Ultrasonic imaging method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an ultrasonic imaging method and device, electronic equipment and a storage medium. The method comprises the following steps: extracting each first section in a plurality of first sections obtained by three-dimensional ultrasonic body data along a first direction, determining first position information of a first edge of a low-echo area in the first tangent plane in a second direction and second position information of a second edge of a high-echo area in the first tangent plane in the second direction, the second direction being perpendicular to the first direction; the second edge is the edge of one side, close to the low echo area, of the high echo area in the second direction; and based on the first position information and the second position information corresponding to the plurality of first tangent planes, a target segmentation plane is determined, and the target segmentation plane is used for segmenting an object region where the target object is located in the three-dimensional ultrasonic body data and other regions except the object region. According to the method, resource consumption can be greatly reduced, and accurate positioning of the target object can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic image processing, and in particular to an ultrasonic imaging method, an ultrasonic imaging device, an electronic device and a computer-readable storage medium. Background Art

[0002] When performing three-dimensional ultrasound imaging of a target object, the target object may be partially obscured, making it difficult to accurately identify and segment the target object. The following description takes three-dimensional ultrasound prenatal examination as an example. Three-dimensional ultrasound prenatal examination is an important measure to examine the fetus during early, mid- and late pregnancy. During a three-dimensional ultrasound examination, due to the influence of amniotic fluid, embryonic disc, etc., there will be some tissue obstructions above the fetal area, making it impossible to accurately segment the fetal area and other areas except the fetus.

[0003] In the prior art, target detection or image segmentation is generally performed on the three-dimensional ultrasound volume data to locate the area where the fetus is located and then perform volume data segmentation, or the three-dimensional ultrasound volume data is matched with the fetal volume data template to determine the fetal position and then perform volume data segmentation. The target detection or image segmentation method often requires the construction of a huge three-dimensional ultrasound volume database and manual annotation of the area where the fetus is located. The initial human and material resources consumed are large, and the use of deep learning methods has high requirements on the hardware capabilities of the machine and is time-consuming. The template matching method takes too long and is not real-time. In addition, the above-mentioned methods have high requirements for the facial features of the fetus in the collected three-dimensional ultrasound volume data. If the facial features of the fetus in the collected three-dimensional ultrasound volume data are not obvious or incomplete, it will lead to inaccurate positioning or inability to locate. Summary of the invention

[0004] The present invention is proposed in view of the above problems. The present invention provides an ultrasonic imaging method, an ultrasonic imaging device, an electronic device and a computer-readable storage medium.

[0005] According to one aspect of the present invention, an ultrasound imaging method is provided, comprising: for each first section among a plurality of first sections extracted along a first direction from three-dimensional ultrasound volume data, determining first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; and determining a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the target segmentation plane being used to segment an object region where a target object is located and other regions except the object region in the three-dimensional ultrasound volume data.

[0006] Exemplarily, for each first section among multiple first sections extracted along a first direction from three-dimensional ultrasound volume data, first position information of a first edge of a low-echo region in the first section in the second direction and second position information of a second edge of a high-echo region in the first section in the second direction are determined, including: for each first section among the multiple first sections, extracting an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate a position of the low-echo region in the corresponding first section, and the initial high-echo image is used to indicate a position of the high-echo region in the corresponding first section; determining first position information of a first edge of the low-echo region in the second direction based at least on the corresponding initial low-echo image; and determining second position information of a second edge of the high-echo region in the second direction based at least on the corresponding initial high-echo image.

[0007] Exemplarily, extracting an initial low-echo image and an initial high-echo image corresponding to the first section includes: acquiring a low-echo template image and a high-echo template image, wherein the image sizes of the low-echo template image and the high-echo template image are the same as the image size of each first section in multiple first sections; comparing the pixel value of each first pixel in the first section with a preset threshold; if the pixel value of the first pixel is less than or equal to the preset threshold, setting the pixel value of the second pixel in the low-echo template image to the first pixel value, wherein the position of the second pixel in the low-echo template image is consistent with the position of the first pixel in the first section; setting the pixel value of the first remaining pixel in the low-echo template image to the second pixel value to obtain the initial low-echo image corresponding to the first section, wherein the first remaining pixel is a pixel other than the pixel set to the first pixel value, and the first pixel value is used to indicate the first pixel in the first section. The corresponding pixel point belongs to the low echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low echo area; if the pixel value of the first pixel point is greater than the preset threshold, the pixel value of the third pixel point in the high echo template image is set to the third pixel value, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; the pixel value of the second remaining pixel points in the high echo template image is set to the fourth pixel value to obtain an initial high echo image corresponding to the first section, wherein the second remaining pixel points are pixel points other than the pixel points set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high echo area; wherein the first pixel point is a pixel point within the effective detection area, and the effective detection area is an area containing the target observation part of the target object.

[0008] Exemplarily, the pixel value of each pixel in the initial low-echo image includes a first pixel value and a second pixel value, the first pixel value is used to indicate that the corresponding pixel in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel in the first section does not belong to the low-echo area; at least based on the corresponding initial low-echo image, determining the first position information of the first edge of the low-echo area in the second direction, including: setting the pixel values ​​in the initial low-echo image in the following manner to obtain the corresponding final low-echo image: based on the initial low-echo image, determining a connected domain in the low-echo area; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is less than the first area threshold, setting the pixel value of the pixel in the initial low-echo image to the second pixel value; For each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold and the pixel meets the first target requirement, the pixel value of the pixel in the initial low-echo image is set to the first pixel value; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold and the pixel does not meet the first target requirement, the pixel value of the pixel in the initial low-echo image is set to the second pixel value; the final low-echo image is traversed along the second direction, and during the traversal process, the position information corresponding to the first pixel point in the second direction obtained from top to bottom in each column along the second direction whose pixel value is the first pixel value is recorded to obtain the first position information of the first edge of the low-echo area in the second direction.

[0009] Exemplarily, the first target requirement includes: the pixel point meets any of the first target conditions, the first target conditions including: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; wherein the first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

[0010] Exemplarily, at least part of the connected domains are a preset number of connected domains with the largest area in the high-echo region, or connected domains in the high-echo region whose area exceeds a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

[0011] Exemplarily, the pixel value of each pixel point in the initial high-echoic image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high-echoic area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high-echoic area; at least based on the corresponding initial high-echoic image, determine the second position information of the second edge of the high-echoic area in the second direction, including: setting the pixel values ​​in the initial high-echoic image in the following manner to obtain the corresponding final high-echoic image: based on the initial high-echoic image, determine the connected domain contained in the high-echoic area; for each pixel point in the initial high-echoic image, if the area of ​​the connected domain where the pixel point is located is less than the third area threshold, set the pixel value of the pixel point in the initial high-echoic image to the fourth pixel value; for the pixel point in the initial high-echoic image For each pixel point of the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the third pixel value; for each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point does not meet the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the fourth pixel value; taking each edge point in the first edge of the low echo area in the second direction as the starting point, traversing the final high echo image along the second direction, during the traversal process, recording the position information in the second direction corresponding to the pixel point whose first pixel value is the third pixel value obtained from top to bottom in each column along the second direction, so as to obtain the second position information of the second edge of the high echo area in the second direction.

[0012] Exemplarily, the second target requirement includes: the pixel point meets any of the second target conditions, the second target conditions include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; wherein the second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction in the second direction.

[0013] Exemplarily, determining a target segmentation plane based on first position information and second position information corresponding to each of the multiple first cut planes includes: determining an initial segmentation plane based on the first position information and second position information corresponding to each of the multiple first cut planes, the initial segmentation plane containing segmentation lines corresponding one-to-one to the multiple first cut planes, and the segmentation line corresponding to each first cut plane is located between an edge corresponding to the first position information and an edge corresponding to the second position information; wherein the initial segmentation plane is the target segmentation plane, or determining the target segmentation plane based on the first position information and second position information corresponding to each of the multiple first cut planes also includes: optimizing the initial segmentation plane to determine the target segmentation plane.

[0014] Exemplarily, optimizing the initial segmentation plane to determine the target segmentation plane includes: interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane.

[0015] Exemplarily, before interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, the initial segmentation plane is optimized to determine the target segmentation plane, and the method further includes: for each fourth pixel point in the initial segmentation plane, calculating the mean of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and the standard deviation of the pixel values ​​of each pixel point in the first pixel point set; when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, setting the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation; or, when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation, setting the pixel value of the fourth pixel point to the sum of the mean and the standard deviation; wherein the first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located.

[0016] Exemplarily, before interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, and / or after interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, the method also includes: for any fifth pixel point in the initial segmentation plane, filtering the fifth pixel point based on the pixel values ​​of non-zero pixel points in an area of ​​the target size around the fifth pixel point.

[0017] Exemplarily, after determining the target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the method further comprises: determining a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane.

[0018] Exemplarily, determining a segmentation line of a two-dimensional ultrasound image of three-dimensional ultrasound volume data on any second section based on a target segmentation plane includes: determining a segmentation template based on the target segmentation plane, the segmentation template being consistent with the number of voxel points in the three-dimensional ultrasound volume data, each voxel point in the segmentation template having a voxel value, and the voxel value being used to indicate whether a corresponding voxel point in the three-dimensional ultrasound volume data belongs to a target object; projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0019] Exemplarily, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. The segmentation template is projected into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section, including: projecting the segmentation template into the two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; determining the pixel points whose first pixel value in each column of the segmentation section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; uniformly sampling the second pixel point set to obtain at least two discrete pixel points; interpolating the at least two discrete pixel points to obtain a target segmentation line, which is the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0020] Exemplarily, after determining a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane, the method further includes: displaying the two-dimensional ultrasound image and the segmentation line of the three-dimensional volume data on the second section on a display interface.

[0021] According to another aspect of the present invention, an ultrasonic imaging device is also provided, comprising: an acquisition module, used to acquire three-dimensional ultrasonic volume data containing a target object; a first determination module, used to determine, for each first section among a plurality of first sections extracted along a first direction from the three-dimensional ultrasonic volume data, first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; and a second determination module, used to determine a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the target segmentation plane being used to segment an object region where the target object is located in the three-dimensional ultrasonic volume data and other regions except the object region.

[0022] According to yet another aspect of the present invention, there is also provided an electronic device, comprising a processor and a memory, wherein the memory stores a computer program / instruction, and the processor executes the computer program / instruction to implement the above-mentioned ultrasonic imaging method.

[0023] According to yet another aspect of the present invention, there is also provided a computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction implements the above-mentioned ultrasound imaging method when executed by a processor.

[0024] According to the ultrasonic imaging method, ultrasonic imaging device, electronic device and computer-readable storage medium of the embodiments of the present invention, the position information of the first edge of the low echo area and the second edge of the high echo area corresponding to each first section along the first direction of the three-dimensional ultrasonic volume data can be determined. Then, based on the position information of the first edge of the low echo area and the second edge of the high echo area corresponding to each first section, the target segmentation surface is determined. This method does not require the construction of a large three-dimensional ultrasonic volume database, nor does it require manual labeling, which can greatly reduce resource consumption. When applied to ultrasonic imaging of the fetus, this method can be well applied to the identification and positioning of the fetus in various periods such as early, middle and late pregnancy.

[0025] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0027] Figure 1 A schematic flow chart of an ultrasonic imaging method according to an embodiment of the present invention is shown;

[0028] Figure 2 A schematic diagram showing three-dimensional ultrasound volume data according to an embodiment of the present invention is shown;

[0029] Figure 3 A schematic diagram of a first section according to an embodiment of the present invention is shown;

[0030] Figure 4 A schematic diagram showing a segmentation line of a two-dimensional ultrasound image according to an embodiment of the present invention is shown;

[0031] Figure 5 A schematic block diagram showing an ultrasonic imaging device according to an embodiment of the present invention; and

[0032] Figure 6 A schematic block diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0034] In order to solve the above technical problems, the present invention provides an ultrasonic imaging method. Figure 1 FIG. 1 is a schematic flow chart of an ultrasonic imaging method 100 according to an embodiment of the present invention. Figure 1 As shown, the ultrasound imaging method 100 includes step S110, step S120 and step S130.

[0035] Step S110: acquiring three-dimensional ultrasound volume data containing the target object.

[0036] Exemplarily, an ultrasonic imaging device can be used to collect an ultrasonic scanning video (which can be referred to as "ultrasound video") for a target object. The target object can be any organism or any part to be measured in any organism. The part to be measured can be a biological tissue, such as the uterus of a human body (scanning the uterus can be equivalent to scanning a fetus), etc. The following mainly describes the target object as a fetus as an example. The ultrasonic video obtained by scanning contains the target object. The ultrasonic scanning video can include multiple frames, each frame can correspond to an ultrasonic image, and the ultrasonic image can be a two-dimensional or three-dimensional ultrasonic image. Optionally, a three-dimensional ultrasonic image can also be obtained based on one or more frames of two-dimensional ultrasonic images. For example, any two-dimensional ultrasonic image in the ultrasonic scanning video can be reconstructed in three dimensions to obtain three-dimensional ultrasonic volume data corresponding to the ultrasonic image. A three-dimensional ultrasonic image is a three-dimensional ultrasonic volume data. Therefore, three-dimensional ultrasonic volume data containing a fetus can be obtained based on the ultrasonic scanning video. For example, a 200-frame ultrasonic scanning video can obtain 200 three-dimensional ultrasonic images, and the 200 three-dimensional ultrasonic images can be optionally sorted according to the acquisition order of each frame in the ultrasonic scanning video. Figure 2A schematic diagram of three-dimensional ultrasound volume data according to an embodiment of the present invention is shown. The size of the three-dimensional ultrasound volume data can be expressed as W×H×D, where W represents the width of the three-dimensional ultrasound volume data, H represents the height of the three-dimensional ultrasound volume data, and D represents the depth of the three-dimensional ultrasound volume data. Optionally, after the three-dimensional ultrasound volume data is acquired in step S110, the three-dimensional ultrasound volume data can be preprocessed to obtain preprocessed three-dimensional ultrasound volume data, and subsequent steps (for example, steps starting from step S120 and going backwards) can be operated on the preprocessed three-dimensional ultrasound volume data. Of course, the preprocessed three-dimensional ultrasound volume data can also be directly acquired in step S110. The above preprocessing may include but is not limited to: denoising, smoothing, enhancement, etc. The acquisition of the three-dimensional ultrasound volume data can be acquired in real time by an ultrasound imaging device, or it can be extracted from a storage device of the ultrasound imaging device. Exemplarily, the ultrasound imaging device can include a volume probe, and the three-dimensional ultrasound volume data can be acquired using the volume probe.

[0037] Step S120, for each first section among the multiple first sections extracted along the first direction from the three-dimensional ultrasound volume data, determine the first position information of the first edge of the low-echo region in the first section in the second direction and the second position information of the second edge of the high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is the edge of the high-echo region on one side close to the low-echo region in the second direction.

[0038] The first direction may be any direction. Exemplarily and non-restrictively, the first direction may be a direction perpendicular to the sagittal plane of the target object, in which case the first section is the sagittal plane of the target object. The second direction may be a direction parallel to the sagittal plane of the target object. Specifically, the second direction may be, for example, a direction parallel to the sagittal axis of the target object. Of course, the first direction and the second direction may be other directions. For example, the first direction may be a direction perpendicular to the coronal plane of the target object, in which case the first section is the coronal plane of the target object, and the second direction is a direction parallel to the coronal plane of the target object. Specifically, the second direction may be, for example, a direction parallel to the coronal axis of the target object. Exemplarily, referring to Figure 2 , take the center of the cube space corresponding to the three-dimensional ultrasound volume data as the origin O, take the direction passing through the origin O and parallel to the lower surface and the front surface of the cube space as the X-axis, take the direction passing through the origin O and perpendicular to the lower surface of the cube space as the Y-axis, take the direction passing through the origin O and perpendicular to the X-axis and the Y-axis as the Z-axis, and establish the following Figure 2 The three-dimensional coordinate system shown. The first direction can be any direction. In one embodiment of the present invention, the first direction is the direction where the Z axis is located. The three-dimensional ultrasound volume data can be extracted along the first direction (Z axis) to obtain D first sections. Each first section can be regarded as a two-dimensional image. The size of each first section can be expressed as: W×H.

[0039] The second direction is a direction perpendicular to the first direction. Figure 3 FIG. 1 is a schematic diagram showing a first section according to an embodiment of the present invention. Figure 3 , taking the upper left corner vertex of the first section as the origin o of the image coordinate system, taking the direction passing through the origin o and parallel to the upper boundary of the first section as the direction where the x-axis is located, and taking the direction passing through the origin o and perpendicular to the x-axis as the direction where the y-axis is located, a two-dimensional image coordinate system is established. In one embodiment of the present invention, the second direction is the direction where the y-axis is located.

[0040] The high echo area and the low echo area can be set and divided as needed, for example, they can be divided according to the pixel value in the first section. For example, for any pixel in the first section, if the pixel value of the pixel is less than or equal to a preset threshold, it can be determined that the pixel belongs to the low echo area, and if the pixel value of the pixel is greater than the preset threshold, it can be determined that the pixel belongs to the high echo area. The low echo area can be, for example, the area where the liquid (such as amniotic fluid) in the first section is located, and the high echo area can be, for example, the area where the solid (such as the fetus) in the first section is located.

[0041] Step S130, determining a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, wherein the target segmentation plane is used to segment an object region where the target object is located and other regions except the object region in the three-dimensional ultrasound volume data.

[0042] Exemplarily, based on the first position information and the second position information corresponding to each first section, the segmentation plane (upper limit segmentation plane) where the upper limit of the target segmentation plane is located and the segmentation plane (lower limit segmentation plane) where the lower limit is located can be obtained. The first edge can be any edge of the low echo area corresponding to each first section. The second edge can be any edge of the high echo area corresponding to each first section. For the convenience of description and understanding, the following mainly takes the first edge as the upper edge of the low echo area corresponding to each first section, and the second edge as the upper edge of the high echo area corresponding to each first section as an example for description. For example, based on the first edge of the low echo area corresponding to each first section, the upper limit segmentation plane can be obtained, and based on the second edge of the high echo area corresponding to each first section, the lower limit segmentation plane can be obtained. The target segmentation plane can be any segmentation plane located between the upper limit segmentation plane and the lower limit segmentation plane. Through the obtained target segmentation plane, the object area where the target object is located in the three-dimensional ultrasound volume data and other areas other than the object area can be segmented. The target object is usually an object that can produce high echoes, so it can be included in the high echo area. The target segmentation plane determined by the high echo area and the low echo area can be used to segment the high echo area and the low echo area, and can also be used to segment the object area where the target object is located and other areas except the object area.

[0043] According to the ultrasonic imaging method of an embodiment of the present invention, the position information of the first edge of the low echo area and the second edge of the high echo area corresponding to each first section along the first direction of the three-dimensional ultrasonic volume data can be determined. Then, based on the position information of the first edge of the low echo area and the second edge of the high echo area corresponding to each first section, the target segmentation surface is determined. This method does not require the construction of a large three-dimensional ultrasonic volume database, nor does it require manual labeling, which can greatly reduce resource consumption. When applied to ultrasonic imaging of the fetus, this method can be well applied to fetal identification and positioning in various periods such as early, middle and late pregnancy.

[0044] Exemplarily, for each first section among multiple first sections extracted along a first direction from three-dimensional ultrasound volume data, first position information of a first edge of a low-echo region in the first section in the second direction and second position information of a second edge of a high-echo region in the first section in the second direction are determined, including: for each first section among the multiple first sections, extracting an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate a position of the low-echo region in the corresponding first section, and the initial high-echo image is used to indicate a position of the high-echo region in the corresponding first section; determining first position information of a first edge of the low-echo region in the second direction based at least on the corresponding initial low-echo image; and determining second position information of a second edge of the high-echo region in the second direction based at least on the corresponding initial high-echo image.

[0045] Exemplarily, each first section may have a respective corresponding initial low-echo image and initial high-echo image. Exemplarily, the sizes of each first section and its corresponding initial low-echo image and initial high-echo image may be the same, that is, the size of each initial low-echo image and each initial high-echo image may also be expressed as: W×H. In this case, the pixels in the initial low-echo image may correspond one-to-one to the pixels on the first section, and the pixel value of each pixel in the initial low-echo image may be used to indicate whether the corresponding pixel on the first section belongs to a low-echo region. The initial high-echo image is similar, that is, the pixels in the initial high-echo image may correspond one-to-one to the pixels on the first section, and the pixel value of each pixel in the initial high-echo image may be used to indicate whether the corresponding pixel on the first section belongs to a high-echo region. Alternatively, the sizes of each first section and its corresponding initial low-echo image and initial high-echo image may also be different. For example, the size of the initial low-echo image may be smaller than the size of the corresponding first section, each pixel in the initial low-echo image may correspond to an image block on the first section, and the pixel value of each pixel in the initial low-echo image may be used to indicate whether the corresponding image block belongs to a low-echo region. The initial high-echo image is similar, that is, the size of the initial high-echo image may be smaller than the size of the corresponding first section, each pixel in the initial high-echo image may correspond to an image block on the first section, and the pixel value of each pixel in the initial high-echo image may be used to indicate whether the corresponding image block belongs to a high-echo region. The initial low-echo image may indicate the location of the low-echo region in the first section. The initial high-echo image may indicate the location of the high-echo region in the first section.

[0046] For each first section, the first position information of the first edge of the low echo area in the second direction can be determined based at least on the corresponding initial low echo image. Taking the first edge as the upper edge as an example, the initial low echo image indicates the position of the low echo area. According to the low echo area in the initial low echo image, the upper edge of the low echo area in the second direction can be determined by the Hilbert method or local peak detection, spline fitting, etc. In one embodiment, each column of pixels in the low echo area in the second direction can be traversed along the second direction based on the initial low echo image, and the first pixel point in each column of pixels in the second direction obtained by traversal is used as each edge point of the upper edge of the low echo area. The first position information of the upper edge of the low echo area can be the coordinate information corresponding to each edge point of the upper edge of the low echo area on the y-axis.

[0047] The method for determining the second position information of the second edge of the hyperechoic region is similar to the method for determining the first position information of the first edge of the hypoechoic region, and for the sake of brevity, it is not repeated here. The method for establishing the two-dimensional image coordinate system corresponding to the initial hyperechoic image is the same as the method for establishing the two-dimensional image coordinate system corresponding to the hypoechoic image, and is not repeated here. The second position information of the second edge of the hyperechoic region can be the coordinate information corresponding to each edge point on the upper edge of the hyperechoic region on the y-axis.

[0048] The initial low-echo image and the initial high-echo image can be used to easily distinguish and identify the low-echo area and the high-echo area, which is convenient for quickly determining the position information of the first edge of the low-echo area and the second edge of the high-echo area. Of course, the above embodiments are only examples and are not limitations of the present invention. The initial low-echo image and the initial high-echo image are not necessary, and the positions of the high-echo area and the low-echo area corresponding to the first section can be directly determined based on the pixel values ​​of the first section without first extracting the initial low-echo image and the initial high-echo image.

[0049] Exemplarily, extracting an initial low-echo image and an initial high-echo image corresponding to the first section may include: acquiring a low-echo template image and a high-echo template image, wherein the image sizes of the low-echo template image and the high-echo template image are the same as the image size of each first section in multiple first sections; comparing the pixel value of each first pixel point in the first section with a preset threshold; if the pixel value of the first pixel point is less than or equal to the preset threshold, setting the pixel value of the second pixel point in the low-echo template image to the first pixel value, wherein the position of the second pixel point in the low-echo template image is consistent with the position of the first pixel point in the first section; setting the pixel value of the first remaining pixel point in the low-echo template image to the second pixel value to obtain the initial low-echo image corresponding to the first section, wherein the first remaining pixel point is the pixel point other than the pixel point set to the first pixel value, and the first pixel value is used to indicate the pixel value of the first pixel point in the first section. The corresponding pixel point belongs to the low echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low echo area; if the pixel value of the first pixel point is greater than the preset threshold, the pixel value of the third pixel point in the high echo template image is set to the third pixel value, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; the pixel values ​​of the second remaining pixel points in the high echo template image are set to the fourth pixel value to obtain an initial high echo image corresponding to the first section, wherein the second remaining pixel points are pixel points other than the pixel points set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high echo area; wherein the first pixel point is a pixel point within the effective detection area, and the effective detection area is an area containing the target observation part of the target object.

[0050] In one embodiment, for each first section, a low-echoic template image and a high-echoic template image can be obtained. The image size of the low-echoic template image and the high-echoic template image is the same as the image size of each first section in each first section, that is, the image size of the low-echoic template image and the high-echoic template image can be expressed as: W×H. In one embodiment of the present invention, the pixel value of each pixel in the low-echoic template image and the high-echoic template image can be arbitrary initially, for example, the pixel value of each pixel can be initially set to be equal to 0. Subsequently, the pixel values ​​of corresponding pixels in the low-echoic template image and the high-echoic template image can be updated based on the pixel values ​​of each pixel in the first section. For example, the pixel value of each first pixel in the first section can be compared with a preset threshold. The first pixel can be any pixel in the effective detection area contained in the first section. The effective detection area is an area that includes the target observation part of the target object. The target observation part can be all or part of the target object, such as the head. See. Figure 3 , where the sector area RI surrounded by the white dotted frame is the effective detection area. In one embodiment of the present invention, the target observation part is the entire fetus. Optionally, the range of the effective detection area can be preset by the user. For the pixel point P in the gth row and jth column in the first section gj (where 1≤g≤H, 1≤j≤W), if the first pixel point P gj If the pixel value of the second pixel point in the low echo template image is less than or equal to the preset threshold, the pixel value of the second pixel point in the low echo template image can be set to the first pixel value. gj The position in the first section is consistent. The preset threshold can be preset to any value between (0, 255), for example, the preset threshold can be equal to 20, 30, 40 or 50. The setting method of the preset threshold includes but is not limited to the fixed threshold method, Otsu method, mean iteration method, etc. In one embodiment of the present invention, the preset threshold is equal to 50. If the first pixel point P gjThe pixel value of is equal to 40, then the pixel value of the second pixel in the low echo template image (the pixel located in the i-th row and j-th column in the low echo template image) can be set to the first pixel value. Then, the pixel value of the first remaining pixel in the low echo template image is set to the second pixel value to obtain the initial low echo image LowImg corresponding to the first section P. Among them, the first remaining pixel is a pixel other than the pixel set to the first pixel value. The first pixel value and the second pixel value are any values ​​between [0,255] set by the user, and the first pixel value and the second pixel value are not equal. Exemplarily, the first pixel value can be 255, and the second pixel value can be 0. The first pixel value can indicate that the corresponding pixel belongs to the low echo area, and the second pixel value can indicate that the corresponding pixel does not belong to the low echo area. Optionally, when acquiring the low echo template image, the pixel value of the third remaining pixel therein can be directly set to the second pixel value. The position of the third remaining pixel in the low echo template image is consistent with the position of each pixel in the area other than the effective detection area in the first section in the first section. That is, the corresponding pixel values ​​of each pixel point in the area outside the effective detection area on the low echo template image can be set to the second pixel value in advance to indicate that these pixel points themselves do not belong to the low echo area. Subsequently, the corresponding pixel value can be set on the low echo template image according to the pixel value of each pixel point in the effective detection area.

[0051] The pixel value setting in the high echo template image is similar to that in the low echo template image. For example, if the first pixel point P gj The pixel value of the third pixel point in the high echo template image is equal to 100 and is greater than the preset threshold value (50), then the pixel value of the third pixel point in the high echo template image can be set to the third pixel value. gjThe position in the first section is consistent. That is, the pixel value of the pixel located in the i-th row and j-th column in the high echo template image can be set to the third pixel value. Then, the pixel value of the second remaining pixel in the high echo template image is set to the fourth pixel value to obtain the initial high echo image HighImg corresponding to the first section. The second remaining pixel is a pixel other than the pixel set to the third pixel value. The third pixel value and the fourth pixel value are any values ​​between [0,255] set by the user, and the third pixel value and the fourth pixel value are not equal. Exemplarily, the third pixel value can be 255 and the fourth pixel value can be 0. The third pixel value can indicate that the corresponding pixel belongs to a high echo area, and the fourth pixel value can indicate that the corresponding pixel does not belong to a high echo area. Optionally, when acquiring the high echo template image, the pixel value of the fourth remaining pixel therein can be directly set to the fourth pixel value. The position of the fourth remaining pixel in the high echo template image is consistent with the position of each pixel in the area other than the effective detection area in the first section in the first section. That is, the corresponding pixel values ​​of each pixel point in the area outside the effective detection area on the high echo template image can be set to the fourth pixel value in advance to indicate that these pixel points themselves do not belong to the high echo area. Subsequently, the corresponding pixel value can be set on the high echo template image according to the pixel value of each pixel point in the effective detection area. The third pixel value can be the same as or different from either the first pixel value or the second pixel value, and the fourth pixel value can be the same as or different from either the first pixel value or the second pixel value.

[0052] The above operation can also be expressed by the following formula:

[0053] Among them, P(x g ,y j ) represents the pixel value of the pixel point located in the g-th row and j-th column (i.e., the first pixel point) in the effective detection area on the first slice, T s Indicates the preset threshold, LowImg(x g ,y j ) represents the pixel value of the pixel at the gth row and the jth column (i.e., the second pixel) in the low echo template image. HighImg(x g ,y j ) represents the pixel value of the pixel point (i.e., the third pixel point) located in the g-th row and the j-th column in the high echo template image. The low echo template image and the high echo template image may set the pixel values ​​of all their pixels to 0 at the beginning (i.e., before the pixel values ​​are updated based on the pixel values ​​of each pixel point in the first section). After the pixel value update is completed based on the pixel values ​​of each pixel point in the first section, the updated low echo template image and the high echo template image are obtained as the initial low echo image and the initial high echo image.

[0054] According to the above technical solution, for each first section, a low-echo template image and a high-echo template image are obtained, and then the pixel value of each first pixel in the first section is compared with a preset threshold. When the pixel value of the first pixel is less than or equal to the preset threshold, the pixel value of the second pixel in the low-echo template image is set to the first pixel value, and the pixel value of the first remaining pixel in the low-echo template image is set to the second pixel value, so as to obtain the initial low-echo image corresponding to the first section. When the pixel value of the first pixel is greater than the preset threshold, the pixel value of the third pixel in the high-echo template image is set to the third pixel value, and the pixel value of the second remaining pixel in the high-echo template image is set to the fourth pixel value, so as to obtain the initial high-echo image corresponding to the first section. In the above embodiment, the initial low-echo image and the initial high-echo image are generated by binarizing the pixel values ​​of each pixel in the first section. The above method of obtaining the initial low-echo image and the initial high-echo image is relatively simple and has high computational efficiency. In addition, the binary initial low-echo image and the initial high-echo image are obtained, which is also convenient for distinguishing the low-echo area and the high-echo area.

[0055] Exemplarily, the pixel value of each pixel in the initial low-echo image includes a first pixel value and a second pixel value, the first pixel value is used to indicate that the corresponding pixel in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel in the first section does not belong to the low-echo area; at least based on the corresponding initial low-echo image, determining the first position information of the first edge of the low-echo area in the second direction, including: setting the pixel values ​​in the initial low-echo image in the following manner to obtain the corresponding final low-echo image: based on the initial low-echo image, determining a connected domain in the low-echo area; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is less than the first area threshold, setting the pixel value of the pixel in the initial low-echo image to the second pixel value; For each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold and the pixel meets the first target requirement, the pixel value of the pixel in the initial low-echo image is set to the first pixel value; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold and the pixel does not meet the first target requirement, the pixel value of the pixel in the initial low-echo image is set to the second pixel value; the final low-echo image is traversed along the second direction, and during the traversal process, the position information corresponding to the first pixel point in the second direction obtained from top to bottom in each column along the second direction whose pixel value is the first pixel value is recorded to obtain the first position information of the first edge of the low-echo area in the second direction.

[0056] In one embodiment, for each first section, the pixel values ​​in the initial hypoechoic image may be set (ie, updated) to obtain the corresponding final hypoechoic image.

[0057] In one embodiment of the present invention, for an initial low-echo image corresponding to any first section, a connected domain in a low-echo region contained in the initial low-echo image may be determined by any connected domain determination method. For example, a connected domain determination operation may be performed on pixels located in the low-echo region of the initial low-echo image using a morphological method to determine the connected domain contained in the initial low-echo image. For example, the morphological method may include a closing operation, etc. For each pixel point in the initial low-echo image, for example, for a pixel point Q located in the mth row and nth column of the initial low-echo image LowImg, if the area of ​​the connected domain where the pixel point is located is AreaLabel(x m ,y n ) is less than the first area threshold T A1 , the pixel value of the pixel in the initial low echo image LowImg can be set to the second pixel value. For example, the second pixel value is 0, and the pixel value of the pixel Q located in the mth row and nth column in the initial low echo image LowImg can be set to 0. For each pixel in the initial low echo image, for example, for the pixel Q located in the mth row and nth column in the initial low echo image LowImg, if the area of ​​the connected domain where the pixel is located is AreaLabel(x m ,y n ) is greater than or equal to the first area threshold T A1 If the pixel point meets the first target requirement, the pixel value of the pixel point in the initial low echo image LowImg can be set to the first pixel value. For example, if the first pixel value is 255, the pixel value of the pixel point Q located in the mth row and nth column in the initial low echo image LowImg can be set to 255. The first area threshold T A1 It can be any preset value, such as 200, 300, 400 or 500. The area of ​​a region can be represented by the number of all pixels contained in the region. For example, an area of ​​200 means that the region contains 200 pixels. A1 is 200. The first target requirement may be any requirement set by the user. For example, the first target requirement may include: the position of the pixel point Q in the second direction is above the second edge (upper edge) of the high echo area.

[0058] Exemplarily, the first target requirement may include: the pixel point meets any of the first target conditions, the first target conditions including: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; wherein the first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

[0059] In one embodiment, the first target condition may include: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position. At this time, when the pixel point satisfies the condition that "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the first target position", it is determined that the pixel point meets the first target requirement. In another embodiment, the first target condition may include: the position of the pixel point in the second direction is higher than the first target position. At this time, when the pixel point satisfies the condition that "the position of the pixel point in the second direction is higher than the first target position", it is determined that the pixel point meets the first target requirement. In another embodiment, the first target condition may include: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and the position of the pixel point in the second direction is higher than the first target position. At this time, when the pixel point satisfies any one of the conditions of "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the first target position" and "the position of the pixel point in the second direction is higher than the first target position", that is, when "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the first target position" or "the position of the pixel point in the second direction is higher than the first target position", it can be determined that the pixel point meets the first target requirement. Of course, in this embodiment, if both conditions of the pixel point are met, it can also be determined that the pixel point meets the first target requirement.

[0060] For example, in Figure 3 In the coordinate system shown, the second direction is the y-axis direction. The larger the y-coordinate is, the lower the pixel point is. Therefore, the centroid of the connected domain where the pixel point Q is located is higher than the first target position in the second direction, and the coordinate corresponding to the centroid of the connected domain where the pixel point Q is located on the y-axis is smaller than the first target position T. y1 Similarly, the position of the pixel point in the second direction is higher than the first target position, and the coordinate corresponding to the pixel point Q on the y-axis is less than the first target position T y1 The corresponding coordinates.

[0061] Optionally, the first target position T y1It can be the average of the centroids of at least part of the connected domains in the high echo region in the second direction. In a similar manner to obtaining the connected domains contained in the initial low echo image, the connected domains in the initial high echo image or the final high echo image described below can be obtained as the connected domains in the high echo region. For the sake of brevity, it is not described here. Assume that the connected domain in the high echo region determined based on the initial high echo image or the final high echo image is L high1 , L high2 , L high3 , L high4 and L high5 , the centroid coordinates of each connected domain are (x high1 ,y high1 )、(x high2 ,y high2 )、(x high3 ,y high3 )、(x high4 ,y high4 ) and (x high5 ,y high5 ). For example, the first target position T y1 It can be the average of the centroid positions of all connected domains in the hyperechoic region on the y-axis, that is, the first target position T y1 =(y high1 +y high2 +y high3 +y high4 +y high5 ) / 5. For another example, the first target position T y1 It can be the average of the centroid positions on the y-axis of the connected domains whose area is greater than the preset area threshold in the high echo region. high2 , L high3 and L high5 , then the first target position T y1 =(y high2 +y high3 +y high5 ) / 3.

[0062] It can be seen from the above scheme that the first target position can be related to the position of the centroid of at least part of the connected domain in the high echo area in the second direction. Therefore, when determining the first position information of the first edge of the low echo area in the second direction, the initial low echo image can be considered, and information such as the initial high echo image can also be considered. Of course, this scheme is only an example. For example, the first target position can be determined by other means, such as by user input, etc., and only the initial low echo image can be considered at this time.

[0063] According to the above technical solution, the first target condition is set as follows: the centroid of the connected domain where the pixel point is located is higher than the first target position in the second direction, and / or the position of the pixel point in the second direction is higher than the first target position. Then, the first target requirement is determined based on any of the first target conditions, so that the first target requirement can meet different application scenarios, and at the same time, the accuracy of the final low echo image obtained based on the first target requirement can be guaranteed.

[0064] For each pixel in the initial low echo image, for example, for the pixel Q located in the mth row and nth column in the initial low echo image LowImg, if the area of ​​the connected domain where the pixel is located is AreaLabel(x m ,y n ) is greater than or equal to the first area threshold T A1 And if the pixel point does not meet the first target requirement, it can be determined that the pixel value of the pixel point in the initial low echo image LowImg is equal to the second pixel value. That is, the pixel value of the pixel point Q located in the mth row and nth column in the initial low echo image LowImg can be set to the second pixel value, for example, set to 0. It can be understood that the above description involving "the connected domain where the pixel point is located" means that the pixel point belongs to a certain connected domain, and the pixel value of the pixel point that does not belong to any connected domain may not be updated, so that its pixel value remains the size in the initial low echo image.

[0065] The method of setting the pixel values ​​of the initial low-echo image to obtain the corresponding final low-echo image can be expressed by the formula:

[0066]

[0067] Among them, AreaLabel(x m ,y n ) represents the area of ​​the connected domain where the pixel point located in the mth row and nth column in the initial low echo image LowImg is located. LowLabel(x m ,y n ) represents the pixel value of the pixel located at the mth row and nth column in the initial low echo image LowImg, arearatio represents the area ratio coefficient in the range of (0,1), CentroidLabel(x m ,y n ) represents the centroid of the connected domain of the pixel point located in the mth row and nth column in the initial low echo image LowImg in the second direction, ycentroid high represents the average value of the position of the centroid of at least part of the connected domain in the hyperechoic region in the second direction, that is, the first target position T y1The area ratio coefficient arearatio can be set to any appropriate value as required, which can be a default setting in the system or input by the user.

[0068] The initial low-echo image LowImg is processed in the above manner to obtain the corresponding final low-echo image LowImg'. Then, the final low-echo image LowImg' is traversed along the second direction (the direction where the y-axis is located). During the traversal process, the position information corresponding to the pixel point with the first pixel value of the first pixel value in each column obtained from top to bottom along the second direction is recorded in the second direction, that is, the coordinate value of the pixel point with the first pixel value of 255 in each column obtained from top to bottom along the second direction on the y-axis is recorded to obtain the position information of each edge point in the first edge (upper edge) of the low-echo area in the second direction, that is, to obtain the first position information. Optionally, the coordinate values ​​of the first edges corresponding to each of the D final low-echo images LowImg' can be saved in sequence to a two-dimensional array. Table 1 lists the pixel values ​​of each pixel point of the first edge of the low-echo area in the D final low-echo images according to an embodiment of the present invention. From Table 1, the first position information TopEdge of the first edge of the low-echo area corresponding to each first section can be determined. low .

[0069] Table 1. Pixel values ​​of each pixel point at the first edge of the hypoechoic area in D final hypoechoic images (where the horizontal direction is the width W and the vertical direction is the depth D)

[0070] 0 0 0 … 45 47 50 56 … 80 78 83 90 … 0 0 0 … … … … … … 0 0 0 … 60 67 70 76 … 90 98 93 95 … 0 0 0 … … …

[0071] As shown in Table 1, for the portion where the data is 0, such as the data 0 in the 1st row and the 1st column of Table 1, it means that all the pixel points obtained from top to bottom in the 1st column of the 1st first section are not equal to 255. For the portion where the data is not 0, such as the data 45 in the 1st row and the 5th column of Table 1, it means that the first pixel point whose pixel value is equal to 255 obtained from top to bottom in the 5th column of the 1st first section along the second direction is the 45th pixel point.

[0072] According to the above technical solution, for each first section, by judging whether the area of ​​the connected domain where the pixel point is located is greater than the first area threshold and whether the first target requirement is met, the pixel value of the pixel at the corresponding position in the initial low echo image is adjusted to obtain the final low echo image. Then, the final low echo image is traversed along the second direction, and the position information corresponding to the pixel point in the second direction whose first pixel value is the first pixel value in each column obtained from top to bottom along the second direction is recorded during the traversal process. In this way, the first position information of each edge point in the first edge of the low echo area in the second direction is obtained more accurately.

[0073] Exemplarily, at least part of the connected domains are a preset number of connected domains with the largest area in the high-echo region, or connected domains in the high-echo region whose area exceeds a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

[0074] At least part of the connected domains can be determined by the initial hyperechoic image. In one embodiment, at least part of the connected domains can be a preset number of connected domains with the largest area in the hyperechoic region or the initial hyperechoic image. The preset number can be any pre-set value less than the total number of connected domains in the hyperechoic region. In one embodiment of the present invention, the preset number is 3. For example, the connected domains included in the initial hyperechoic image are L high1 , L high2 , L high3 , L high4 and L high5 , arrange the connected domains from large to small, in the following order: L high3 , L high5 , L high2 , L high4 and L high1 At least part of the connected domains can be the hyperechoic region or the three connected domains with the largest area in the initial hyperechoic image, that is, the connected domain L high3 , L high5 and L high2 In another embodiment, at least part of the connected domain is a high echo area or the area in the initial high echo image exceeds the second area threshold T A2 The second area threshold T A2 It can be any preset value, such as 500, 600, 1000, etc. In one embodiment of the present invention, the second area threshold T A2 is 1000. The connected domain with an area greater than 1000 in the hyperechoic region or the initial hyperechoic image may be used as the at least partially connected domain to determine the first target position. In another embodiment, the at least partially connected domain is a connected domain in which the area of ​​the hyperechoic region or the initial hyperechoic image is greater than a preset ratio threshold in the total area of ​​the initial hyperechoic image. high1 , L high2 , L high3 , L high4 and L high5, the proportions of the areas of the corresponding connected domains in the total area of ​​the initial hyperechoic image are 2 / 5, 1 / 5, 1 / 5, 1 / 10 and 1 / 10 respectively. The preset ratio threshold can be any preset value, for example, the preset ratio threshold can be 1 / 5, 1 / 6 or 1 / 10. In one embodiment of the present invention, the preset ratio threshold is 1 / 10. Therefore, it can be determined that the connected domain L in which the proportion of the area in the initial hyperechoic image to the total area of ​​the initial hyperechoic image is greater than the preset ratio threshold is high1 , L high2 and L high3 , and use these as the connected domain to determine the first target position.

[0075] According to the above technical solution, the connected domains with the largest preset number of areas in the hyperechoic region, or the connected domains in the hyperechoic region whose area exceeds the second area threshold, or the connected domains in the hyperechoic region whose area occupies a proportion greater than the preset proportion threshold in the total area of ​​the initial hyperechoic image are taken as at least partially connected domains. In this way, the method of screening at least partially connected domains can be flexibly adapted to different application scenarios, and the efficiency of determining at least partially connected domains is improved. In addition, the connected domains screened in this way are all connected domains with larger areas in the initial hyperechoic image, which can avoid the influence of the recognition noise of the hyperechoic region, improve the accuracy of the determined first target position, and further improve the accuracy of determining the low echo region.

[0076] Exemplarily, the pixel value of each pixel point in the initial high-echoic image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high-echoic area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high-echoic area; at least based on the corresponding initial high-echoic image, determine the second position information of the second edge of the high-echoic area in the second direction, including: setting the pixel values ​​in the initial high-echoic image in the following manner to obtain the corresponding final high-echoic image: based on the initial high-echoic image, determine the connected domain contained in the high-echoic area; for each pixel point in the initial high-echoic image, if the area of ​​the connected domain where the pixel point is located is less than the third area threshold, set the pixel value of the pixel point in the initial high-echoic image to the fourth pixel value; for the pixel point in the initial high-echoic image For each pixel point of the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the third pixel value; for each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point does not meet the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the fourth pixel value; taking each edge point in the first edge of the low echo area in the second direction as the starting point, traversing the final high echo image along the second direction, during the traversal process, recording the position information in the second direction corresponding to the pixel point whose first pixel value is the third pixel value obtained from top to bottom in each column along the second direction, so as to obtain the second position information of the second edge of the high echo area in the second direction.

[0077] In one embodiment, for each first section, the initial hyperechoic image is processed in the following manner to obtain a corresponding final hyperechoic image.

[0078] In one embodiment of the present invention, for the initial hyperechoic image corresponding to any first section, the connected domain in the hyperechoic region contained in the initial hyperechoic image can be determined by any connected domain determination method. For example, a morphological method can be used to perform a connected domain determination operation on pixels located in the hyperechoic region of the initial hyperechoic image to determine the connected domain contained in the initial hyperechoic image. For example, the morphological method may include a closing operation, etc. For each pixel point in the initial hyperechoic image, for example, for the pixel point R located in the kth row and the lth column in the initial hyperechoic image HighImg, if the area of ​​the connected domain where the pixel point is located is AreaLabel(x k ,y l ) is less than the third area threshold T A3, the pixel value of the pixel in the initial high echo image HighImg can be set to the fourth pixel value. For example, the fourth pixel value is 0, and the pixel value of the pixel R located in the kth row and the lth column in the initial high echo image HighImg can be set to 0. For each pixel in the initial high echo image, for example, for the pixel R located in the kth row and the lth column in the initial high echo image HighImg, if the area of ​​the connected domain where the pixel is located is AreaLabel(x k ,y l ) is greater than or equal to the third area threshold T A3 If the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image HighImg can be set to the third pixel value. For example, the third pixel value is 255, and the pixel value of the pixel point R located in the kth row and the lth column in the initial high echo image HighImg can be set to 255. The third area threshold T A3 It can be any preset value, such as 200, 300, 400 or 500. In one embodiment of the present invention, the third area threshold T A3 is 400. The second target requirement may be any requirement set by the user. For example, the second target requirement may be: the position of the pixel point R in the second direction is below the first edge (upper edge) of the low echo area.

[0079] Exemplarily, the second target requirement may include: the pixel point meets any of the second target conditions, and the second target conditions may include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; wherein the second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction in the second direction.

[0080] In one embodiment, the second target condition may include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position. At this time, when the pixel point satisfies the condition that "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position", it is determined that the pixel point meets the second target requirement. In another embodiment, the second target condition may include: the position of the pixel point in the second direction is lower than the second target position. At this time, when the pixel point satisfies the condition that "the position of the pixel point in the second direction is lower than the second target position", it is determined that the pixel point meets the second target requirement. In another embodiment, the second target condition may include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and the position of the pixel point in the second direction is lower than the second target position. At this time, when the pixel point satisfies any one of the conditions of "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position" and "the position of the pixel point in the second direction is lower than the second target position", that is, when "the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position" or "the position of the pixel point in the second direction is lower than the second target position", it can be determined that the pixel point meets the second target requirement. Of course, in this embodiment, if both conditions of the pixel point are met, it can also be determined that the pixel point meets the second target requirement.

[0081] For example, the position of the centroid of the connected domain where the pixel point R is located in the second direction is lower than the second target position, and the coordinate corresponding to the centroid of the connected domain where the pixel point R is located on the y-axis is greater than the second target position T y2 Similarly, the position of the pixel point in the second direction is lower than the second target position, corresponding to the coordinate corresponding to the pixel point R on the y-axis being greater than the second target position T y2 The corresponding coordinates.

[0082] Optionally, the second target position T y1 It can be the average value of the centroid of at least part of the connected domains in the low echo area in the second direction. Assume that the connected domain contained in the low echo area determined based on the initial low echo image or the final low echo image is L low1 , L low2 , L low3 , L low4 , L low5 and L low6 , the centroid coordinates of each connected domain are (x low1 ,y low1 )、(x low2 ,y low2 )、(x low3 ,y low3 )、(x low4 ,y low4 )、(xlow5 ,y low5 ) and (x low6 ,y low6 ). For example, the second target position T y2 It can be the average of the positions of the centroids of all connected domains in the low echo area on the y-axis, that is, the second target position T y2 =(y low1 +y low2 +y low3 +y low4 +y low5 +y low6 ) / 6. For another example, the second target position T y2 It can be the average of the positions of the centroids of the connected domains whose areas are greater than the preset area threshold in the low echo region on the y-axis. low2 , L low4 and L low5 , then the second target position T y2 =(y low2 +y low4 +y low5 ) / 3.

[0083] It can be seen from the above scheme that the second target position can be related to the low echo area, so when determining the second position information of the second edge of the high echo area in the second direction, the initial high echo image can be considered, and information such as the initial low echo image can also be considered. Of course, this scheme is only an example, for example, the second target position can be determined by other means, such as by user input, etc., in which case only the initial high echo image can be considered.

[0084] According to the above technical solution, the second target condition is set as follows: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position. Then, the second target requirement is determined based on any of the second target conditions, so that the second target requirement can meet different application scenarios, and at the same time, the accuracy of the final high echo image obtained based on the second target requirement can be guaranteed.

[0085] For each pixel in the initial high echo image, for example, for the pixel R located in the kth row and the lth column in the initial high echo image HighImg, if the area of ​​the connected domain where the pixel is located is AreaLabel(x k ,y l ) is greater than or equal to the third area threshold T A3And if the pixel point does not meet the second target requirement, it can be determined that the pixel value of the pixel point in the initial high echo image HighImg is equal to the fourth pixel value. That is, the pixel value of the pixel point R located in the kth row and the lth column in the initial high echo image HighImg can be set to the fourth pixel value, for example, equal to 0. It can be understood that the above description involving "the connected domain where the pixel point is located" means that the pixel point belongs to a certain connected domain, and the pixel value of the pixel point that does not belong to any connected domain may not be updated, so that its pixel value maintains its size in the initial high echo image.

[0086] The method of setting the pixel value of the initial hyperechoic image to obtain the corresponding final hyperechoic image can be expressed by the formula:

[0087]

[0088] Among them, AreaLabel(x k ,y l ) represents the area of ​​the connected domain where the pixel point located at the kth row and the lth column in the initial high echo image HighImg is located, represents the pixel value of the pixel point located at the kth row and the lth column in the initial high echo image HighImg, arearatio represents the area ratio coefficient in the range of (0,1), CentroidLabel(x k ,y l ) represents the centroid of the connected domain of the pixel point located in the kth row and the lth column in the initial high echo image HightImg in the second direction, TopEdge low Indicates the edge point of the first edge of the low echo area in the second direction. The area ratio coefficient arearatio can be set to any appropriate value as needed, which can be set by default in the system or input by the user. The area ratio coefficient arearatio used when setting the pixel value of the initial high echo image and the area ratio coefficient arearatio used when setting the pixel value of the initial low echo image can be the same or different.

[0089] The initial high-echo image HighImg is processed in the above manner to obtain the corresponding final high-echo image HighImg'. Then, taking each edge point in the first edge (upper edge) of the final low-echo area in the second direction as the starting point, the final high-echo image HighImg' is traversed along the second direction (the direction where the y-axis is located). During the traversal process, the position information corresponding to the pixel point in the second direction whose first pixel value is the third pixel value in each column obtained from top to bottom along the second direction is recorded, that is, the coordinate value on the y-axis of the pixel point whose first pixel value is 255 in each column obtained from top to bottom along the second direction is recorded to obtain the position information of each edge point in the second edge of the high-echo area in the second direction, that is, to obtain the second position information. Optionally, the coordinate values ​​of the second edges corresponding to each of the D final high-echo images HighImg' can be saved in sequence to a two-dimensional array.

[0090] According to the above technical solution, for each first section, by judging whether the area of ​​the connected domain where the pixel point is located is greater than the third area threshold and whether the second target requirement is met, the pixel value of the corresponding position pixel in the initial high echo image is adjusted to obtain the final high echo image. Then, the final high echo image is traversed along the second direction, and the position information corresponding to the first pixel point with the first pixel value in each column obtained from top to bottom along the second direction is recorded during the traversal process. In this way, the second position information of each edge point in the second edge of the high echo area in the second direction is obtained more accurately.

[0091] Exemplarily, determining a target segmentation plane based on first position information and second position information corresponding to each of the multiple first cut planes includes: determining an initial segmentation plane based on the first position information and second position information corresponding to each of the multiple first cut planes, the initial segmentation plane containing segmentation lines corresponding one-to-one to the multiple first cut planes, and the segmentation line corresponding to each first cut plane is located between an edge corresponding to the first position information and an edge corresponding to the second position information; wherein the initial segmentation plane is the target segmentation plane, or determining the target segmentation plane based on the first position information and second position information corresponding to each of the multiple first cut planes also includes: optimizing the initial segmentation plane to determine the target segmentation plane.

[0092] In one embodiment, the initial segmentation plane can be determined based on the first position information and the second position information corresponding to each first section. The initial segmentation plane contains segmentation lines corresponding to each first section one by one, and the segmentation line corresponding to each first section is located between the edges corresponding to the first position information and the second position information. For example, if for any first section, the coordinates of the first column of pixels in the edge corresponding to the corresponding first position information (i.e., the first edge of the low echo area) are 50, and the coordinates of the first column of pixels in the edge corresponding to the second position information (i.e., the second edge of the high echo area) are 150, then the coordinates of the pixels in the first column of the segmentation line corresponding to the first section can be any coordinate value within the range of [50,150]. For example, the coordinate value in the middle position of [50,150], i.e., the coordinate value 100, can be selected as the position information of the first pixel on the segmentation line. In a similar manner, the position information of each point on the segmentation line can be determined, which will not be repeated here for the sake of brevity. Based on the segmentation line corresponding to each first section, the initial segmentation plane can be determined. In one embodiment, the initial segmentation plane can be directly used as the target segmentation plane. In another embodiment, after determining the initial segmentation plane based on the first position information and the second position information corresponding to each first section, the initial segmentation plane may be optimized to determine the target segmentation plane. Exemplarily and non-limitingly, the initial segmentation plane may be optimized by smoothing, interpolating, filtering, etc. to determine the target segmentation plane.

[0093] In one embodiment, the initial segmentation surface can be determined by the following expression:

[0094] InitCurvelPlane(x,y v1 )=

[0095] TopEdge low (x,y v1 )+{TopEdge high (x,y v1 )-TopEdge low (x,y v1 )}×factor, where InitCurvelPlane(x u1 ,y v1 ) indicates that the initial segmentation surface is the first segmentation surface d i The coordinates of the pixel points of the corresponding segmentation line located in the v1th column, i = 1, 2, 3, ..., D. TopEdge low (x,y v1 ) represents the first section d i The coordinates of the pixel point located in the v1th column in the first edge of the hypoechoic region in TopEdge high (x,yv1 ) represents the first section d i The coordinates of the pixel point located in the v1th column in the second edge of the high echo area in , factor represents the influence factor, and factor can be any value in the range of [0,1]. Optionally, factor can be set by default in the system, or can be set by the user at any time as needed.

[0096] According to the above technical solution, a segmentation line is determined between the edges corresponding to the first position information and the second position information corresponding to the first section plane to obtain an initial segmentation plane and use the initial segmentation plane as the target segmentation plane or further obtain the target segmentation plane by optimizing the initial segmentation plane. The target segmentation plane determined in this way is basically between the first edge of the low echo area and the second edge of the high echo area. The target segmentation plane set in this way can ensure accurate distinction between the low echo area and the high echo area.

[0097] Exemplarily, optimizing the initial segmentation plane to determine the target segmentation plane may include: interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane.

[0098] In one embodiment, the pixel points with zero pixel values ​​in the initial segmentation surface may be interpolated to obtain the target segmentation surface. The interpolation method may include but is not limited to: any one or more of nearest neighbor interpolation, linear interpolation and high-order interpolation.

[0099] According to the above technical solution, by interpolating the pixel points with zero pixel value in the initial segmentation surface, the obtained target segmentation surface can be made more continuous as a whole, which helps to improve the segmentation accuracy of the target segmentation surface for the area where the target object is located.

[0100] Exemplarily, before interpolating the pixel points with zero pixel value in the initial segmentation surface to obtain the target segmentation surface, optimizing the initial segmentation surface and determining the target segmentation surface may also include: for each fourth pixel point in the initial segmentation surface, calculating the mean of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and the standard deviation of the pixel values ​​of each pixel point in the first pixel point set; when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, setting the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation; or, when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation, setting the pixel value of the fourth pixel point to the sum of the mean and the standard deviation; wherein the first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located. A non-zero pixel point is a pixel point whose pixel value is not 0.

[0101] In one embodiment, any non-zero pixel point in the initial segmentation surface can be used as the fourth pixel point. For each fourth pixel point, for example, the fourth pixel point A is a pixel point located at the u2th row and the v2th column in the initial segmentation surface, the mean avg of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point A is located and the standard deviation std of the pixel values ​​of each pixel point in the first pixel point set can be calculated. The first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located. When the first pixel set is a set consisting of all non-zero pixels in the row where the fourth pixel point is located, if the pixel value of the fourth pixel point A is less than the absolute value of the difference between the mean avg and the standard deviation std, the pixel value of the fourth pixel point A can be set to the absolute value of the difference between the mean avg and the standard deviation std; or, if the pixel value of the fourth pixel point A is greater than the sum of the mean avg and the standard deviation std, the pixel value of the fourth pixel point A can be set to the sum of the mean avg and the standard deviation std, so as to optimize the initial segmentation surface in the row direction. When the first pixel set is a set consisting of all non-zero pixels in the column where the fourth pixel point is located, the initial segmentation surface can also be optimized in the column direction in a manner similar to the above. The optimization in the row direction and the optimization in the column direction can be performed one by one, or both can be performed. For example, the initial segmentation surface can be optimized in the row direction first, and then the optimized initial segmentation surface can be optimized in the column direction. In addition, the row-wise optimization and the column-wise optimization may be performed once or multiple times respectively, and any row-wise optimization or column-wise optimization may be performed before or after the step of interpolating the pixel points with zero pixel values ​​in the initial segmentation surface.

[0102] The above operation can be expressed by the following formula:

[0103]

[0104] Among them, InitCurvePlane(x u2 ,y v2 ) represents the pixel point located at the u2th row and v2th column in the initial segmentation surface, “|avg-std|” represents the absolute value of the difference between the mean avg of the pixel values ​​of all non-zero pixels in the row (or column) where the fourth pixel point is located and the standard deviation std, and “avg+std” represents the sum of the mean avg of the pixel values ​​of all non-zero pixels in the row (or column) where the fourth pixel point is located and the standard deviation std.

[0105] According to the above technical solution, when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, the pixel value of the fourth pixel point is set to the absolute value of the difference between the mean and the standard deviation; or, when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation, the pixel value of the fourth pixel point is set to the sum of the mean and the standard deviation. In this way, the initial segmentation surface can be optimized in the row direction and / or column direction to ensure the accuracy of the target segmentation surface obtained.

[0106] Exemplarily, before interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, and / or after interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, the method also includes: for any fifth pixel point in the initial segmentation plane, filtering the fifth pixel point based on the pixel values ​​of non-zero pixel points in an area of ​​the target size around the fifth pixel point.

[0107] The fifth pixel point may be any pixel point in the initial segmentation plane. In one embodiment of the present invention, the fifth pixel point is any non-zero pixel point in the initial segmentation plane. The target-sized area around the fifth pixel point may be an area of ​​any size. For example, the target-sized area around the fifth pixel point may be a 3×3 area centered on the fifth pixel point, or a 5×5 area centered on the fifth pixel point, etc. The filtering method includes, but is not limited to, any one or more of median filtering, mean filtering, median filtering, etc., and the present invention does not limit this. For example, the pixel values ​​of the non-zero pixels in the target-sized area may be averaged, and the obtained average value may be used as the pixel value of the fifth pixel point.

[0108] In one embodiment, before the step of "interpolating the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane", the following operation may be performed: for any fifth pixel point in the initial segmentation plane, filtering the fifth pixel point based on the pixel values ​​of non-zero pixel points in the area of ​​the target size around the fifth pixel point. In another embodiment, after the step of "interpolating the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane", the following operation may be performed: for any fifth pixel point in the initial segmentation plane, filtering the fifth pixel point based on the pixel values ​​of non-zero pixel points in the area of ​​the target size around the fifth pixel point.

[0109] According to the above technical solution, before and / or after interpolating the pixel points with zero pixel values ​​in the initial segmentation surface to obtain the target segmentation surface, the noise in the initial segmentation surface can be removed by filtering the pixel values ​​of the non-zero pixels in the area of ​​the target size around any fifth pixel point in the initial segmentation surface, thereby improving the accuracy of the target segmentation surface obtained based on the initial segmentation surface.

[0110] Exemplarily, after determining the target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the method may further include: determining a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane.

[0111] In one embodiment, after step S130, the method may further include the following operations. Based on the obtained target segmentation plane, the target segmentation plane may be projected onto any second section of the three-dimensional ultrasound volume data to obtain a segmentation line in the two-dimensional ultrasound image. The second section may be the same as any first section, or the second section may be a section of the three-dimensional ultrasound volume data in a direction other than the first direction (e.g., the direction where the Y axis is located).

[0112] According to the above technical solution, the target segmentation plane is determined by the low echo area and the high echo area, and then the segmentation line of the two-dimensional ultrasound image on any second section of the three-dimensional ultrasound volume data is determined, so that the characteristics of the target object in the three-dimensional ultrasound volume data are relatively low, and the target object can be accurately positioned. In addition, the method can obtain the segmentation line in the two-dimensional ultrasound image, which helps to assist the user to determine the area where the target object is located and improve the accuracy of the ultrasound examination results.

[0113] Exemplarily, determining a segmentation line of a two-dimensional ultrasound image of three-dimensional ultrasound volume data on any second section based on a target segmentation plane may include: determining a segmentation template based on the target segmentation plane, the segmentation template being consistent with the number of voxel points in the three-dimensional ultrasound volume data, each voxel point in the segmentation template having a voxel value, and the voxel value being used to indicate whether a corresponding voxel point in the three-dimensional ultrasound volume data belongs to a target object; and projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0114] In one embodiment, the step of "determining the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane" may include the following operations. Based on the target segmentation plane, a segmentation template may be determined. The number of voxel points in the segmentation template is the same as the number of voxel points in the three-dimensional ultrasound volume data. The voxel value of each voxel point in the segmentation template may be used to indicate whether the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object. Exemplarily and not restrictively, the voxel value of any voxel point in the segmentation template may be equal to 0 or 255. For example, if the voxel value of the voxel point is equal to 0, it may indicate that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object; if the voxel value of the voxel point is equal to 255, it may indicate that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object. Then, the obtained segmentation template is projected into a two-dimensional coordinate system corresponding to the second section, and the segmentation line of the three-dimensional ultrasound volume data in the two-dimensional ultrasound image on the second section may be obtained.

[0115] In one embodiment of the present invention, the implementation method of determining the segmentation template based on the target segmentation surface can be expressed by the following formula:

[0116]

[0117] Among them, CurvePlane(x u3 , z v3 ) represents the pixel value at row u3 and column v3 in the target segmentation surface. CutVol(x u3 ,y u3 , z v3 ) indicates that the coordinates in the segmented 3D ultrasound volume data are (x u3 ,y u3 , z v3 ) is the voxel value of the voxel point at u3 ,y u3 , z v3 ) represents the coordinates of the unsegmented 3D ultrasound volume data (x u3， y u3， z v3 ), the voxel value of the voxel point at u3， y u3 , z v3 ) indicates that the coordinates in the segmentation template are (x u3 ,y u3 , z v3 ) is the voxel value of the voxel point at .

[0118] According to the above technical solution, the method obtains the segmentation line of the two-dimensional ultrasound image on the second section of the three-dimensional ultrasound volume data through the segmentation template, so that the segmentation line of the two-dimensional ultrasound image on any second section can be flexibly obtained with high efficiency.

[0119] Exemplarily, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. Projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section may include: projecting the segmentation template into the two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; determining the pixel points whose first pixel value in each column of the segmentation section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; uniformly sampling the second pixel point set to obtain at least two discrete pixel points; interpolating the at least two discrete pixel points to obtain a target segmentation line, which is the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0120] In one embodiment, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. Exemplarily and not restrictively, the first value and the second value can be any two unequal values ​​between [0, 255], for example, the first value can be equal to 255 and the second value can be equal to 0, or the first value can be equal to 245 and the second value can be equal to 15.

[0121] Exemplarily, the segmentation template can be projected into a two-dimensional coordinate system corresponding to the second section using a matrix transformation operation, thereby obtaining the segmentation section. The two-dimensional coordinate system corresponding to the second section can be a screen coordinate system of a display screen. For the obtained segmentation section, the pixel points whose first pixel value in each column of the segmentation section is equal to the first value are determined from top to bottom along the second direction (the direction of the y-axis) to obtain a second pixel point set. In one embodiment of the present invention, the first value is 255. The second pixel point set is uniformly sampled to obtain at least two discrete pixel points. For example, by uniformly sampling the second pixel point set, n discrete pixel points {F 1 (x 1 ,y 1 ), F 2 (x 2 ,y 2 ),...,F n (x n ,y n)}, 2≤n≤W. The target segmentation line can be obtained by interpolating n discrete pixel points. The target segmentation line is the segmentation line of the two-dimensional ultrasound image on the second section of the three-dimensional ultrasound volume data. Interpolation can be implemented using any existing or future interpolation algorithm. By way of example and not limitation, the interpolation methods may include: quadratic spline interpolation, cubic spline interpolation or bilinear interpolation, etc. In one embodiment of the present invention, cubic spline interpolation can be used to interpolate at least two discrete pixel points in the range of [0,W]. The principle of cubic spline interpolation is: for n+1 nodes, there are n segments, and each segment is fitted using a cubic function. In order to maintain continuity and smoothness between adjacent segments, the following conditions need to be met:

[0122] S i (x) = a i +b i (xx i )+c i (xx i ) 2 +d i (xx i ) 3 ,i=0,1,…n-1

[0123]

[0124]

[0125]

[0126] In the formula, S i (x) is the cubic function expression of the ith segment, and a, b, c, d are the coefficient values ​​of the cubic function; (x i ,y i )、(x i+1 ,y i+1 ) are the left and right discrete points of the i-th segment respectively; S i ′(x i+1 ) is the first-order derivative of the right discrete point of the i-th segment, S i ″(x i+1 ) is the second-order derivative of the right discrete point of the i-th segment.

[0127] According to the above technical solution, based on the segmentation section, a second set of pixel points can be obtained, and then the second set of pixel points is uniformly sampled to obtain at least two discrete pixel points. Finally, at least two discrete pixel points are interpolated to obtain a final segmentation line. The final segmentation line obtained by this method can remain continuous and smooth, so the final segmentation line is used to segment the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section more accurately.

[0128] Exemplarily, after determining a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane, the method further includes: displaying the two-dimensional ultrasound image and the segmentation line of the three-dimensional volume data on the second section on a display interface.

[0129] In one embodiment, the device for implementing the ultrasonic imaging method of the present invention may include a display device. After determining the segmentation line of the two-dimensional ultrasonic image of the three-dimensional ultrasonic volume data on any second section based on the target segmentation plane, the two-dimensional ultrasonic image and the segmentation line of the three-dimensional volume data on the second section may be displayed on a display interface of the display device. Figure 4 FIG. 4 is a schematic diagram showing a segmentation line of a two-dimensional ultrasound image according to an embodiment of the present invention. Figure 4 As shown, the dividing line can divide the area where the fetus is located in the two-dimensional ultrasound image and other areas except the fetus. This solution supports presenting the position of the dividing line in the two-dimensional ultrasound section to facilitate users to view the specific segmentation position. At the same time, it can also help to quickly display the area where the target object is located in the two-dimensional ultrasound image without being blocked by obstructions. For example, by displaying the two-dimensional ultrasound image and the dividing line displayed on the display interface, some tissue obstructions that may exist above the target object can be removed, thereby quickly displaying the area where the target object is located. In addition, before displaying the two-dimensional ultrasound image of the three-dimensional volume data on the second section, the three-dimensional ultrasound volume data can also be rendered by volume rendering, and lighting models such as ambient light and scattered light can be added during the rendering process, so that the display of the rendered three-dimensional ultrasound volume data can be smoother, thereby making the display effect of the two-dimensional ultrasound image of the three-dimensional volume data on the second section better. This makes it convenient for users to view and improves user experience.

[0130] According to another aspect of the present invention, an ultrasonic imaging device is provided. Figure 5 FIG. 5 shows a schematic block diagram of an ultrasonic imaging device 500 according to an embodiment of the present invention. Figure 5 As shown, the device 500 may include an acquisition module 510 , a first determination module 520 , and a second determination module 530 .

[0131] The acquisition module 510 is used to acquire three-dimensional ultrasound volume data containing the target object.

[0132] The first determination module 520 is used to determine, for each first section among multiple first sections extracted and obtained along the first direction of the three-dimensional ultrasound volume data, first position information of a first edge of a low-echo region in the first section in the second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of the high-echo region on a side close to the low-echo region in the second direction.

[0133] The second determination module 530 is used to determine a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, wherein the target segmentation plane is used to segment an object region where a target object is located and other regions except the object region in the three-dimensional ultrasound volume data.

[0134] Exemplarily, the first determination module 520 includes: an extraction submodule, used to extract, for each first section among multiple first sections, an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate the position of the low-echo area in the corresponding first section, and the initial high-echo image is used to indicate the position of the high-echo area in the corresponding first section; a first determination submodule, used to determine, for each first section among multiple first sections, first position information of a first edge of the low-echo area in the second direction based at least on the corresponding initial low-echo image; and a second determination submodule, used to determine, for each first section among multiple first sections, second position information of a second edge of the high-echo area in the second direction based at least on the corresponding initial high-echo image.

[0135] Exemplarily, the extraction submodule may include: an acquisition unit, used to acquire a low-echo template image and a high-echo template image, wherein the image size of the low-echo template image and the high-echo template image is the same as the image size of each first section in multiple first sections; a comparison unit, used to compare the pixel value of each first pixel in the first section with a preset threshold; a first setting unit, used to set the pixel value of a second pixel in the low-echo template image to the first pixel value if the pixel value of the first pixel is less than or equal to the preset threshold, wherein the position of the second pixel in the low-echo template image is consistent with the position of the first pixel in the first section; a second setting unit, used to set the pixel value of the first remaining pixel in the low-echo template image to the second pixel value, so as to obtain an initial low-echo image corresponding to the first section, wherein the first remaining pixel is a pixel other than the pixel set to the first pixel value, and the first pixel value is used to indicate the corresponding pixel in the first section. The point belongs to the low echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low echo area; the third setting unit is used to set the pixel value of the third pixel point in the high echo template image to the third pixel value if the pixel value of the first pixel point is greater than the preset threshold, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; the fourth setting unit is used to set the pixel value of the second remaining pixel points in the high echo template image to the fourth pixel value to obtain an initial high echo image corresponding to the first section, wherein the second remaining pixel points are pixel points other than the pixel points set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high echo area; wherein the first pixel point is a pixel point in the effective detection area, and the effective detection area is an area containing the target observation part in the target object.

[0136] Exemplarily, the pixel value of each pixel in the initial low-echo image includes a first pixel value and a second pixel value, the first pixel value is used to indicate that the corresponding pixel in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel in the first section does not belong to the low-echo area; the first determination submodule includes: a fifth setting unit, used to determine the connected domain in the low-echo area based on the initial low-echo image; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is less than the first area threshold, the pixel value of the pixel in the initial low-echo image is set to the second pixel value; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold, If the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point meets the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the first pixel value; for each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point does not meet the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the second pixel value; a first traversal unit is used to traverse the final low-echo image along the second direction, and during the traversal process, record the position information in the second direction corresponding to the first pixel point whose pixel value is the first pixel value in each column obtained from top to bottom along the second direction, so as to obtain the first position information of the first edge of the low-echo area in the second direction.

[0137] Exemplarily, the first target requirement includes: the pixel point meets any of the first target conditions, the first target conditions including: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; wherein the first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

[0138] Exemplarily, at least part of the connected domains are a preset number of connected domains with the largest area in the high-echo region, or connected domains in the high-echo region whose area exceeds a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

[0139] Exemplarily, the pixel value of each pixel in the initial high echo image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel in the first section does not belong to the high echo area; the second determination submodule may include: a sixth setting unit, used to determine the connected domain contained in the high echo area based on the initial high echo image; for each pixel in the initial high echo image, if the area of ​​the connected domain where the pixel is located is less than the third area threshold, the pixel value of the pixel in the initial high echo image is set to the fourth pixel value; for each pixel in the initial high echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the third area threshold and the image If the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the third pixel value; for each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point does not meet the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the fourth pixel value; a second traversal unit is used to traverse the final high echo image along the second direction with each edge point in the first edge of the low echo area in the second direction as the starting point, and during the traversal process, record the position information in the second direction corresponding to the pixel point whose first pixel value is the third pixel value obtained from top to bottom in each column along the second direction, so as to obtain the second position information of the second edge of the high echo area in the second direction.

[0140] Exemplarily, the second target requirement includes: the pixel point meets any of the second target conditions, the second target conditions include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; wherein the second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction in the second direction.

[0141] Exemplarily, the second determination module may include a third determination submodule, which is used to: determine an initial segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, wherein the initial segmentation plane includes segmentation lines corresponding to the multiple first sections one by one, and the segmentation line corresponding to each first section is located between the edge corresponding to the first position information and the edge corresponding to the second position information; wherein the initial segmentation plane is the target segmentation plane, or the second determination module may further include an optimization submodule, which is used to optimize the initial segmentation plane and determine the target segmentation plane.

[0142] Exemplarily, the optimization submodule may include a first interpolation unit, configured to interpolate pixel points with zero pixel values ​​in the initial segmentation surface to obtain a target segmentation surface.

[0143] Exemplarily, the optimization submodule may also include: a calculation unit, which is used to interpolate the pixel points with zero pixel values ​​in the initial segmentation surface in the first interpolation unit to obtain the target segmentation surface, and before calculating, for each fourth pixel point in the initial segmentation surface, the mean of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and the standard deviation of the pixel values ​​of each pixel point in the first pixel point set; a seventh setting unit, which is used to set the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation for each fourth pixel point in the initial segmentation surface when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation; or, a sixth submodule, which is used to set the pixel value of the fourth pixel point to the sum of the mean and the standard deviation for each fourth pixel point in the initial segmentation surface when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation; wherein the first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located.

[0144] Exemplarily, the ultrasonic imaging device 500 may further include a filtering module, which is used to filter any fifth pixel point in the initial segmentation plane based on the pixel values ​​of non-zero pixels in an area of ​​a target size around the fifth pixel point before the first interpolation unit interpolates the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, and / or after the first interpolation unit interpolates the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane.

[0145] Exemplarily, the ultrasonic imaging device 500 may further include a third determination module. The third determination module is configured to determine a segmentation line of a two-dimensional ultrasonic image of the three-dimensional ultrasonic volume data on any second section based on the target segmentation plane after the second determination module 530 determines the target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections.

[0146] Exemplarily, the third determination module may include a fourth determination submodule and a projection submodule. The fourth determination submodule is used to determine a segmentation template based on the target segmentation plane, the segmentation template is consistent with the number of voxel points in the three-dimensional ultrasound volume data, each voxel point in the segmentation template has a voxel value, and the voxel value is used to indicate whether the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object; the projection submodule is used to project the segmentation template into a two-dimensional coordinate system corresponding to the second section, and obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0147] Exemplarily, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. The acquisition submodule may include a first acquisition unit, a second acquisition unit, a sampling unit, and a second interpolation unit. The projection submodule may specifically include: a projection unit, which is used to project the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; a determination unit, which is used to sequentially determine the pixel points whose first pixel value in each column of the segmentation section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; a sampling unit, which is used to uniformly sample the second pixel point set to obtain at least two discrete pixel points; a second interpolation unit, which is used to interpolate at least two discrete pixel points to obtain a target segmentation line, which is a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0148] Exemplarily, the ultrasonic imaging device 500 may include a display module. The display module is configured to display the two-dimensional ultrasonic image and the segmentation line of the three-dimensional ultrasonic volume data on the second section on a display interface after the third determination module determines the segmentation line of the two-dimensional ultrasonic image of the three-dimensional ultrasonic volume data on any second section based on the target segmentation plane.

[0149] Those skilled in the art may understand the implementation of the ultrasonic imaging device and its beneficial effects by reading the above description of the ultrasonic imaging method, and will not be described in detail here for the sake of brevity.

[0150] According to yet another aspect of the present invention, an electronic device is provided. Figure 6 FIG. 2 shows a schematic block diagram of an electronic device according to an embodiment of the present invention. Figure 6 As shown, the electronic device includes a processor 610 and a memory 620. The memory 620 stores computer programs / instructions. The processor 610 executes the computer programs / instructions to implement the above-mentioned ultrasound imaging method.

[0151] The electronic device may be an ultrasonic device, such as a desktop ultrasonic diagnostic device, or a portable ultrasonic diagnostic device (such as a notebook ultrasonic diagnostic device or a tablet ultrasonic diagnostic device), and may also be an ultrasonic imaging workstation.

[0152] In one embodiment, the computer program / instructions are used by the processor 610 to execute the following when it is running: acquiring three-dimensional ultrasound volume data containing a target object; for each first section among a plurality of first sections extracted along a first direction from the three-dimensional ultrasound volume data, determining first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; determining a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the target segmentation plane being used to segment an object region in the three-dimensional ultrasound volume data where the target object is located and other regions except the object region.

[0153] Exemplarily, the computer program / instructions executed when the processor 610 is running the step of "for each first section among multiple first sections extracted along the first direction from the three-dimensional ultrasound volume data, determining first position information of a first edge of a low-echo region in the first section in the second direction and second position information of a second edge of a high-echo region in the first section in the second direction", include: for each first section among the multiple first sections, extracting an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate the position of the low-echo region in the corresponding first section, and the initial high-echo image is used to indicate the position of the high-echo region in the corresponding first section; determining first position information of a first edge of the low-echo region in the second direction based at least on the corresponding initial low-echo image; and determining second position information of a second edge of the high-echo region in the second direction based at least on the corresponding initial high-echo image.

[0154] Exemplarily, the computer program / instructions used to execute the step of "extracting an initial low-echo image and an initial high-echo image corresponding to the first section" when the processor 610 is running include: acquiring a low-echo template image and a high-echo template image, wherein the image size of the low-echo template image and the high-echo template image is the same as the image size of each first section in multiple first sections; comparing the pixel value of each first pixel in the first section with a preset threshold; if the pixel value of the first pixel is less than or equal to the preset threshold, setting the pixel value of the second pixel in the low-echo template image to the first pixel value, wherein the position of the second pixel in the low-echo template image is consistent with the position of the first pixel in the first section; setting the pixel value of the first remaining pixel in the low-echo template image to the second pixel value to obtain the initial low-echo image corresponding to the first section, wherein the first remaining pixel is the pixel other than the pixel set to the first pixel value, and the first The pixel value is used to indicate that the corresponding pixel point in the first section belongs to the low echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low echo area; if the pixel value of the first pixel point is greater than the preset threshold, the pixel value of the third pixel point in the high echo template image is set to the third pixel value, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; the pixel value of the second remaining pixel points in the high echo template image is set to the fourth pixel value to obtain an initial high echo image corresponding to the first section, wherein the second remaining pixel points are pixel points other than the pixel points set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high echo area; wherein the first pixel point is a pixel point within the effective detection area, and the effective detection area is an area containing the target observation part of the target object.

[0155] Exemplarily, the pixel value of each pixel in the initial low-echo image includes a first pixel value and a second pixel value, the first pixel value is used to indicate that the corresponding pixel in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel in the first section does not belong to the low-echo area; the computer program / instructions are used by the processor 610 to execute the step of "determining the first position information of the first edge of the low-echo area in the second direction at least based on the corresponding initial low-echo image" when it is executed, including: setting the pixel values ​​in the initial low-echo image in the following manner to obtain the corresponding final low-echo image: based on the initial low-echo image, determining the connected domain in the low-echo area; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is less than the first area threshold, the pixel in the initial low-echo image is set. The pixel value of the point is set to the second pixel value; for each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point meets the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the first pixel value; for each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point does not meet the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the second pixel value; the final low-echo image is traversed along the second direction, and during the traversal process, the position information corresponding to the first pixel point in the second direction obtained from top to bottom in each column along the second direction whose pixel value is the first pixel value is recorded to obtain the first position information of the first edge of the low-echo area in the second direction.

[0156] Exemplarily, the first target requirement includes: the pixel point meets any of the first target conditions, the first target conditions including: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; wherein the first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

[0157] Exemplarily, at least part of the connected domains are a preset number of connected domains with the largest area in the high-echo region, or connected domains in the high-echo region whose area exceeds a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

[0158] Exemplarily, the pixel value of each pixel in the initial high-echoic image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel in the first section belongs to the high-echoic area, and the fourth pixel value is used to indicate that the corresponding pixel in the first section does not belong to the high-echoic area; the computer program / instructions are used by the processor 610 to execute the step of "determining the second position information of the second edge of the high-echoic area in the second direction at least based on the corresponding initial high-echoic image" when it is executed, including: setting the pixel values ​​in the initial high-echoic image in the following manner to obtain the corresponding final high-echoic image: determining the connected domain contained in the high-echoic area based on the initial high-echoic image; for each pixel in the initial high-echoic image, if the area of ​​the connected domain where the pixel is located is less than the third area threshold, setting the pixel value of the pixel in the initial high-echoic image to the fourth area threshold; pixel value; for each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the third pixel value; for each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point does not meet the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the fourth pixel value; starting from each edge point in the first edge of the low echo area in the second direction, traversing the final high echo image along the second direction, during the traversal process, recording the position information in the second direction corresponding to the pixel point whose first pixel value is the third pixel value obtained from top to bottom in each column along the second direction, so as to obtain the second position information of the second edge of the high echo area in the second direction.

[0159] Exemplarily, the second target requirement includes: the pixel point meets any of the second target conditions, the second target conditions include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; wherein the second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction in the second direction.

[0160] Exemplarily, the step of "determining the target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections" executed by the computer program / instructions when the processor 610 is running includes: determining an initial segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, the initial segmentation plane containing segmentation lines corresponding one-to-one to the multiple first sections, and the segmentation line corresponding to each first section is located between the edge corresponding to the first position information and the edge corresponding to the second position information; wherein the initial segmentation plane is the target segmentation plane, or, determining the target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, also includes: optimizing the initial segmentation plane to determine the target segmentation plane.

[0161] Exemplarily, the step of "optimizing the initial segmentation plane and determining the target segmentation plane" performed by the processor 610 when the computer program / instructions are executed includes: interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane.

[0162] Exemplarily, before the step of "interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain a target segmentation plane" executed when the computer program / instruction is executed by the processor 610, the step of "optimizing the initial segmentation plane and determining the target segmentation plane" executed when the computer program / instruction is executed by the processor 610 may also include: for each fourth pixel point in the initial segmentation plane, calculating the mean of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and the standard deviation of the pixel values ​​of each pixel point in the first pixel point set; when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, setting the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation; or, when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation, setting the pixel value of the fourth pixel point to the sum of the mean and the standard deviation; wherein the first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located.

[0163] Exemplarily, before the computer program / instruction is executed by the processor 610 when it is running, and / or after the computer program / instruction is executed by the processor 610 when it is running, the computer program / instruction is also used by the processor 610 to execute: for any fifth pixel point in the initial segmentation plane, the fifth pixel point is filtered based on the pixel values ​​of non-zero pixels in an area of ​​the target size around the fifth pixel point.

[0164] Exemplarily, after the computer program / instruction is executed by the processor 610 to perform the step of "determining a target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections", the computer program / instruction is also executed by the processor 610 to perform: determining a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane.

[0165] Exemplarily, the step of "determining a segmentation line of a two-dimensional ultrasound image of three-dimensional ultrasound volume data on any second section based on a target segmentation plane" executed by the computer program / instructions when the processor 610 is running includes: determining a segmentation template based on the target segmentation plane, the segmentation template being consistent with the number of voxel points in the three-dimensional ultrasound volume data, each voxel point in the segmentation template having a voxel value, and the voxel value being used to indicate whether a corresponding voxel point in the three-dimensional ultrasound volume data belongs to a target object; projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section, and obtaining a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0166] Exemplarily, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. The computer program / instructions used by the processor 610 to execute the step of "projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section" include: projecting the segmentation template into the two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; determining the pixel points whose first pixel value in each column of the segmentation section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; uniformly sampling the second pixel point set to obtain at least two discrete pixel points; interpolating the at least two discrete pixel points to obtain a target segmentation line, which is the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0167] Exemplarily, after the computer program / instructions are used to execute the step of "determining the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane" when the processor 610 is running, the computer program / instructions are also used to execute the step of: displaying the two-dimensional ultrasound image and segmentation line of the three-dimensional volume data on the second section on the display interface.

[0168] According to another aspect of the present invention, a computer readable storage medium is also provided, on which a computer program / instruction is stored, and the computer program / instruction is used to execute the above-mentioned ultrasound imaging method when it is run. The computer readable storage medium may include, for example, a storage component of a tablet computer, a hard disk of a personal computer, an erasable programmable read-only memory (EPROM), a portable read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer readable storage medium may be any combination of one or more computer readable storage media.

[0169] In one embodiment, the computer program / instructions are used to execute the following when running: acquiring three-dimensional ultrasound volume data containing a target object; determining, for each first section among a plurality of first sections extracted along a first direction from the three-dimensional ultrasound volume data, first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; determining a target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the target segmentation plane being used to segment an object region where the target object is located in the three-dimensional ultrasound volume data and other regions except the object region.

[0170] Exemplarily, the step of "for each first section among multiple first sections extracted along the first direction from three-dimensional ultrasound volume data, determining first position information of a first edge of a low-echo region in the first section and second position information of a second edge of a high-echo region in the first section in the second direction" executed by the computer program / instructions when running includes: for each first section among the multiple first sections, extracting an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate the position of the low-echo region in the corresponding first section, and the initial high-echo image is used to indicate the position of the high-echo region in the corresponding first section; determining first position information of the first edge of the low-echo region in the second direction based at least on the corresponding initial low-echo image; and determining second position information of the second edge of the high-echo region in the second direction based at least on the corresponding initial high-echo image.

[0171] Exemplarily, the step of "extracting an initial low-echo image and an initial high-echo image corresponding to the first section" executed by the computer program / instruction when running includes: obtaining a low-echo template image and a high-echo template image, wherein the image size of the low-echo template image and the high-echo template image is the same as the image size of each first section in multiple first sections; comparing the pixel value of each first pixel in the first section with a preset threshold; if the pixel value of the first pixel is less than or equal to the preset threshold, setting the pixel value of the second pixel in the low-echo template image to the first pixel value, wherein the position of the second pixel in the low-echo template image is consistent with the position of the first pixel in the first section; setting the pixel value of the first remaining pixel in the low-echo template image to the second pixel value to obtain the initial low-echo image corresponding to the first section, wherein the first remaining pixel is a pixel other than the pixel set to the first pixel value, and the first pixel value Used to indicate that the corresponding pixel point in the first section belongs to the low echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low echo area; if the pixel value of the first pixel point is greater than the preset threshold, the pixel value of the third pixel point in the high echo template image is set to the third pixel value, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; the pixel value of the second remaining pixel points in the high echo template image is set to the fourth pixel value to obtain an initial high echo image corresponding to the first section, wherein the second remaining pixel points are pixel points other than the pixel points set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the high echo area, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the high echo area; wherein the first pixel point is a pixel point in the effective detection area, and the effective detection area is an area containing the target observation part of the target object.

[0172] Exemplarily, the pixel value of each pixel in the initial low-echo image includes a first pixel value and a second pixel value, the first pixel value is used to indicate that the corresponding pixel in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel in the first section does not belong to the low-echo area; the step of "determining the first position information of the first edge of the low-echo area in the second direction at least based on the corresponding initial low-echo image" executed by the computer program / instruction when running includes: setting the pixel values ​​in the initial low-echo image in the following manner to obtain the corresponding final low-echo image: determining the connected domain in the low-echo area based on the initial low-echo image; for each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is less than the first area threshold, the image of the pixel in the initial low-echo image is set. The pixel value is set to the second pixel value; for each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point meets the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the first pixel value; for each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point does not meet the first target requirement, the pixel value of the pixel point in the initial low-echo image is set to the second pixel value; the final low-echo image is traversed along the second direction, and during the traversal process, the position information corresponding to the first pixel point in the second direction obtained from top to bottom in each column along the second direction whose pixel value is the first pixel value is recorded, so as to obtain the first position information of the first edge of the low-echo area in the second direction.

[0173] Exemplarily, the first target requirement includes: the pixel point meets any of the first target conditions, the first target conditions including: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; wherein the first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

[0174] Exemplarily, at least part of the connected domains are a preset number of connected domains with the largest area in the high-echo region, or connected domains in the high-echo region whose area exceeds a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

[0175] Exemplarily, the pixel value of each pixel in the initial high-echoic image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel in the first section belongs to the high-echoic area, and the fourth pixel value is used to indicate that the corresponding pixel in the first section does not belong to the high-echoic area; the step of "determining the second position information of the second edge of the high-echoic area in the second direction at least based on the corresponding initial high-echoic image" executed by the computer program / instruction when running includes: setting the pixel values ​​in the initial high-echoic image in the following manner to obtain the corresponding final high-echoic image: determining the connected domain contained in the high-echoic area based on the initial high-echoic image; for each pixel in the initial high-echoic image, if the area of ​​the connected domain where the pixel is located is less than the third area threshold, setting the pixel value of the pixel in the initial high-echoic image to the fourth pixel value ; For each pixel in the initial high echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the third area threshold and the pixel meets the second target requirement, the pixel value of the pixel in the initial high echo image is set to the third pixel value; For each pixel in the initial high echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the third area threshold and the pixel does not meet the second target requirement, the pixel value of the pixel in the initial high echo image is set to the fourth pixel value; Taking each edge point in the first edge of the low echo area in the second direction as the starting point, traverse the final high echo image along the second direction, and during the traversal process, record the position information in the second direction corresponding to the pixel point whose first pixel value is the third pixel value obtained from top to bottom in each column along the second direction, so as to obtain the second position information of the second edge of the high echo area in the second direction.

[0176] Exemplarily, the second target requirement includes: the pixel point meets any of the second target conditions, the second target conditions include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; wherein the second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction in the second direction.

[0177] Exemplarily, the step of "determining the target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections" executed by the computer program / instructions at runtime includes: determining an initial segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, the initial segmentation plane containing segmentation lines corresponding one-to-one to the multiple first sections, and the segmentation line corresponding to each first section is located between the edge corresponding to the first position information and the edge corresponding to the second position information; wherein the initial segmentation plane is the target segmentation plane, or, determining the target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, further includes: optimizing the initial segmentation plane to determine the target segmentation plane.

[0178] Exemplarily, the step of "optimizing the initial segmentation plane and determining the target segmentation plane" performed by the computer program / instructions during operation includes: interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane.

[0179] Exemplarily, before the step of "interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain a target segmentation plane" executed by the computer program / instruction at runtime, the step of "optimizing the initial segmentation plane to determine the target segmentation plane" executed by the computer program / instruction at runtime may also include: for each fourth pixel point in the initial segmentation plane, calculating the mean of the pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and the standard deviation of the pixel values ​​of each pixel point in the first pixel point set; when the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, setting the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation; or, when the pixel value of the fourth pixel point is greater than the sum of the mean and the standard deviation, setting the pixel value of the fourth pixel point to the sum of the mean and the standard deviation; wherein the first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located.

[0180] Exemplarily, before the step of "interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain a target segmentation plane" executed by the computer program / instruction at runtime, and / or after the step of "interpolating pixel points with zero pixel values ​​in the initial segmentation plane to obtain a target segmentation plane" executed by the computer program / instruction at runtime, the computer program / instruction at runtime is also used to execute: for any fifth pixel point in the initial segmentation plane, filtering the fifth pixel point based on the pixel values ​​of non-zero pixels in an area of ​​the target size around the fifth pixel point.

[0181] Exemplarily, after the step of "determining a target segmentation plane based on first position information and second position information corresponding to each of multiple first sections" is executed by the computer program / instruction at runtime, the computer program / instruction at runtime is also used to execute: determining a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane.

[0182] Exemplarily, the step of "determining a segmentation line of a two-dimensional ultrasound image of three-dimensional ultrasound volume data on any second section based on a target segmentation plane" executed by a computer program / instruction when running includes: determining a segmentation template based on the target segmentation plane, the segmentation template being consistent with the number of voxel points in the three-dimensional ultrasound volume data, each voxel point in the segmentation template having a voxel value, and the voxel value being used to indicate whether a corresponding voxel point in the three-dimensional ultrasound volume data belongs to a target object; projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section, and obtaining a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0183] Exemplarily, when the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object, and when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. The computer program / instructions used to execute the step of "projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section" during operation include: projecting the segmentation template into the two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; determining the pixel points whose first pixel value in each column of the segmentation section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; uniformly sampling the second pixel point set to obtain at least two discrete pixel points; interpolating the at least two discrete pixel points to obtain a target segmentation line, which is the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

[0184] Exemplarily, after the step of "determining the segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second section based on the target segmentation plane" executed by the computer program / instructions at runtime, the computer program / instructions at runtime are also used to execute: displaying the two-dimensional ultrasound image and segmentation line of the three-dimensional volume data on the second section on a display interface.

[0185] A person skilled in the art may understand the specific implementation scheme of the ultrasonic imaging device, electronic device and computer-readable storage medium by reading the above description of the ultrasonic imaging method, which will not be described in detail here for the sake of brevity.

[0186] It should be noted that the present invention is not limited to the implementation method of the corresponding orientation in the embodiment. Specifically, the present invention relates to orientation words such as "up", "down", "left", and "right". These orientations can be based on the display orientation of the ultrasound image displayed on the display screen of the device for performing the ultrasound imaging method (such as an ultrasound device). For example, Figure 3 , Figure 4 Or the orientation of the approximate figure. In this orientation, the fetus is basically lying flat, with its head on the left and its feet on the right. If the display orientation of the ultrasound image changes, the orientation in the scheme can also be adjusted as needed. It is understandable that various adaptive adjustments should not be considered beyond the scope of the present invention.

[0187] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as required by the appended claims.

[0188] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0189] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0190] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0191] Similarly, it should be understood that in order to streamline the present invention and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be interpreted as reflecting the following intention: the claimed invention requires more features than the features explicitly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0192] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0193] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0194] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules in an ultrasonic imaging device according to an embodiment of the present invention. The present invention may also be implemented as a device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0195] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0196] The above is only a specific embodiment of the present invention or an explanation of a specific embodiment. The protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An ultrasonic imaging method, comprising: Acquire three-dimensional ultrasound volume data containing a target object; For each first section among a plurality of first sections extracted from the three-dimensional ultrasound volume data along a first direction, determine first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; Based on the first position information and the second position information respectively corresponding to the plurality of first sections, a target segmentation plane is determined, wherein the target segmentation plane is used to segment an object region where the target object is located and other regions except the object region in the three-dimensional ultrasound volume data.

2. The method of claim 1, wherein: The step of determining, for each of a plurality of first sections extracted along a first direction from the three-dimensional ultrasound volume data, first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction comprises: For each first section of the plurality of first sections, Extracting an initial low-echo image and an initial high-echo image corresponding to the first section, wherein the initial low-echo image is used to indicate the position of the low-echo region in the corresponding first section, and the initial high-echo image is used to indicate the position of the high-echo region in the corresponding first section; determining first position information of a first edge of the hypoechoic region in the second direction based at least on the corresponding initial hypoechoic image; Based at least on the corresponding initial high-echoic image, second position information of a second edge of the high-echoic region in the second direction is determined.

3. The method of claim 2, wherein: The extracting the initial low-echo image and the initial high-echo image corresponding to the first section includes: Acquire a low-echo template image and a high-echo template image, wherein the image size of the low-echo template image and the high-echo template image is the same as the image size of each first section in the plurality of first sections; Comparing the pixel value of each first pixel point in the first section with a preset threshold; If the pixel value of the first pixel point is less than or equal to the preset threshold, the pixel value of the second pixel point in the low-echo template image is set to the first pixel value, wherein the position of the second pixel point in the low-echo template image is consistent with the position of the first pixel point in the first section; Setting the pixel value of the first remaining pixel point in the low-echo template image to the second pixel value to obtain an initial low-echo image corresponding to the first section, wherein the first remaining pixel point is a pixel point other than the pixel point set to the first pixel value, the first pixel value is used to indicate that the corresponding pixel point in the first section belongs to the low-echo area, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the low-echo area; If the pixel value of the first pixel point is greater than the preset threshold, the pixel value of the third pixel point in the high echo template image is set to a third pixel value, wherein the position of the third pixel point in the high echo template image is consistent with the position of the first pixel point in the first section; Setting the pixel value of the second remaining pixel point in the hyperechoic template image to the fourth pixel value to obtain an initial hyperechoic image corresponding to the first section, wherein the second remaining pixel point is a pixel point other than the pixel point set to the third pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the hyperechoic region, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the hyperechoic region; The first pixel point is a pixel point in an effective detection area, and the effective detection area is an area including a target observation part in the target object.

4. The method according to claim 2 or 3, wherein: The pixel value of each pixel point in the initial hypoechoic image includes a first pixel value and a second pixel value, wherein the first pixel value is used to indicate that the corresponding pixel point in the first section belongs to the hypoechoic region, and the second pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the hypoechoic region; The determining, at least based on the corresponding initial hypoechoic image, first position information of a first edge of the hypoechoic region in the second direction comprises: The pixel values ​​in the initial low-echo image are set in the following manner to obtain the corresponding final low-echo image: Based on the initial hypoechoic image, determining a connected domain in the hypoechoic region; For each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is less than the first area threshold, setting the pixel value of the pixel point in the initial low-echo image to the second pixel value; For each pixel point in the initial low-echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the first area threshold and the pixel point meets the first target requirement, setting the pixel value of the pixel point in the initial low-echo image to the first pixel value; For each pixel in the initial low-echo image, if the area of ​​the connected domain where the pixel is located is greater than or equal to the first area threshold and the pixel does not meet the first target requirement, the pixel value of the pixel in the initial low-echo image is set to the second pixel value; the final low-echo image is traversed along the second direction, and during the traversal process, the corresponding position information in the second direction of the pixel point whose first pixel value is the first pixel value in each column obtained from top to bottom along the second direction is recorded to obtain the first position information of the first edge of the low-echo area in the second direction.

5. The method of claim 4, wherein: The first target requirement includes: the pixel point meets any one of the first target conditions, and the first target condition includes: the position of the centroid of the connected domain where the pixel point is located in the second direction is higher than the first target position, and / or the position of the pixel point in the second direction is higher than the first target position; The first target position is the average of the positions of the centroids of at least part of the connected domains in the high echo area in the second direction.

6. The method of claim 5, wherein: The at least partially connected domains are a preset number of connected domains with the largest areas in the high-echo region, or connected domains in the high-echo region whose areas exceed a second area threshold, or connected domains in the high-echo region whose area accounts for a proportion of the total area of ​​the initial high-echo image that is greater than a preset proportion threshold.

7. The method according to claim 2 or 3, wherein: The pixel value of each pixel point in the initial hyperechoic image includes a third pixel value and a fourth pixel value, the third pixel value is used to indicate that the corresponding pixel point in the first section belongs to the hyperechoic region, and the fourth pixel value is used to indicate that the corresponding pixel point in the first section does not belong to the hyperechoic region; The determining, at least based on the corresponding initial high echo image, second position information of a second edge of the high echo area in the second direction comprises: The pixel values ​​in the initial hyperechoic image are set in the following manner to obtain the corresponding final hyperechoic image: Based on the initial high-echo image, determining a connected domain contained in the high-echo region; For each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is less than a third area threshold, setting the pixel value of the pixel point in the initial high echo image to the fourth pixel value; For each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point meets the second target requirement, the pixel value of the pixel point in the initial high echo image is set to the third pixel value; For each pixel point in the initial high echo image, if the area of ​​the connected domain where the pixel point is located is greater than or equal to the third area threshold and the pixel point does not meet the second target requirement, setting the pixel value of the pixel point in the initial high echo image to the fourth pixel value; Taking each edge point in the first edge of the low echo area in the second direction as the starting point, the final high echo image is traversed along the second direction. During the traversal process, the position information corresponding to the pixel point whose first pixel value obtained from top to bottom along the second direction in each column is the third pixel value in the second direction is recorded to obtain the second position information of the second edge of the high echo area in the second direction.

8. The method of claim 7, wherein: The second target requirement includes: the pixel point meets any one of the second target conditions, and the second target conditions include: the position of the centroid of the connected domain where the pixel point is located in the second direction is lower than the second target position, and / or the position of the pixel point in the second direction is lower than the second target position; The second target position is the average of the positions of the centroids of at least part of the connected domains in the low echo area in the second direction, or the average of the positions of the edge points in the first edge of the low echo area in the second direction.

9. The method according to any one of claims 1 to 3, wherein: The determining of the target segmentation plane based on the first position information and the second position information respectively corresponding to the plurality of first sections includes: Based on the first position information and the second position information corresponding to each of the plurality of first cut planes, an initial segmentation plane is determined, wherein the initial segmentation plane includes segmentation lines corresponding to the plurality of first cut planes one by one, and the segmentation line corresponding to each first cut plane is located between an edge corresponding to the first position information and an edge corresponding to the second position information; The initial segmentation plane is the target segmentation plane, or the target segmentation plane is determined based on the first position information and the second position information corresponding to each of the multiple first sections, and further includes: optimizing the initial segmentation plane to determine the target segmentation plane.

10. The method of claim 9, wherein: The step of optimizing the initial segmentation plane to determine the target segmentation plane includes: Interpolate the pixel points with zero pixel values ​​in the initial segmentation surface to obtain the target segmentation surface.

11. The method of claim 10, wherein: Before interpolating the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, optimizing the initial segmentation plane to determine the target segmentation plane further includes: For each fourth pixel point in the initial segmentation surface, Calculating a mean value of pixel values ​​of each pixel point in the first pixel point set where the fourth pixel point is located and a standard deviation of the pixel values ​​of each pixel point in the first pixel point set; When the pixel value of the fourth pixel point is less than the absolute value of the difference between the mean and the standard deviation, setting the pixel value of the fourth pixel point to the absolute value of the difference between the mean and the standard deviation; or, When the pixel value of the fourth pixel point is greater than the sum of the mean value and the standard deviation, setting the pixel value of the fourth pixel point to the sum of the mean value and the standard deviation; The first pixel point set where the fourth pixel point is located is a set consisting of all non-zero pixel points in the row where the fourth pixel point is located or a set consisting of all non-zero pixel points in the column where the fourth pixel point is located.

12. The method of claim 10, wherein: Before interpolating the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, and / or after interpolating the pixel points with zero pixel values ​​in the initial segmentation plane to obtain the target segmentation plane, the method further includes: For any fifth pixel point in the initial segmentation surface, the fifth pixel point is filtered based on the pixel values ​​of non-zero pixels in an area of ​​a target size around the fifth pixel point.

13. The method according to any one of claims 1 to 3, wherein: After determining the target segmentation plane based on the first position information and the second position information corresponding to each of the plurality of first sections, the method further includes: A segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second slice is determined based on the target segmentation plane.

14. The method of claim 13, wherein: The step of determining a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second slice based on the target segmentation plane comprises: Based on the target segmentation surface, determining a segmentation template, wherein the number of the segmentation template is consistent with the number of voxel points in the three-dimensional ultrasound volume data, and each voxel point in the segmentation template has a voxel value, and the voxel value is used to indicate whether a corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object; The segmentation template is projected into a two-dimensional coordinate system corresponding to the second section plane to obtain a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section plane.

15. The method of claim 14, wherein: When the voxel value is a first value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data belongs to the target object; when the voxel value is a second value, it indicates that the corresponding voxel point in the three-dimensional ultrasound volume data does not belong to the target object. The step of projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation line of a two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section includes: Projecting the segmentation template into a two-dimensional coordinate system corresponding to the second section to obtain a segmentation section; Determine the pixel points whose first pixel value in each column of the segmented section is equal to the first value from top to bottom along the second direction to obtain a second pixel point set; Uniformly sampling the second pixel point set to obtain at least two discrete pixel points; The at least two discrete pixel points are interpolated to obtain a target segmentation line, where the target segmentation line is a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on the second section.

16. The method of claim 13, wherein: After determining a segmentation line of the two-dimensional ultrasound image of the three-dimensional ultrasound volume data on any second slice based on the target segmentation plane, the method further includes: The two-dimensional ultrasound image of the three-dimensional volume data on the second section and the segmentation line are displayed on a display interface.

17. An ultrasonic imaging device, comprising: An acquisition module, used for acquiring three-dimensional ultrasonic volume data containing a target object; A first determination module is configured to determine, for each first section among a plurality of first sections extracted and obtained from the three-dimensional ultrasound volume data along a first direction, first position information of a first edge of a low-echo region in the first section in a second direction and second position information of a second edge of a high-echo region in the first section in the second direction, wherein the second direction is perpendicular to the first direction, and the second edge is an edge of a side of the high-echo region close to the low-echo region in the second direction; The second determination module is used to determine a target segmentation plane based on the first position information and the second position information corresponding to each of the multiple first sections, and the target segmentation plane is used to segment the object area where the target object is located and other areas except the object area in the three-dimensional ultrasound volume data.

18. An electronic device, comprising a processor and a memory, wherein a computer program / instruction is stored in the memory, and the processor executes the computer program / instruction to implement the ultrasonic imaging method according to any one of claims 1 to 16.

19. A computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the ultrasonic imaging method according to any one of claims 1 to 16.

Images