic symphysis measurement includes: The image quality of the ultrasound image to be determined is determined based on a deep learning-based target detection model, and it is then determined whether the image quality of the ultrasound image to be determined meets the requirements for pubic symphysis measurement.

5. The method according to claim 2, characterized in that, Also includes: If the ultrasound image to be determined meets the requirements for pubic symphysis measurement, first information indicating that the ultrasound image to be determined meets the requirements for pubic symphysis measurement is displayed; And / or, if the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement, display second information indicating that the ultrasound image to be determined does not meet the requirements for pubic symphysis measurement.

6. The method according to any one of claims 1-5, characterized in that, The step of segmenting the target ultrasound image to generate a segmented image containing the pubic symphysis region includes: The target ultrasound image is subjected to shape prediction and image segmentation to determine a mask image corresponding to the location of the pubic symphysis region. The shape prediction is used to remove regions that do not match the shape of the pubic symphysis. The mask image is post-processed to generate a segmented image containing two segmented regions. One segmented region in the segmented image is the first region of the pubic symphysis region, and the other segmented region is the second region of the pubic symphysis region.

7. The method according to claim 6, characterized in that, The step of performing shape prediction and image segmentation on the target ultrasound image to determine the mask image corresponding to the location of the pubic symphysis region includes: The pubic symphysis region in the target ultrasound image is located using a deep learning image segmentation model. Shape prediction and image segmentation are performed on the target within the pubic symphysis region to generate a mask image corresponding to the location of the pubic symphysis region.

8. The method according to claim 6, characterized in that, The post-processing of the mask image to generate a segmented image containing two segmented regions includes: If the number of segmented regions in the mask image exceeds 2, perform a region search on the mask image and retain the two segmented regions with the largest areas. Morphological processing and / or edge smoothing are performed on the preserved segmented regions to obtain a segmented image containing two segmented regions.

9. The method according to any one of claims 1-5 and 7-8, characterized in that, The locating of the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region includes: The endpoint in the first region that is closest to the second region is taken as the first endpoint of the pubic symphysis, and the endpoint in the second region that is closest to the first region is taken as the second endpoint of the pubic symphysis.

10. The method according to any one of claims 1-5 and 7-8, characterized in that, Also includes: Show the numerical value of the pubic symphysis distance, and / or The first endpoint, the second endpoint, and the line segment between the first endpoint and the second endpoint are marked and displayed in the target ultrasound image.

11. A pubic symphysis measuring device, characterized in that, The device includes: The acquisition module is used to acquire target ultrasound images that meet the requirements for pubic symphysis measurement; The processing module is used to perform image segmentation on the target ultrasound image to generate a segmented image containing the pubic symphysis region, wherein the pubic symphysis region includes a separated first region and a second region; The positioning module is used to locate the first endpoint of the pubic symphysis in the first region and the second endpoint of the pubic symphysis in the second region; and to use the distance between the first endpoint and the second endpoint as the pubic symphysis distance.

12. An ultrasonic device, characterized in that, include: Processor, ultrasound probe, and display; The processor is communicatively connected to the ultrasound probe and the display, and the processor is used to execute the pubic symphysis measurement method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the pubic symphysis measurement method according to any one of claims 1 to 10.

Images