Three-dimensional ultrasonic body data processing method, device, equipment and medium

Abstract

The invention discloses a three-dimensional ultrasonic body data processing method and device, equipment and a medium, and relates to the field of ultrasonic images, and the method comprises the steps: determining a surface region of a shielded target in three-dimensional ultrasonic body data; performing three-dimensional curved surface fitting based on the coordinate points on the surface area to obtain a fitted curved surface; and cutting off ultrasonic body data located on the outer side of the fitting curved surface in the three-dimensional ultrasonic body data to obtain cut ultrasonic body data corresponding to the shielded target. It can be seen that the coordinate points on the surface area are fitted to obtain the fitting curved surface, and the ultrasonic body data, located on the outer side of the fitting curved surface, in the three-dimensional ultrasonic body data are cut off, so that sheltered tissues around the sheltered target can be stripped, and the correct sheltered target can be displayed.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic image technology, and in particular to a three-dimensional ultrasonic volume data processing method, device, equipment and medium. Background Art

[0002] At present, the interactive volume cropping method and the automated occlusion removal method are mainly used to remove the occluded parts in the three-dimensional ultrasound image. The interactive volume cropping method mainly refers to the inspector manually operating the cropping function of the ultrasound instrument to crop the occluded parts. The automated occlusion removal method refers to the method of using software algorithms to divide the three-dimensional ultrasound image into target areas and non-target areas, and finally only displaying the target area. The automated occlusion removal method is divided into traditional algorithms and AI (Artificial Intelligence) algorithms. The commonly used method in traditional algorithms is image edge detection, and the commonly used technologies in AI intelligent algorithms are target detection algorithms and semantic segmentation algorithms.

[0003] The manual cropping method relies too much on personal experience and is cumbersome and time-consuming. The image edge detection algorithm in the traditional algorithm has average effect on standard slice segmentation in some scenarios and is prone to misjudgment. The target detection, semantic segmentation and other algorithms in the AI ​​algorithm have very poor effect on non-standard slices in some scenarios and cannot be directly used for example to peel off the occluded tissue in front of the fetal face, and cannot correctly display the fetal face.

[0004] Therefore, an effective and automated method for removing obstructions and displaying them correctly is urgently needed. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a three-dimensional ultrasound volume data processing method, device, equipment and medium, which can automatically remove the blocking tissue and display the correct blocked target. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a three-dimensional ultrasound volume data processing method, comprising:

[0007] determining a surface area of ​​an occluded object in three-dimensional ultrasound volume data;

[0008] Perform three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface;

[0009] The ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off to obtain the cut ultrasonic volume data corresponding to the blocked object.

[0010] Optionally, determining a surface area of ​​an obscured target in the three-dimensional ultrasound volume data includes:

[0011] The semantic segmentation model is used to determine relative spatial information of multiple target objects in three-dimensional ultrasound volume data, and the surface area of ​​the occluded target is determined based on the relative spatial information; wherein the multiple target objects are used to splice to obtain the occluded target.

[0012] Optionally, performing three-dimensional surface fitting based on coordinate points on the surface area includes:

[0013] Extracting a plurality of slices in a preset direction from the three-dimensional ultrasound volume data;

[0014] Three-dimensional surface fitting is performed based on coordinate points at intersections between the plurality of cut surfaces and the surface area.

[0015] Optionally, performing three-dimensional surface fitting based on coordinate points at intersections between the plurality of cut surfaces and the surface area includes:

[0016] Part of the coordinate points are selected from all the coordinate points at the intersection position, and three-dimensional surface fitting is performed based on the part of the coordinate points.

[0017] Optionally, before the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off, the method further includes:

[0018] Determine a target area overlapping with a target projection area from the fitting curved surface; the target projection area is a projection area of ​​the surface area on the fitting curved surface;

[0019] The target area in the fitting surface is replaced by the surface area to obtain the updated fitting surface.

[0020] Optionally, the clipping of ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data includes:

[0021] Constructing a target cutting template based on the fitting surface;

[0022] The target cropping template is used to crop the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data.

[0023] Optionally, constructing a target clipping template based on the fitting surface includes:

[0024] Configuring a preset type parameter with a value of 1 for the coordinate points on the inner side of the fitting surface, and configuring a preset type parameter with a value of 0 for the coordinate points on the outer side of the fitting surface, so as to obtain a target clipping template;

[0025] Correspondingly, the using the target clipping template to clip the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data includes:

[0026] The three-dimensional ultrasound volume data is multiplied by the preset type parameter at the corresponding coordinate point of the target cropping template to obtain cropped ultrasound volume data.

[0027] Optionally, determining a surface area of ​​an obscured target in the three-dimensional ultrasound volume data includes:

[0028] compressing the three-dimensional ultrasonic volume data to obtain compressed ultrasonic volume data;

[0029] A surface area of ​​the occluded object in the compressed ultrasound volume data is determined.

[0030] Optionally, multiplying the three-dimensional ultrasound volume data by the preset type parameter at the coordinate point corresponding to the target cropping template includes:

[0031] Restoring the size of the target cropping template to be consistent with the size of the three-dimensional ultrasound volume data through interpolation operation to obtain an interpolated template;

[0032] The three-dimensional ultrasound volume data is multiplied by the preset type parameter at the corresponding coordinate point of the interpolated template.

[0033] Optionally, before performing three-dimensional surface fitting based on the coordinate points on the surface area, the method further includes:

[0034] determining a current location of the surface area;

[0035] Determining a target rotation parameter using a positional relationship between the current orientation and the target orientation;

[0036] The surface region is rotated from the current orientation to the target orientation based on the target rotation parameters.

[0037] Optionally, determining the current position of the surface area includes:

[0038] constructing a spatial coordinate system where the surface area is located, and determining a current orientation of the surface area;

[0039] The current orientation is determined based on the current orientation and a preset center point in the spatial coordinate system.

[0040] Optionally, constructing a spatial coordinate system where the surface area is located and determining a current orientation of the surface area includes:

[0041] Determine three direction vectors based on the target key information on the surface area; wherein the three direction vectors include a sagittal plane direction vector, a transverse plane direction vector and a coronal plane direction vector of the surface area;

[0042] A space coordinate system where the surface area is located is constructed according to the three direction vectors to obtain a current orientation of the surface area.

[0043] Optionally, the determining three direction vectors based on the target key information on the surface area includes:

[0044] Determine the normal vector of the surface area to obtain a sagittal plane direction vector;

[0045] Identifying target key points on the surface area, and determining a cross-sectional direction vector based on a line connecting the target key points;

[0046] A coronal plane direction vector is obtained based on the sagittal plane direction vector and the transverse plane direction vector.

[0047] Optionally, before determining the target rotation parameter by using the positional relationship between the current orientation and the target orientation, the method further includes:

[0048] Preconfigure three target directions corresponding to the three direction vectors respectively;

[0049] determining a target orientation of the surface area after the rotation is completed based on the three target directions;

[0050] The target orientation is determined based on the target orientation and the preset center point.

[0051] Optionally, determining the target rotation parameter by using the positional relationship between the current orientation and the target orientation includes:

[0052] Determine a first direction vector and a second direction vector from the three direction vectors;

[0053] Determine a first angle between the first direction vector and a target plane; the target plane is a plane determined based on a first target direction and a second target direction, the first target direction and the second target direction are the target directions corresponding to the first direction vector and the second direction vector respectively;

[0054] Determine a second angle between a projection direction of the first direction vector on the target plane and the first target direction;

[0055] Calculating a third angle between the second direction vector and the second target direction after the surface area is rotated based on the first angle and the second angle;

[0056] The first angle, the second angle, the third angle and the coordinates of a preset rotation center point are determined as the target rotation parameters.

[0057] Optionally, before the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off, the method further includes:

[0058] The three-dimensional ultrasound volume data is rotated accordingly based on the target rotation parameter.

[0059] In a second aspect, the present application discloses a three-dimensional ultrasound volume data processing device, comprising:

[0060] A surface area determination module, used to determine the surface area of ​​the occluded target in the three-dimensional ultrasound volume data;

[0061] A fitting module, used for performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface;

[0062] The cropping module is used to crop the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data to obtain cropped ultrasonic volume data corresponding to the blocked object.

[0063] In a third aspect, the present application discloses an electronic device, comprising:

[0064] Memory, used to store computer programs;

[0065] The processor is used to execute the computer program to implement the three-dimensional ultrasound volume data processing method disclosed above.

[0066] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the three-dimensional ultrasound volume data processing method disclosed above is implemented.

[0067] It can be seen that the present application provides a three-dimensional ultrasound volume data processing method, including: determining the surface area of ​​the occluded target in the three-dimensional ultrasound volume data; performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface; cutting off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain the cut ultrasound volume data corresponding to the occluded target. In summary, it can be seen that the present application first determines the surface area of ​​the occluded target in the three-dimensional ultrasound volume data, then performs three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface, and finally cuts off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data. In this way, the present application can automatically peel off the occluding tissue around the occluded target, reducing the time spent on peeling and improving the efficiency of peeling. Since the surface area can be a facial area, the present application can also realize the peeling of the occluding tissue in front of the facial area and display the peeled three-dimensional ultrasound volume data. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0069] Figure 1 A flow chart of a three-dimensional ultrasound volume data processing method disclosed in this application;

[0070] Figure 2 A schematic diagram of an identification surface area disclosed in the present application;

[0071] Figure 3 This is a flow chart of another three-dimensional ultrasound volume data processing method disclosed in this application;

[0072] Figure 4 This is a flow chart of another three-dimensional ultrasound volume data processing method disclosed in this application;

[0073] Figure 5 A schematic diagram of three-dimensional ultrasound volume data disclosed in the present application in a coordinate system;

[0074] Figure 6 A flow chart of another three-dimensional ultrasound volume data processing method disclosed in the present application;

[0075] Figure 7 A flow chart of another three-dimensional ultrasound volume data processing method disclosed in the present application;

[0076] Figure 8A flowchart of a three-dimensional surface fitting disclosed in this application;

[0077] Fig. 9 A schematic diagram of a target cutting template disclosed in this application;

[0078] Fig.10 This is a schematic diagram of the structure of a three-dimensional ultrasound volume data processing device disclosed in this application;

[0079] Fig.11 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] The manual cropping method relies too much on personal experience and is cumbersome and time-consuming. The image edge detection algorithm in the traditional algorithm has average effect on standard slice segmentation in some scenarios and is prone to misjudgment. The target detection, semantic segmentation and other algorithms in the AI ​​algorithm have very poor effect on non-standard slices in some scenarios and cannot be directly used for example to peel off the occluded tissue in front of the fetal face, and cannot correctly display the fetal face.

[0082] To this end, an embodiment of the present application proposes a three-dimensional ultrasound volume data processing solution, which can effectively and automatically remove obstructions around an obstructed target and display the obstructed target.

[0083] The present application discloses a method for processing three-dimensional ultrasound volume data. Figure 1 As shown, the method includes:

[0084] Step S11: determining the surface area of ​​the blocked object in the three-dimensional ultrasound volume data.

[0085] In this embodiment, the three-dimensional ultrasound volume data is three-dimensional data collected based on three-dimensional ultrasound imaging technology, such as fetal volume data, heart volume data, etc. Taking fetal volume data as an example, the occluded target can be the limbs, head or body of the fetus, etc., and the surface area can be the surface area of ​​the limbs, the facial area or the body surface area, etc.

[0086] In some embodiments, a semantic segmentation model is used to determine the relative spatial information of multiple target objects in the three-dimensional ultrasound volume data, and the surface area of ​​the occluded target is determined based on the relative spatial information; wherein the multiple target objects are used to splice to obtain the occluded target. The target object may be different areas or parts corresponding to the three-dimensional ultrasound volume data. Taking the face as an example, the target object may be the forehead, eyes, cheeks, nose, mouth, etc. The semantic segmentation model accurately splices the occluded target based on the relative spatial position information between the target objects, and then determines the surface area of ​​the occluded target. The surface area of ​​the occluded target can be accurately determined to achieve reliable cropping of the volume data. The semantic segmentation model may be a 3D (Three Dimensions) semantic segmentation network. In a specific embodiment, taking three-dimensional fetal ultrasound volume data as an example, the three-dimensional fetal ultrasound volume data is input into the 3D semantic segmentation network to obtain the corresponding label data, such as the facial area. The 3D semantic segmentation network will memorize the relative spatial information of each object during the reasoning process, so that the reasoning result is more accurate, and the facial area obtained by reasoning completely overlaps with the real fetal facial area. The reasoning result is as follows: Figure 2 It should be noted that the semantic segmentation model can also be any other pixel segmentation network.

[0087] Step S12: performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface.

[0088] In this embodiment, the coordinate points on the surface area are first determined, and then three-dimensional surface fitting is performed based on the coordinate points to obtain a fitting surface. Since the coordinate points on the surface area are also the coordinate points at the intersection between the section of the surface area and the surface area, the present embodiment first determines a number of sections parallel to the preset direction of the surface area, and then three-dimensional surface fitting is performed based on the coordinate points at the intersection between the several sections and the surface area, wherein the preset direction may include sagittal plane direction, coronal plane direction, cross-sectional direction, etc., and may also include other directions, such as the fetal head orientation, etc. The several sections are separated by a certain preset interval. In this embodiment, the number of sections can be changed by changing the size of the preset interval, thereby obtaining the several sections. Among them, several can be more than one. That is, the present embodiment determines at least one section parallel to the preset direction of the surface area.

[0089] In a specific implementation, in order to reduce the amount of calculation and the time spent on fitting, some coordinate points are selected from all the coordinate points at the intersection position, and three-dimensional surface fitting is performed based on the some coordinate points to obtain a fitting surface. In this way, less hardware resources are used while ensuring that the fitting accuracy is not much different, and the amount of calculation and the time spent on fitting are reduced.

[0090] Step S13: clipping the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain clipped ultrasound volume data corresponding to the blocked object.

[0091] It should be noted that the ultrasound volume data outside the fitting surface in the three-dimensional ultrasound volume data is also the occluding tissue of the occluded target, such as the umbilical cord in front of the fetal face. In this embodiment, after the ultrasound volume data outside the fitting surface in the three-dimensional ultrasound volume data is cut off, the fitting surface and the ultrasound volume data inside the fitting surface are obtained. For example, after the umbilical cord in front of the fetal face is cut off, the real face of the fetus is obtained, so that the real face of the fetus can be displayed.

[0092] In addition, the shape of the surface fitting is similar to a "bowl shape", so there is a certain space between the "bottom of the bowl" and the surface area, and there may be free impurities in this space. In order to remove this part of the impurities, this embodiment needs to remove the "bottom of the bowl", that is, remove the target area in the fitting surface that overlaps with the target projection area, and the target projection area is the projection area of ​​the surface area on the fitting surface. Further, the target area in the fitting surface is replaced with the real surface area to obtain the updated fitting surface, and then the ultrasound volume data located outside the updated fitting surface in the three-dimensional ultrasound volume data is cropped to obtain the cropped ultrasound volume data. Since there is no space between the updated fitting surface and the surface area, there is no free impurities between the updated fitting surface and the surface area.

[0093] It can be seen that the present application provides a three-dimensional ultrasound volume data processing method, including: determining the surface area of ​​the occluded target in the three-dimensional ultrasound volume data; performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface; cutting off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain the cut ultrasound volume data corresponding to the occluded target. In summary, it can be seen that the present application first determines the surface area of ​​the occluded target in the three-dimensional ultrasound volume data, then performs three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface, and finally cuts off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data. In this way, the present application can automatically peel off the occluding tissue around the occluded target, reducing the time spent on peeling and improving the efficiency of peeling. Since the surface area can be a facial area, the present application can also realize the peeling of the occluding tissue in front of the facial area and display the peeled three-dimensional ultrasound volume data.

[0094] The present application embodiment discloses a specific method for processing three-dimensional ultrasound volume data. Compared with the previous embodiment, this embodiment further explains and optimizes step S13. Figure 3 As shown, specifically including:

[0095] Step S131: constructing a target cutting template based on the fitting surface.

[0096] After obtaining the fitting surface, this embodiment constructs a target cropping template based on the fitting surface, so as to use the target cropping template to crop the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data.

[0097] In some embodiments, the construction process of the target cropping template includes: configuring a preset type parameter with a value of 1 for the coordinate points on the inner side of the fitting surface, and configuring the preset type parameter with a value of 0 for the coordinate points on the outer side of the fitting surface, so as to obtain the target cropping template.

[0098] In a first specific implementation, the preset type parameter is a pixel value, that is, a pixel value of 1 is configured for the coordinate point inside the fitting surface, and a pixel value of 0 is configured for the coordinate point outside the fitting surface, so as to obtain a target clipping template;

[0099] In a second specific implementation, the preset type parameter is a weight value, that is, a weight value of 1 is configured for the coordinate points on the inner side of the fitting surface, and a weight value of 0 is configured for the coordinate points on the outer side of the fitting surface to obtain the target clipping template.

[0100] Step S132: using the target cropping template, cropping the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data.

[0101] In this embodiment, the three-dimensional ultrasound volume data is multiplied by the preset type parameter at the corresponding coordinate point of the target cropping template to obtain the cropped ultrasound volume data.

[0102] For example, the three-dimensional ultrasound volume data is multiplied by the pixel value at the coordinate point corresponding to the target cropping template. Specifically, the part of the three-dimensional ultrasound volume data multiplied by the coordinate point with a pixel value of 1 on the target cropping template remains unchanged, and the part of the three-dimensional ultrasound volume data multiplied by the coordinate point with a pixel value of 0 on the target cropping template is cropped to obtain the cropped ultrasound volume data.

[0103] For another example, the three-dimensional ultrasound volume data is multiplied by the weight value at the corresponding coordinate point of the target cropping template. Specifically, the part of the three-dimensional ultrasound volume data multiplied by the coordinate point with a weight value of 1 on the target cropping template remains unchanged, and the part multiplied by the coordinate point with a weight value of 0 on the target cropping template is cropped to obtain the cropped ultrasound volume data.

[0104] In addition, in order to further reduce the time spent on fitting and improve the efficiency of cropping, the present embodiment can pre-compress the three-dimensional ultrasound volume data to obtain compressed ultrasound volume data, and determine the surface area of ​​the occluded target in the compressed ultrasound volume data. For the above compression processing, for example, the size of the three-dimensional ultrasound volume data is compressed from 100×100×100 to 50×50×50. In the process of compression processing, the size of the three-dimensional ultrasound volume data is reduced, and the amount of data is also reduced. That is, the present embodiment compresses the three-dimensional ultrasound volume data before reasoning, which can reduce the time spent on reasoning and the amount of calculation, thereby reducing the time spent on fitting and improving the efficiency of cropping.

[0105] In this way, the target cropping template is a template determined by the compressed fitting surface. Therefore, before multiplying the three-dimensional ultrasound volume data with the preset type parameters at the corresponding coordinate points of the target cropping template, this embodiment needs to restore the size of the target cropping template. Specifically, this embodiment restores the size of the target cropping template to be consistent with the size of the three-dimensional ultrasound volume data through interpolation operation to obtain an interpolated template, and multiplies the three-dimensional ultrasound volume data with the preset type parameters at the corresponding coordinate points of the interpolated template.

[0106] Furthermore, since interpolation may cause the target cropping template to be non-smooth, this embodiment smoothes the interpolated template to obtain a smoothed template, and then multiplies the three-dimensional ultrasound volume data by the preset type parameters at the corresponding coordinate points of the smoothed template.

[0107] In summary, when cropping ultrasound volume data, this embodiment may construct a target cropping template based on the fitting surface, and use the target cropping template to crop ultrasound volume data outside the fitting surface in the three-dimensional ultrasound volume data.

[0108] The embodiment of the present application discloses a specific method for processing three-dimensional ultrasound volume data. Compared with the previous embodiment, this embodiment further explains and optimizes the technical solution. Figure 4 As shown, specifically including:

[0109] Step S21: determining the surface area of ​​the blocked object in the three-dimensional ultrasound volume data.

[0110] Step S22: Determine the current position of the surface area.

[0111] It should be pointed out that since the directions of the identified surface areas are different, it is impossible to use a unified method to make a target cropping template. In order to further improve the cropping efficiency, all surface areas need to be rotated to a specific position. It is understandable that before the rotation, the current orientation and target orientation of the surface area must be clarified first, and then the target rotation parameters can be determined based on the positional relationship between the current orientation and the target orientation, and finally the surface area is rotated from the current orientation to the target orientation according to the target rotation parameters.

[0112] In this embodiment, the process of determining the current position of the surface area is described in detail. It can be understood that the current position of the surface area includes the current position information and the current direction information of the surface area. Next, this embodiment describes the process of determining the current position information and the current direction information of the surface area respectively.

[0113] First, determine the current position information of the surface area. First, convert the three-dimensional size information in the geometric space of the three-dimensional ultrasound volume data into the coordinate information of the three-dimensional ultrasound volume data, that is, coordinate the three-dimensional size information of the three-dimensional ultrasound volume data. Figure 5 As shown, the three-dimensional size information of the three-dimensional ultrasound volume data in the geometric space can be expressed as (D, H, W) = volume.size(), wherein D represents the depth direction, i.e., the Z-axis direction in the geometric space, H represents the height direction, i.e., the Y-axis direction in the geometric space, and W represents the width direction, i.e., the X-axis direction in the geometric space. This embodiment converts the three-dimensional ultrasound volume data in the geometric space into the three-dimensional ultrasound volume data in the form of a coordinate system, thereby obtaining the coordinate information of the three-dimensional ultrasound volume data, and also obtaining the coordinate information of the surface area.

[0114] Second, determine the current direction information of the surface area. In this embodiment, a spatial coordinate system where the surface area is located is constructed to obtain the current orientation of the surface area, and the current orientation of the surface area can be used to represent the current direction information of the surface area. Specifically, three direction vectors are determined based on the target key information on the surface area, and further, the spatial coordinate system where the surface area is located is constructed according to the three direction vectors to obtain the current orientation of the surface area.

[0115] The above-mentioned determination of three direction vectors based on the target key information on the surface area includes: determining the normal vector of the surface area to obtain the sagittal plane direction vector; identifying the target key points on the surface area, and determining the transverse direction vector based on the connecting line of the target key points; and obtaining the coronal plane direction vector based on the sagittal plane direction vector and the transverse direction vector. The target key points may be at least two, such as the coordinates of both eyes of the fetus, and the coronal plane direction vector is a vector that is perpendicular to the sagittal plane direction vector and the transverse direction vector.

[0116] After determining the coordinate information and the current orientation of the surface area, based on the coordinate information, the current orientation and Figure 5 The preset center point in the coordinate system determines the current position of the surface area. It should be noted that the preset center point can be any point on the surface area or any point outside the surface area. For example, the preset center point can be the midpoint of the two eyes of the facial contour or the origin (0,0,0).

[0117] Step S23: Determine the target rotation parameter using the positional relationship between the current orientation and the target orientation.

[0118] In this embodiment, the target orientation is the orientation of the surface area after rotation. In a specific implementation, the target orientation can be determined by pre-configuring three target directions corresponding to the three direction vectors, and then determining the target orientation of the surface area after rotation based on the three target directions, and determining the target orientation based on the target orientation and the preset center point, wherein the three target directions are Figure 5 The three coordinate axis directions of the coordinate system shown.

[0119] In a specific implementation, this embodiment corresponds the sagittal plane direction vector of the surface area to the X-axis of the coordinate system, corresponds the cross-sectional direction vector of the surface area to the Y-axis of the coordinate system, and corresponds the coronal plane direction vector of the surface area to the Z-axis of the coordinate system. Further, when the surface area is rotated to the point where the three direction vectors are respectively parallel to the three target directions corresponding to each other, the orientation of the surface area is the target orientation of the surface area, and the orientation determined based on the target orientation and the preset center point is the target orientation. That is, when the surface area is rotated to the point where the sagittal plane direction vector is parallel to the X-axis direction, the cross-sectional direction vector is parallel to the Y-axis direction, and the surface area is rotated to the point where the coronal plane direction vector is parallel to the Z-axis direction, the orientation of the surface area is the target orientation of the surface area, and the orientation determined based on the target orientation and the preset center point is the target orientation.

[0120] After determining the current orientation and the target orientation, the target rotation parameters are determined using the positional relationship between the current orientation and the target orientation. It can be understood that the target rotation parameters are the parameters required to rotate the surface area from the current orientation to the target orientation.

[0121] In a specific implementation, determining the target rotation parameter comprises the following steps:

[0122] (1) Determine a first direction vector and a second direction vector from the three direction vectors corresponding to the current orientation, and determine a first angle between the first direction vector and a target plane, wherein the target plane is a plane determined based on the first target direction and the second target direction, and the first target direction and the second target direction are the target directions corresponding to the first direction vector and the second direction vector, respectively. Exemplarily, the sagittal plane direction vector is determined as the first direction vector, and the transverse direction is determined as the second direction vector, and then the plane determined based on the sagittal plane direction vector and the transverse direction vector is set as the target plane, and finally, the first angle between the sagittal plane direction vector and the target plane is determined to be φ1.

[0123] (2) Determine a second angle between the projection direction of the first direction vector on the target plane and the first target direction. Exemplarily, when the sagittal plane direction vector corresponds to the X-axis of the coordinate system, the second angle between the sagittal plane direction vector and the X-axis is determined to be φ2.

[0124] (3) Calculating a third angle between the second direction vector and the second target direction after the surface area is rotated based on the first angle and the second angle. Exemplarily, when the cross-sectional direction vector corresponds to the Y axis of the coordinate system, the third angle between the cross-sectional direction vector and the Y axis is determined to be φ3.

[0125] Finally, the first angle φ1, the second angle φ2, the third angle φ3 and the coordinates of a preset rotation center point are determined as the target rotation parameters.

[0126] Step S24: Rotating the surface area from the current orientation to the target orientation based on the target rotation parameter.

[0127] It can be understood that, in the process of rotating the surface area from the current orientation to the target orientation based on the target rotation parameters, the surface area can be rotated in sequence according to the target sequence, the pre-rotation center point and the above three angles to obtain the rotated target.

[0128] In a specific embodiment, the surface area is the facial contour of the fetus. The midpoint of the two eyes can be used as the preset rotation center point, and φ1 can be used as the rotation angle for the first rotation around the axis; the midpoint of the two eyes can be used as the preset rotation center point, and φ2 can be used as the rotation angle for the second rotation around the axis; the midpoint of the two eyes can be used as the preset rotation center point, and φ3 can be used as the rotation angle for the third rotation around the axis. After three rotations, the facial contour of the rotated fetus is obtained.

[0129] Step S25: performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface.

[0130] Furthermore, in this embodiment, three-dimensional surface fitting is performed based on the coordinate points on the surface area after rotation to obtain a fitting surface.

[0131] Step S26: clipping the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain clipped ultrasound volume data corresponding to the blocked object.

[0132] It is understandable that, since the fitting surface is a fitting surface obtained by fitting the rotated surface area, the present embodiment needs to first rotate the three-dimensional ultrasound volume data accordingly based on the target rotation parameter, and then cut out the ultrasound volume data located outside the rotated fitting surface in the rotated three-dimensional ultrasound volume data to obtain the cut ultrasound volume data. In summary, the present embodiment rotates the identified surface areas with different directions to a specific direction in advance, so that a target cutting template can be made in a unified manner, thereby improving the overall cutting efficiency.

[0133] See also Figure 6 As shown, compared with the previous embodiment, this embodiment can also determine the current orientation based on a direction vector of the surface area, specifically including the following contents:

[0134] Step S31: determining a direction vector of the surface area as the current orientation of the surface area, and determining the current position of the surface area based on the current orientation and a preset center point in a coordinate system.

[0135] It should be noted that the coordinate system refers to Figure 5 The coordinate system in .

[0136] In a first specific implementation, a sagittal plane direction vector of the surface area is determined as the current orientation of the surface area, and further, the current orientation is determined based on the sagittal plane direction vector and a preset center point in the coordinate system.

[0137] In a second specific implementation, a cross-sectional direction vector of the surface area is determined as the current orientation of the surface area, and further, the current orientation is determined based on the cross-sectional direction vector and a preset center point in the coordinate system.

[0138] In a third specific implementation, the coronal plane direction vector of the surface area is determined as the current orientation of the surface area, and further, the current orientation is determined based on the coronal plane direction vector and a preset center point in a coordinate system.

[0139] In a fourth specific implementation, other section direction vectors of the surface area are determined as the current orientation of the surface area, and further, the current orientation is determined based on the other section direction vectors and a preset center point in the coordinate system.

[0140] Step S32: pre-configure a target direction, and determine the target direction as the target orientation of the surface area after the rotation is completed, and then determine the target orientation based on the target orientation and a preset center point in the coordinate system.

[0141] In this embodiment, the coordinate system refers to Figure 5 The coordinate system in .

[0142] In a first specific implementation, the X-axis direction of the coordinate system is preconfigured as the target direction, and the X-axis direction is determined as the target orientation of the surface area after the rotation is completed, and then the target orientation is determined based on the X-axis direction and the rotation center point.

[0143] In a second specific implementation, the Y-axis direction of the coordinate system is preconfigured as the target direction, and the Y-axis direction is determined as the target orientation of the surface area after the rotation is completed, and then the target orientation is determined based on the Y-axis direction and the preset center point.

[0144] In a third specific implementation, the Z-axis direction of the coordinate system is preconfigured as the target direction, and the Z-axis direction is determined as the target orientation of the surface area after the rotation is completed, and then the target orientation is determined based on the Z-axis direction and the preset center point.

[0145] In a fourth specific implementation, any other direction of the coordinate system is preconfigured as the target direction, and the other arbitrary direction is determined as the target orientation of the surface area after the rotation is completed, and then the target orientation is determined based on the other arbitrary direction and the preset center point.

[0146] Step S33: Determine a corresponding total rotation angle using the positional relationship between the current orientation and the target orientation, and determine the total rotation angle and the coordinates of a preset rotation center point as the target rotation parameters.

[0147] In this embodiment, the total rotation angle is the rotation angle required to rotate the surface area from the current orientation to the target orientation.

[0148] Assuming that the current orientation is an orientation determined based on the sagittal plane direction vector, and the target orientation is an orientation determined based on the X-axis direction, then the total rotation angle is the rotation angle required to rotate the surface area from the sagittal plane direction vector to the X-axis direction, and the target rotation parameter is a parameter determined based on the total rotation angle and the coordinates of the preset rotation center point.

[0149] Step S34: using the target rotation parameter to rotate each coordinate point on the surface area respectively, so as to rotate the surface area from the current orientation to the target orientation.

[0150] After determining the target rotation parameter, each coordinate point on the surface area can be rotated using the target rotation parameter to rotate the surface area from the current orientation to the target orientation. That is, in this embodiment, the surface area can be rotated from the current orientation to the target orientation by rotating the coordinate points.

[0151] Step S35: rotating the current orientation of the surface area using the target rotation parameter, so as to rotate the surface area as a whole from the current orientation to the target orientation.

[0152] After the target rotation parameter is determined, the surface area may be rotated as a whole using the target rotation parameter, so as to rotate the surface area as a whole from the current orientation to the target orientation.

[0153] In summary, it can be seen that when rotating the surface area, the present application can perform a plane rotation on the surface area, or a whole rotation on the surface area, or a coordinate point rotation on the surface area. That is to say, the present application provides a variety of automatic rotation methods of whole rotation, plane rotation and coordinate point rotation. Furthermore, in the actual rotation process, a suitable automatic rotation method can be selected according to actual needs to quickly rotate the surface area from the current orientation to the target orientation.

[0154] The following is a detailed description of the three-dimensional ultrasound volume data processing method of the present application through an embodiment:

[0155] See also Figure 7As shown, given a complete fetal body data, the corresponding label data is inferred using a 3D semantic segmentation network. The label data contains regional information such as the fetal facial contour. Using this regional information, the fetal facial contour is rotated to a specific direction, and a cropping template is made. Finally, the cropping template is applied to the fetal body data to obtain a three-dimensional fetal ultrasound image after occluded tissue is stripped and displayed correctly.

[0156] Specifically, the fetal facial contour is rotated to an upward position, see Figure 8 As shown, in the X-axis direction of the coordinate system, the fetal facial contour is cut to obtain the minimum coordinates of all non-zero pixel values ​​on the fetal facial contour, and further, the fetal facial contour is fitted with a three-dimensional surface based on the minimum coordinates. In the fitting process, some coordinate points can be selected from all the minimum coordinates for three-dimensional surface fitting, which ensures that the required hardware resources are small when the fitting accuracy is not much different, and at the same time, reduces the amount of calculation and the time spent on fitting.

[0157] After obtaining the fitted three-dimensional surface, the coordinate points inside the three-dimensional surface are assigned pixel values ​​of 0 (black), and the coordinate points outside the three-dimensional surface are assigned pixel values ​​of 1 (white). Figure 8 The target cropping template shown.

[0158] At the same time, there is a certain space between the target cropping template and the fetal facial contour, and there may be free impurities in this space. In order to remove this part of impurities, this embodiment removes the target area in the target cropping template that overlaps with the target projection area, and the target projection area is the projection area of ​​the fetal facial contour on the target cropping template. Further, the target area in the target cropping template is replaced with the real fetal facial contour to obtain the updated target cropping template. Fig. 9 shown.

[0159] After obtaining the target cropping template, the original three-dimensional fetal facial volume data is rotated accordingly to obtain the rotated volume data. At this time, the pixel values ​​at the corresponding positions of the rotated original fetal volume data and the target cropping template are multiplied to obtain the final result. In the above process, while removing the free tissue in front of the fetal face, the original features of other tissues of the fetal data are greatly retained, thereby improving the data integrity.

[0160] In summary, the present application can automatically peel off the obstructing tissue around the fetal face, which is more suitable for users. At the same time, the overall process of the present application can be controlled in about 2S, which reduces the peeling time and improves the peeling efficiency. In addition, since the present application automatically rotates the fetal facial contour based on the rotation parameters during the rotation process, the present application does not require the operator to manually rotate the fetal facial contour frequently based on prior knowledge, thereby reducing the labor cost and time cost during the rotation process and ensuring the reliability of the rotation.

[0161] Correspondingly, the present application also discloses a three-dimensional ultrasound volume data processing device, see Fig.10 As shown, the device comprises:

[0162] A surface area determination module 11, used to determine the surface area of ​​the obscured object in the three-dimensional ultrasound volume data;

[0163] A fitting module 12, configured to perform three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface;

[0164] The clipping module 13 is used to clip the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain clipped ultrasound volume data corresponding to the blocked object.

[0165] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0166] It can be seen that the present application provides a three-dimensional ultrasound volume data processing method, including: determining the surface area of ​​the occluded target in the three-dimensional ultrasound volume data; performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface; cutting off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data to obtain the cut ultrasound volume data corresponding to the occluded target. In summary, it can be seen that the present application first determines the surface area of ​​the occluded target in the three-dimensional ultrasound volume data, then performs three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface, and finally cuts off the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data. In this way, the present application can automatically peel off the occluding tissue around the occluded target, reducing the time spent on peeling and improving the efficiency of peeling. Since the surface area can be a facial area, the present application can also realize the peeling of the occluding tissue in front of the facial area and display the peeled three-dimensional ultrasound volume data.

[0167] Furthermore, an embodiment of the present application also provides an electronic device. Fig.11This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0168] Fig.11 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the three-dimensional ultrasound volume data processing method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0169] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0170] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc., and the resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to including a computer program that can be used to complete the three-dimensional ultrasound volume data processing method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0171] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the three-dimensional ultrasound volume data processing method disclosed above is implemented.

[0172] For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0173] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0174] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may 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 this application.

[0175] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0176] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0177] The above is a detailed introduction to a three-dimensional ultrasound volume data processing method, device, equipment, and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for a person skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A three-dimensional ultrasound volume data processing method, characterized in that: include: determining a surface area of ​​an occluded object in three-dimensional ultrasound volume data; Perform three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface; The ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off to obtain the cut ultrasonic volume data corresponding to the blocked object.

2. The three-dimensional ultrasound volume data processing method according to claim 1, characterized in that: The determining of the surface area of ​​the obscured object in the three-dimensional ultrasound volume data comprises: The semantic segmentation model is used to determine relative spatial information of multiple target objects in three-dimensional ultrasound volume data, and the surface area of ​​the occluded target is determined based on the relative spatial information; wherein the multiple target objects are used to splice to obtain the occluded target.

3. The three-dimensional ultrasound volume data processing method according to claim 1, characterized in that: The three-dimensional surface fitting based on the coordinate points on the surface area includes: Extracting a plurality of slices in a preset direction from the three-dimensional ultrasound volume data; Three-dimensional surface fitting is performed based on coordinate points at intersections between the plurality of cut surfaces and the surface area.

4. The three-dimensional ultrasound volume data processing method according to claim 3, characterized in that: The performing three-dimensional surface fitting based on the coordinate points at the intersection positions between the plurality of cut surfaces and the surface area comprises: Part of the coordinate points are selected from all the coordinate points at the intersection position, and three-dimensional surface fitting is performed based on the part of the coordinate points.

5. The three-dimensional ultrasound volume data processing method according to claim 1, characterized in that: Before the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off, the method further includes: Determine a target area overlapping with a target projection area from the fitting curved surface; the target projection area is a projection area of ​​the surface area on the fitting curved surface; The target area in the fitting surface is replaced by the surface area to obtain the updated fitting surface.

6. The three-dimensional ultrasound volume data processing method according to claim 1, characterized in that: The step of cutting out the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data comprises: Constructing a target cutting template based on the fitting surface; The target cropping template is used to crop the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data.

7. The three-dimensional ultrasound volume data processing method according to claim 6, characterized in that: The step of constructing a target clipping template based on the fitting surface includes: Configuring a preset type parameter with a value of 1 for the coordinate points on the inner side of the fitting surface, and configuring a preset type parameter with a value of 0 for the coordinate points on the outer side of the fitting surface, so as to obtain a target clipping template; Correspondingly, the using the target clipping template to clip the ultrasound volume data located outside the fitting surface in the three-dimensional ultrasound volume data includes: The three-dimensional ultrasound volume data is multiplied by the preset type parameter at the corresponding coordinate point of the target cropping template to obtain cropped ultrasound volume data.

8. The three-dimensional ultrasound volume data processing method according to claim 7, characterized in that: The determining of the surface area of ​​the obscured object in the three-dimensional ultrasound volume data comprises: compressing the three-dimensional ultrasonic volume data to obtain compressed ultrasonic volume data; A surface area of ​​the occluded object in the compressed ultrasound volume data is determined.

9. The three-dimensional ultrasonic volume data processing method according to claim 8, characterized in that: The step of multiplying the three-dimensional ultrasound volume data by the preset type parameter at the coordinate point corresponding to the target cropping template comprises: Restoring the size of the target cropping template to be consistent with the size of the three-dimensional ultrasound volume data through interpolation operation to obtain an interpolated template; The three-dimensional ultrasound volume data is multiplied by the preset type parameter at the corresponding coordinate point of the interpolated template.

10. The three-dimensional ultrasound volume data processing method according to any one of claims 1 to 9, characterized in that: Before performing three-dimensional surface fitting based on the coordinate points on the surface area, the method further includes: determining a current location of the surface area; Determining a target rotation parameter using a positional relationship between the current orientation and the target orientation; The surface region is rotated from the current orientation to the target orientation based on the target rotation parameters.

11. The three-dimensional ultrasound volume data processing method according to claim 10, characterized in that: Determining the current position of the surface area includes: constructing a spatial coordinate system where the surface area is located, and determining a current orientation of the surface area; The current orientation is determined based on the current orientation and a preset center point in the spatial coordinate system.

12. The three-dimensional ultrasound volume data processing method according to claim 11, characterized in that: The step of constructing a spatial coordinate system where the surface area is located and determining a current orientation of the surface area includes: Determine three direction vectors based on the target key information on the surface area; wherein the three direction vectors include a sagittal plane direction vector, a transverse plane direction vector and a coronal plane direction vector of the surface area; A space coordinate system where the surface area is located is constructed according to the three direction vectors to obtain a current orientation of the surface area.

13. The three-dimensional ultrasound volume data processing method according to claim 12, characterized in that: The determining of three direction vectors based on the target key information on the surface area includes: Determine the normal vector of the surface area to obtain a sagittal plane direction vector; Identifying target key points on the surface area, and determining a cross-sectional direction vector based on a line connecting the target key points; A coronal plane direction vector is obtained based on the sagittal plane direction vector and the transverse plane direction vector.

14. The three-dimensional ultrasound volume data processing method according to claim 12, characterized in that: Before determining the target rotation parameter by using the positional relationship between the current orientation and the target orientation, the method further includes: Preconfigure three target directions corresponding to the three direction vectors one by one; determining a target orientation of the surface area after the rotation is completed based on the three target directions; The target orientation is determined based on the target orientation and the preset center point.

15. The three-dimensional ultrasound volume data processing method according to claim 14, characterized in that: Determining the target rotation parameter by using the positional relationship between the current orientation and the target orientation includes: Determine a first direction vector and a second direction vector from the three direction vectors; Determine a first angle between the first direction vector and a target plane; the target plane is a plane determined based on a first target direction and a second target direction, the first target direction and the second target direction are the target directions corresponding to the first direction vector and the second direction vector respectively; Determine a second angle between a projection direction of the first direction vector on the target plane and the first target direction; Calculating a third angle between the second direction vector and the second target direction after the surface area is rotated based on the first angle and the second angle; The first angle, the second angle, the third angle and the coordinates of a preset rotation center point are determined as the target rotation parameters.

16. The three-dimensional ultrasound volume data processing method according to claim 15, characterized in that: Before the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data is cut off, the method further includes: The three-dimensional ultrasound volume data is rotated accordingly based on the target rotation parameter.

17. A three-dimensional ultrasonic volume data processing device, characterized in that: include: A surface area determination module, used to determine the surface area of ​​the occluded target in the three-dimensional ultrasound volume data; A fitting module, used for performing three-dimensional surface fitting based on the coordinate points on the surface area to obtain a fitting surface; The cropping module is used to crop the ultrasonic volume data located outside the fitting surface in the three-dimensional ultrasonic volume data to obtain cropped ultrasonic volume data corresponding to the blocked object.

18. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the three-dimensional ultrasound volume data processing method according to any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the three-dimensional ultrasound volume data processing method according to any one of claims 1 to 16 is implemented.

Images