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

Abstract

The invention discloses a three-dimensional ultrasonic body data pose adjustment method, device and equipment and a medium, which are applied to the technical field of ultrasound, and the method comprises the following steps: determining an initial point and an initial tangent plane from three-dimensional ultrasonic body data; determining a pose adjustment parameter based on the initial point, the initial tangent plane and the optimal visual angle information; the pose adjustment parameters comprise translation parameters and / or rotation parameters; the optimal view angle information comprises an ideal position to which the initial point is to be adjusted and a normal vector of a target tangent plane; the target tangent plane is a tangent plane to which the initial tangent plane is to be adjusted; and if the pose adjustment condition is met, adjusting the pose of the three-dimensional ultrasonic body data on the screen based on the pose adjustment parameter. Therefore, the pose of the three-dimensional ultrasonic body data can be automatically adjusted, a trackball does not need to be manually dragged for adjustment, the influence of subjective judgment is avoided, and the adjustment efficiency of the pose of the three-dimensional ultrasonic body data is improved.

Description

Technical Field

[0001] This application relates to the field of ultrasonic technology, and particularly relates to a method, device, equipment and medium for adjusting the pose of three-dimensional ultrasonic volume data. Background Art

[0002] The three-dimensional ultrasonic rendering diagram can vividly display the three-dimensional effect of human tissues. However, due to the variability of the relative position between the probe and human tissues, there is a certain deviation in the imaging perspective, manifested as the rendering diagram not being in the best orientation towards the screen direction. Currently, it is usually necessary to manually align it to adjust the three-dimensional ultrasonic volume data to the best pose, that is, to drag the trackball sequentially from the X-Y-Z three-axis directions in three-dimensional space to rotate the three-dimensional volume by a certain angle. In this way, it is highly dependent on subjective judgment, and the operation process also takes a certain amount of time. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method, device, equipment and medium for adjusting the pose of three-dimensional ultrasonic volume data, which can automatically adjust the pose of three-dimensional ultrasonic volume data, avoid the influence of subjective judgment, and improve the adjustment efficiency of the pose of three-dimensional ultrasonic volume data. The specific scheme is as follows:

[0004] In the first aspect, this application discloses a method for adjusting the pose of three-dimensional ultrasonic volume data, including:

[0005] Determining an initial point and an initial section plane from the three-dimensional ultrasonic volume data;

[0006] Determining pose adjustment parameters based on the initial point, the initial section plane and the best viewing angle information; the pose adjustment parameters include translation parameters and / or rotation parameters; the best viewing angle information includes the ideal position to which the initial point is to be adjusted and the normal vector of the target section plane; the target section plane is the section plane to which the initial section plane is to be adjusted;

[0007] If the pose adjustment condition is met, adjusting the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters.

[0008] Optionally, determining the initial point from the three-dimensional ultrasonic volume data includes:

[0009] Performing feature analysis on the three-dimensional ultrasonic volume data, and inferring the first reference key area where the first target part is located based on the volume data characteristics of the first target part;

[0010] Performing maximum connected domain processing on the first reference key area to obtain the first target key area uniquely corresponding to the first target part;

[0011] Calculating the centroid coordinates of the first target key area to obtain the initial point;

[0012] Optionally, determining an initial point from three-dimensional ultrasound volume data includes:

[0013] Performing feature analysis on the three-dimensional ultrasound volume data, inferring a second reference key region where the second target part is located based on the volume data features of the second target part, and inferring a third reference key region where the third target part is located based on the volume data features of the third target part;

[0014] Performing a maximum connected component process on the second reference key region to obtain a second target key region uniquely corresponding to the second target part, and calculating the centroid coordinates of the second target key region to obtain a first reference point;

[0015] Performing a maximum connected component process on the third reference key region to obtain a third target key region uniquely corresponding to the third target part, and calculating the centroid coordinates of the third target key region to obtain a second reference point;

[0016] Determining the initial point based on the first reference point and the second reference point.

[0017] Optionally, determining an initial section from three-dimensional ultrasound volume data includes:

[0018] Determining at least three key points from the three-dimensional ultrasound volume data;

[0019] Calculating a normal vector based on at least two of the at least three key points, and determining the initial section using the normal vector and the remaining key points.

[0020] Optionally, determining an initial section from three-dimensional ultrasound volume data includes:

[0021] Determining at least three key points from the three-dimensional ultrasound volume data;

[0022] Directly determining the initial section using the at least three key points.

[0023] Optionally, the determining an initial point and an initial section from three-dimensional ultrasound volume data includes:

[0024] Determining an initial point and two mutually perpendicular initial sections from the three-dimensional ultrasound volume data; wherein, the initial point passes through the straight line where the two initial sections intersect.

[0025] Optionally, the three-dimensional ultrasound volume data is three-dimensional fetal volume data, and the determining an initial point and an initial section from the three-dimensional ultrasound volume data includes:

[0026] Determining the centroid of the face as the initial point from the three-dimensional fetal volume data;

[0027] Determine the median sagittal plane of the fetal face and the horizontal transverse plane of the two eyeballs as the initial planes from the three-dimensional fetal body data.

[0028] Optionally, determining the horizontal transverse plane of the two eyeballs as the initial plane from the three-dimensional fetal body data includes:

[0029] Determine three key points corresponding to the horizontal transverse plane of the two eyeballs from the three-dimensional ultrasound body data; the three key points include the centroid of the left eye, the centroid of the right eye, and the centroid of the nose;

[0030] Taking the line connecting the centroid of the left eye and the centroid of the right eye as the axis, rotate the centroid of the nose clockwise around the axis by a preset angle to obtain the rotated point;

[0031] Determine the plane where the centroid of the left eye, the centroid of the right eye, and the rotated point are located as the horizontal transverse plane of the two eyeballs.

[0032] Optionally, when the pose adjustment parameters include translation parameters and rotation parameters, determining the pose adjustment parameters based on the initial point, the initial plane, and the optimal viewing angle information includes:

[0033] Calculate the translation parameters based on the initial point and the ideal position;

[0034] Calculate the rotation parameters based on the normal vectors of the initial plane and the target plane, and the points passed by the target plane.

[0035] Optionally, adjusting the pose of the three-dimensional ultrasound body data on the screen based on the pose adjustment parameters includes:

[0036] Taking the initial point as the rotation point, rotate the three-dimensional ultrasound body data according to the rotation parameters to obtain the rotated three-dimensional ultrasound body data; translate the rotated three-dimensional ultrasound body data according to the translation parameters.

[0037] Optionally, adjusting the pose of the three-dimensional ultrasound body data on the screen based on the pose adjustment parameters includes:

[0038] Translate the three-dimensional ultrasound body data according to the translation parameters to obtain the translated three-dimensional ultrasound body data; taking the translated initial point as the rotation point, rotate the translated three-dimensional ultrasound body data according to the rotation parameters.

[0039] In a second aspect, the present application discloses a three-dimensional ultrasound body data pose adjustment device, including:

[0040] A point-plane determination module for determining an initial point and an initial section from three-dimensional ultrasonic volume data; a parameter determination module for determining pose adjustment parameters based on the initial point, the initial section, and optimal viewing angle information; the pose adjustment parameters including translation parameters and / or rotation parameters; the optimal viewing angle information including an ideal position to which the initial point is to be adjusted and a normal vector of a target section; the target section being a section to which the initial section is to be adjusted;

[0041] A pose adjustment module for, if a pose adjustment condition is met, adjusting the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters.

[0042] In a third aspect, the present application discloses an ultrasonic device including a memory and a processor, wherein:

[0043] The memory is used for storing a computer program;

[0044] The processor is used for executing the computer program to implement the foregoing method for adjusting the pose of three-dimensional ultrasonic volume data.

[0045] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the foregoing method for adjusting the pose of three-dimensional ultrasonic volume data.

[0046] As can be seen from the above solutions, the present application provides a method for adjusting the pose of three-dimensional ultrasonic volume data, including: determining an initial point and an initial section from three-dimensional ultrasonic volume data; determining pose adjustment parameters based on the initial point, the initial section, and optimal viewing angle information; the pose adjustment parameters including translation parameters and / or rotation parameters; the optimal viewing angle information including an ideal position to which the initial point is to be adjusted and a normal vector of a target section; the target section being a section to which the initial section is to be adjusted; if a pose adjustment condition is met, adjusting the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters.

[0047] It can be seen that the beneficial effects of the present application are: determining pose adjustment parameters based on an initial point and an initial section in three-dimensional ultrasonic volume data and optimal viewing angle information corresponding to the initial point and the initial section, and then adjusting the pose of the three-dimensional ultrasonic volume data based on the pose adjustment parameters. In this way, the pose of the three-dimensional ultrasonic volume data can be automatically adjusted without manually dragging a trackball for adjustment, avoiding the influence of subjective judgment and improving the adjustment efficiency of the pose of the three-dimensional ultrasonic volume data.

[0048] Correspondingly, a device, an apparatus, and a readable storage medium for adjusting the pose of three-dimensional ultrasonic volume data provided by the present application also have the above technical effects. Description of the Drawings

[0049] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0050] Figure 1 Flowchart of a three-dimensional ultrasound volume data pose adjustment method provided by an embodiment of the present application;

[0051] Figure 2 Flowchart of a specific three-dimensional ultrasound volume data pose adjustment method provided by an embodiment of the present application;

[0052] Figure 3 Flowchart of a specific three-dimensional ultrasound volume data pose adjustment method provided by an embodiment of the present application;

[0053] Figure 4 Schematic diagram of the pose adjustment of a three-dimensional fetal volume data provided by an embodiment of the present application;

[0054] Figure 5 Schematic diagram of the structure of a three-dimensional ultrasound volume data pose adjustment device provided by an embodiment of the present application;

[0055] Figure 6 Structural diagram of an ultrasound device provided by an embodiment of the present application. Detailed implementation manners

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0057] See Figure 1 As shown, an embodiment of the present application discloses a three-dimensional ultrasound volume data pose adjustment method, including steps S11, S12, and S13:

[0058] Step S11: Determine the initial point and the initial section from the three-dimensional ultrasound volume data.

[0059] Among them, the three-dimensional ultrasound volume data can be the three-dimensional ultrasound volume data of the tissue to be measured such as the human body / animal body, etc., for example, the three-dimensional ultrasound volume data corresponding to the fetus, fetal face, uterus, ovary, liver, etc. Specifically, the ultrasound device emits ultrasonic waves to the detection area through the probe. The ultrasound device reconstructs the three-dimensional volume data based on the reflected ultrasound echo data to obtain the three-dimensional ultrasound volume data. The three-dimensional ultrasound volume data can be generated in real time or generated based on historical ultrasound echo data. In the embodiments of the present application, the initial points and initial sections corresponding to the three-dimensional ultrasound volume data of different tissues are different. The initial point can be a key point in the three-dimensional ultrasound volume data, and the initial section is a section that can contain as much information of the object to be measured as possible. For the convenience of adjusting the pose of the three-dimensional ultrasound volume data, the initial section can be a section with a positive orientation, such as a sagittal plane, a coronal plane, a transverse plane, etc.

[0060] Exemplarily, after obtaining the three-dimensional ultrasound volume data, the image corresponding to the three-dimensional ultrasound volume data can be displayed on the screen. In some cases, the display pose of the three-dimensional ultrasound volume data is not convenient for the user to observe, and it is necessary to adjust its display pose.

[0061] The embodiments of the present application can perform feature analysis on the three-dimensional ultrasound volume data, and infer the first reference key area where the first target part is located based on the volume data features of the first target part; perform the largest connected domain processing on the first reference key area to obtain the first target key area uniquely corresponding to the first target part; calculate the centroid coordinates of the first target key area to obtain the initial point. Among them, the first target part can be the face or a certain key part of the face. The key parts of the face can be the nose, mouth, center of the eyebrows, etc.

[0062] Alternatively, the embodiments of the present application can perform feature analysis on the three-dimensional ultrasound volume data, infer the second reference key area where the second target part is located based on the volume data features of the second target part, and infer the third reference key area where the third target part is located based on the volume data features of the third target part; perform the largest connected domain processing on the second reference key area to obtain the second target key area uniquely corresponding to the second target part, and calculate the centroid coordinates of the second target key area to obtain the first reference point; perform the largest connected domain processing on the third reference key area to obtain the third target key area uniquely corresponding to the third target part, and calculate the centroid coordinates of the third target key area to obtain the second reference point; determine the initial point based on the first reference point and the second reference point.

[0063] Among them, the second target part and the third target part can be different parts on the tissue to be measured. Taking the fetal face as an example, the second target part and the third target part can be the two eyes of the fetus respectively.

[0064] Furthermore, the midpoint of the line connecting the first reference point and the second reference point can be used as the initial point. It should be noted that when inferring the second reference key area or the third reference key area in the 3D ultrasound volume data, more than one key area may be obtained. Through the maximum connected component processing, multiple key areas with a relevance higher than the set condition are fused into one key area, and the uniquely corresponding key area can be determined.

[0065] In an alternative embodiment, the step of determining the initial section may include: determining at least three key points from the 3D ultrasound volume data; calculating a normal vector based on at least two of the at least three key points, and using the normal vector and the remaining key points to determine the initial section; it can be understood that if the key points required to determine the initial section are determined during the process of determining the initial point, they can be directly used to determine the initial section. If other auxiliary key points are required to determine the initial section, the determination method of the other auxiliary key points may be: performing feature analysis on the 3D ultrasound volume data, and inferring the fourth reference key area where the fourth target part is located based on the volume data features of the fourth target part; performing maximum connected component processing on the fourth reference key area to obtain the fourth target key area uniquely corresponding to the fourth target part; calculating the centroid coordinates of the fourth target key area to obtain this key point. Among them, the fourth target part may be the chin, mouth, etc.

[0066] At least three points on two intersecting straight lines in the 3D ultrasound volume data can be used as the three key points, or at least two points on the same straight line in the 3D ultrasound volume data and a point outside the straight line can be used as the three key points. These key points can characterize the position of the section, and then the initial section can be determined based on these three key points.

[0067] In an alternative embodiment, the step of determining the initial section may include: determining at least three key points from the 3D ultrasound volume data; directly using the at least three key points to determine the initial section. That is, the target section can be determined by using the three-point plane formula and the coordinates of the three key points.

[0068] In an alternative embodiment, the step of determining the initial section may include: using a section recognition model to recognize the initial section in the 3D ultrasound volume data. A plane can be parameterized as ax + by + cz + d = 0, and a model can be customized, and the model is trained with training data, and the plane parameters a, b, c are gradually adjusted until the model converges to obtain the section recognition model.

[0069] Further, embodiments of the present application can obtain optimal viewing angle information, which includes the ideal position to which the initial point is to be adjusted and the normal vector of the target section plane; the target section plane is the section plane to which the initial section plane is to be adjusted. Due to differences in user requirements and the shapes of tissues and organs, the optimal viewing angle information for different tissues may be different. Among them, the optimal viewing angle information can be determined according to the type of three-dimensional ultrasound volume data. That is, according to the characteristics of the three-dimensional ultrasound volume data, the corresponding initial point and initial section plane can be determined, and the corresponding optimal viewing angle information can be obtained. In addition, one or more initial points and one or more initial section planes can be determined according to actual requirements.

[0070] Step S12: Determine pose adjustment parameters based on the initial point, the initial section plane, and the optimal viewing angle information; the pose adjustment parameters include translation parameters and / or rotation parameters; the optimal viewing angle information includes the ideal position to which the initial point is to be adjusted and the normal vector of the target section plane; the target section plane is the section plane to which the initial section plane is to be adjusted.

[0071] In embodiments of the present application, when the initial point is in the ideal position and the direction of the initial section plane is not the ideal direction, only rotation is required without translation, and the pose adjustment parameter is the rotation parameter, and the translation parameter is zero at this time. When the initial point is not in the ideal position and the direction of the initial section plane is the ideal direction, only translation is required without rotation, and the pose adjustment parameter is the translation parameter, and the rotation parameter is zero at this time. When the initial point is not in the ideal position and the direction of the initial section plane is not the ideal direction, both translation and rotation are required, and the pose adjustment parameters include translation parameters and rotation parameters. Among them, the ideal direction is the direction of the target section plane. The normal vector of the initial section plane can be obtained, and the normal vector of the initial section plane and the normal vector of the target section plane can be used to determine whether the direction of the initial section plane is the ideal direction. Specifically, if the two normal vectors are parallel, it is determined that the direction of the initial section plane is the ideal direction.

[0072] Moreover, embodiments of the present application can calculate the translation parameter based on the initial point and the ideal position. Optionally, the translation matrix can be calculated using the coordinates of the initial point and the coordinates of the ideal position as the translation parameter.

[0073] Further, the rotation matrix can be calculated based on the normal vectors of the initial section plane and the target section plane and the points passed by the target section plane as the rotation parameter.

[0074] Step S13: If the pose adjustment condition is met, adjust the pose of the three-dimensional ultrasound volume data on the screen based on the pose adjustment parameters.

[0075] Exemplarily, the pose adjustment condition may be the condition that the pose adjustment parameters need to meet. Further, when at least one of the translation parameter and the rotation parameter is not zero, it is determined that the pose adjustment condition is met. Specifically, if the pose adjustment parameters are that both the translation parameter and the rotation parameter are zero, it indicates that the display pose of the current three-dimensional ultrasound volume data is the optimal pose, and there is no need to adjust the pose of the three-dimensional ultrasound volume data on the screen; if the pose adjustment parameters are that at least one of the translation parameter and the rotation parameter is not zero, it indicates that the display pose of the current three-dimensional ultrasound volume data is not the optimal pose, and the pose of the three-dimensional ultrasound volume data on the screen needs to be adjusted, then the pose of the three-dimensional ultrasound volume data on the screen is adjusted based on the pose adjustment parameters.

[0076] Exemplarily, when adjusting the pose of the three-dimensional ultrasound volume data on the screen based on the pose adjustment parameters, the three-dimensional ultrasound volume data can be translated and / or rotated.

[0077] In the embodiments of the present application, the three-dimensional ultrasound volume data can be rotated with the initial point as the rotation point according to the rotation parameter to obtain the rotated three-dimensional ultrasound volume data; and the rotated three-dimensional ultrasound volume data can be translated according to the translation parameter. Or, the three-dimensional ultrasound volume data can be translated according to the translation parameter to obtain the translated three-dimensional ultrasound volume data; and the translated three-dimensional ultrasound volume data can be rotated with the translated initial point as the rotation point according to the rotation parameter.

[0078] It can be seen that the embodiments of the present application determine the pose adjustment parameters based on the initial point and the initial section in the three-dimensional ultrasound volume data and the optimal viewing angle information corresponding to the initial point and the initial section, and then adjust the pose of the three-dimensional ultrasound volume data based on the pose adjustment parameters. In this way, the pose of the three-dimensional ultrasound volume data can be automatically adjusted without manually dragging the trackball for adjustment, avoiding the influence of subjective judgment and improving the adjustment efficiency of the pose of the three-dimensional ultrasound volume data.

[0079] Further, referring to Figure 2 as shown Figure 2 FIG. is a flowchart of a specific method for adjusting the pose of three-dimensional ultrasound volume data disclosed in the embodiments of the present application. The embodiments of the present application can determine an initial point and two initial sections that intersect perpendicularly from the three-dimensional ultrasound volume data; wherein, the initial point passes through the straight line where the two initial sections intersect. First, the optimal viewing angle of the three-dimensional ultrasound volume data in the clinical sense can be defined in combination with the application scenario; second, an initial point and two initial sections can be found by using the point positioning and section positioning algorithms of the three-dimensional ultrasound volume data; third, the rotation and translation matrix can be calculated from the initial point and the initial sections; finally, the pose of the three-dimensional ultrasound volume data on the screen can be adjusted according to the rotation and translation matrix.

[0080] Further, the three-dimensional ultrasound volume data is three-dimensional fetal volume data, referring toFigure 3 As shown in Figure 3 , an embodiment of the present application discloses a specific method for adjusting the pose of three-dimensional ultrasound volume data, including:

[0081] Step S21: Determine the facial centroid as the initial point from the three-dimensional fetal volume data.

[0082] Among them, the facial centroid can be the centroid of the fetal facial area, also known as the craniofacial centroid.

[0083] The embodiment of the present application can perform feature analysis on the three-dimensional ultrasound volume data, and infer the first reference key area where the first target part is located based on the volume data features of the first target part; perform the largest connected domain processing on the first reference key area to obtain the first target key area uniquely corresponding to the first target part; calculate the centroid coordinates of the first target key area to obtain the initial point.

[0084] Among them, performing feature analysis on the three-dimensional ultrasound volume data can be to determine the contour, texture features and other feature information of each closed area in the three-dimensional ultrasound volume data, and perform a matching check on the feature information of these closed areas with the feature information of the parts of the set type. If it is determined based on the matching check result that a certain closed area matches the feature information of a certain target type of part (the first target part), it is determined that the closed area is the first reference key area corresponding to the first target part.

[0085] Optionally, perform feature analysis on the three-dimensional ultrasound volume data, infer the second reference key area where the left eye is located based on the volume data features of the left eye, and infer the third reference key area where the right eye is located based on the volume data features of the right eye; perform the largest connected domain processing on the second reference key area to obtain the second target key area uniquely corresponding to the left eye, and calculate the centroid coordinates of the second target key area to obtain the left eye centroid; perform the largest connected domain processing on the third reference key area to obtain the third target key area uniquely corresponding to the right eye, and calculate the centroid coordinates of the third target key area to obtain the right eye centroid; take the midpoint of the line connecting the left eye centroid and the right eye centroid as the initial point.

[0086] Step S22: Determine the median sagittal plane of the craniofacial region and the horizontal transverse plane of the two eyeballs as the initial planes from the three-dimensional fetal volume data.

[0087] The embodiment of the present application can determine three key points corresponding to the horizontal transverse plane of the two eyeballs from the three-dimensional ultrasound volume data; the three key points include the left eye centroid, the right eye centroid, and the nose centroid; with the line connecting the left eye centroid and the right eye centroid as the axis, rotate the nose centroid clockwise by a preset angle around the axis to obtain the rotated point; determine the plane where the left eye centroid, the right eye centroid, and the rotated point are located as the horizontal transverse plane of the two eyeballs.

[0088] Exemplarily, the purpose of rotating the nasal centroid is to make the rotated nasal centroid lie in the same plane as the left eye centroid and the right eye centroid. Therefore, the preset angle of rotation can be determined based on the positional relationship between the nasal centroid of the object to be measured and the left eye centroid and the right eye centroid. Optionally, the preset angle is 30 degrees.

[0089] Moreover, the binocular connection vector can be determined using the left eye centroid and the right eye centroid, and the median sagittal plane of the facial region can be determined using the binocular connection vector and the nasal centroid. Alternatively, the nasal centroid, the mouth centroid, and the chin centroid are determined, and the median sagittal plane of the facial region is determined using the nasal centroid, the mouth centroid, and the chin centroid.

[0090] In the embodiments of the present application, the ideal position to which the facial centroid is to be adjusted is the center position of the screen. The ideal direction of the median sagittal plane of the facial region is parallel to the XOZ plane, the normal vector of the median sagittal plane of the facial region is the Y-axis, the ideal direction of the horizontal transverse plane of the two eyeballs is parallel to the XOY plane, and the normal vector of the horizontal transverse plane of the two eyeballs is the Z-axis; wherein, the positive direction of the X-axis is perpendicular to the screen and points to the observer, the positive direction of the Y-axis is horizontally to the right, and the positive direction of the Z-axis is vertically upward. That is, in the three-dimensional coordinate system of the three-dimensional ultrasound volume data, the positive direction of the X-axis is perpendicular to the screen and points to the observer, the positive direction of the Y-axis is horizontally to the right, and the positive direction of the Z-axis is vertically upward.

[0091] Step S23: Calculate the translation matrix based on the facial centroid and the ideal position to which the facial centroid is to be adjusted.

[0092] In the embodiments of the present application, the ideal position of the facial centroid can be determined first, and then the translation matrix for translating the facial centroid to the ideal position of the facial centroid is determined. In the embodiments of the present application, when displaying the three-dimensional ultrasound volume data, the centroid of the three-dimensional ultrasound volume data is displayed at the center position of the screen, and the coordinates of the center position of the screen are (W / 2, H / 2, D / 2), where W, H, and D respectively represent the depth, height, and width of the three-dimensional ultrasound volume data.

[0093] Step S24: Calculate the rotation matrix based on the median sagittal plane of the facial region, the normal vector of the target plane corresponding to the median sagittal plane of the facial region, and the points passed through to obtain the first rotation matrix.

[0094] In the embodiments of the present application, the direction of the adjusted median sagittal plane of the facial region needs to be parallel to the XOZ plane, the normal vector is the Y-axis and passes through the center position of the screen, and the rotation matrix corresponding to the median sagittal plane of the facial region is calculated using the normal vector and the center position of the screen.

[0095] Step S25: Calculate a rotation matrix based on the horizontal cross-section of the binocular spheres, the normal vectors of the target cross-sections corresponding to the horizontal cross-sections of the binocular spheres, and the points passed through to obtain a second rotation matrix.

[0096] In the embodiment of the present application, the adjusted direction of the horizontal cross-section of the binocular spheres needs to be parallel to the XOY plane, the normal vector is the Z-axis and passes through the center position of the screen, and the rotation matrix corresponding to the horizontal cross-section of the binocular spheres is calculated using the normal vector and the center position of the screen.

[0097] Step S26: Adjust the pose of the three-dimensional ultrasound volume data on the screen based on the translation matrix, the first rotation matrix, and the second rotation matrix.

[0098] In the embodiment of the present application, the centroid of the face can be used as the rotation point, the first rotation is performed based on the first rotation matrix, then the centroid of the face is used as the rotation point, the second rotation is performed based on the second rotation matrix, and then the translation is performed based on the translation matrix.

[0099] Alternatively, the centroid of the face is used as the rotation point, the first rotation is performed based on the second rotation matrix, then the centroid of the face is used as the rotation point, the second rotation is performed based on the first rotation matrix, and then the translation is performed based on the translation matrix.

[0100] Alternatively, the translation is performed based on the translation matrix, then the centroid of the face after translation is used as the rotation point, the first rotation is performed based on the first rotation matrix, and then the centroid of the face after translation is used as the rotation point, the second rotation is performed based on the second rotation matrix.

[0101] Alternatively, the translation is performed based on the translation matrix, then the centroid of the face after translation is used as the rotation point, the first rotation is performed based on the second rotation matrix, and then the centroid of the face after translation is used as the rotation point, the second rotation is performed based on the first rotation matrix.

[0102] Further, as shown in Figure 4 shown, Figure 4 is a schematic diagram of the pose adjustment of a three-dimensional fetal volume data provided by the embodiment of the present application.

[0103] First, define the optimal viewing angle of the three-dimensional fetus. Establish a three-dimensional coordinate system, stipulating that the positive direction of the X-axis points vertically to the observer from the screen, the positive direction of the Y-axis is horizontally to the right, and the positive direction of the Z-axis is vertically upward. Assume the size of the volume data is (D, H, W), where D, H, and W represent depth, height, and width respectively, corresponding to the Z-axis, Y-axis, and X-axis directions in three-dimensional space. Clinically, to observe the development of the fetus's facial features more clearly, the optimal viewing position of the fetus's face is defined as: being in the middle of the screen and facing the screen, without any left-right deviation and without being upside down. Therefore, the centroid of the fetus's face needs to be placed at the center of the screen, the mid-sagittal plane of the face needs to be parallel to the XOZ plane, and the horizontal cross-section of the two eyeballs needs to be parallel to the XOY plane. There is no need to additionally stipulate that the nasolabial coronal section is parallel to the YOZ plane. That is, the initial point and the initial section are determined in the following way: the initial point is the centroid of the face, and the initial sections are the mid-sagittal plane of the face and the horizontal cross-section of the two eyeballs. The two initial sections intersect perpendicularly, and the initial point passes through the straight line where the two initial sections intersect. According to the above definition of the optimal viewing angle, the centroid of the fetus's face can be the midpoint of the line connecting the two eyeballs, denoted as P; the mid-sagittal plane of the face is denoted as Plane1; the horizontal cross-section of the two eyeballs is denoted as Plane2.

[0104] Furthermore, in the embodiment of the present application, the target tissue region can be segmented from the initially obtained three-dimensional fetus volume data to obtain the segmented three-dimensional fetus volume data. Using a 3D key point detection algorithm, the segmentation masks of the key regions corresponding to parts such as the left eye, right eye, nose, mouth, and chin are inferred. The maximum connected component processing is performed on each region to obtain the unique regions corresponding to the left eye, right eye, nose, mouth, and chin, and the centroid coordinates of each region are calculated. The centroid coordinates corresponding to the left eye, right eye, nose, mouth, and chin are P1, P2, P3, P4, and P5 respectively. According to clinical experience, the mid-sagittal plane of the face passes through the three points of the nose, mouth, and chin, passes through the midpoint of the line connecting the two eyes, and is perpendicular to the vector of the line connecting the two eyes; the horizontal cross-section of the two eyeballs passes through the two points of the eyes, and the nose coordinate point is rotated 30° upward (i.e., clockwise) around the line connecting the two eyes to obtain the third point of this section. The two-dimensional plane in the three-dimensional coordinate system can be calculated by three points determining a plane or the point-normal form. The coordinate of P is (P1 + P2) / 2. In addition, the calculation parameters of Plane1 can include the nose, i.e., P3, and the normal vector, i.e., the vector of the line connecting the two eyes: The calculation parameters of Plane2 can include the left eye, right eye, and the point obtained by rotating the nose 30 degrees upward around the line connecting the two eyes, i.e., P1, P2, and the point obtained by rotating P3 30 degrees upward around the line connecting the two eyes.

[0105] Furthermore, the translation matrix is calculated. According to "the center of mass of the fetal face needs to be placed at the center of the screen", the ideal position corresponding to the initial point P is the center of the screen, and the coordinates of the center of the screen are P_(W / 2,H / 2,D / 2). The translation matrix M1 of the identification point P to P_ is calculated. The rotation matrix is calculated. Since the direction of the midsagittal section of the face must be parallel to the direction of the XOZ plane, the normal vector of the target section corresponding to Plane1 is the Y axis and passes through P_. The target section corresponding to Plane1 is recorded as Plane1_. The rotation matrix M2 of Plane1 rotating to Plane1_ is calculated; similarly, since the horizontal cross-section direction of the eyeballs needs to be parallel to the direction of the XOY plane, the normal vector of the target section corresponding to Plane2 is the Z axis and passes through P_. The target section corresponding to Plane2 is recorded as Plane2_. The rotation matrix M3 of Plane2 rotating to Plane2_ is calculated. The expressions of Plane1_ and Plane2_ are as follows:

[0106]

[0107]

[0108] After obtaining the translation matrix M1, rotation matrix M2 and rotation matrix M3, the original three-dimensional body can be subjected to spatial geometric transformation. The specific order is to first perform the first rotation with point P as the rotation point and M2 as the rotation matrix; then perform the second rotation with point P as the rotation point and M3 as the rotation matrix; finally, perform translation with M1 as the translation matrix to obtain the adjusted three-dimensional body.

[0109] The 3D ultrasound volume data pose adjustment solution provided in this application embodiment calculates a rotation and translation matrix based on the initial point and initial section of the 3D ultrasound volume data, as well as the optimal viewing angle information. Through a series of rotation and translation operations, the 3D ultrasound volume data is adjusted from the initial pose to the optimal viewing angle. This solution does not rely on clinical experience and does not require manual operation, thereby improving the efficiency of the doctor's examination.

[0110] For further information, see Figure 5 As shown, the embodiment of the present application discloses a three-dimensional ultrasound volume data posture adjustment device, comprising:

[0111] A point-plane determination module 11 is configured to determine an initial point and an initial section from three-dimensional ultrasound volume data; a parameter determination module 12 is configured to determine posture adjustment parameters based on the initial point, the initial section, and optimal viewing angle information; the posture adjustment parameters include translation parameters and / or rotation parameters; the optimal viewing angle information includes an ideal position to which the initial point is to be adjusted and a normal vector of a target section; the target section is the section to which the initial section is to be adjusted;

[0112] The pose adjustment module 13 is configured to adjust the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters if the pose adjustment condition is met.

[0113] It can be seen that the embodiment of the present application determines the pose adjustment parameters based on the initial point and the initial section in the three-dimensional ultrasonic volume data and the best viewing angle information corresponding to the initial point and the initial section, and then adjusts the pose of the three-dimensional ultrasonic volume data based on the pose adjustment parameters. In this way, the pose of the three-dimensional ultrasonic volume data can be automatically adjusted without manually dragging the trackball for adjustment, avoiding the influence of subjective judgment and improving the adjustment efficiency of the pose of the three-dimensional ultrasonic volume data.

[0114] Among them, the point-plane determination module 11 specifically includes a point determination sub-module and a plane determination sub-module; among them,

[0115] The point determination sub-module includes:

[0116] The key area inference unit is configured to perform feature analysis on the three-dimensional ultrasonic volume data and infer the first reference key area where the first target part is located based on the volume data features of the first target part;

[0117] The key area determination unit is configured to perform a maximum connected domain process on the first reference key area to obtain the first target key area uniquely corresponding to the first target part;

[0118] The point calculation unit is configured to calculate the centroid coordinates of the first target key area to obtain the initial point. Optionally, the key area inference unit is configured to perform feature analysis on the three-dimensional ultrasonic volume data, infer the second reference key area where the second target part is located based on the volume data features of the second target part, and infer the third reference key area where the third target part is located based on the volume data features of the third target part;

[0119] The key area determination unit is configured to perform a maximum connected domain process on the second reference key area to obtain the second target key area uniquely corresponding to the second target part; perform a maximum connected domain process on the third reference key area to obtain the third target key area uniquely corresponding to the third target part;

[0120] The point calculation unit is configured to calculate the centroid coordinates of the second target key area to obtain the first reference point; calculate the centroid coordinates of the third target key area to obtain the second reference point; and determine the initial point based on the first reference point and the second reference point.

[0121] Further, the point determination sub-module is further configured to determine at least three key points from the three-dimensional ultrasound volume data; correspondingly, the plane determination sub-module is configured to calculate a normal vector based on at least two of the at least three key points, and use the normal vector and the remaining key points to determine the initial section plane, or directly determine the initial section plane using the at least three key points.

[0122] Moreover, the point-plane determination module 11 can specifically be configured to determine an initial point and two initial section planes that intersect vertically from the three-dimensional ultrasound volume data; wherein, the initial point passes through the straight line where the two initial section planes intersect.

[0123] Further, the point determination sub-module can be configured to determine the facial centroid as the initial point from the three-dimensional fetal volume data; the plane determination sub-module can be configured to determine the median sagittal section plane of the fetal face and the horizontal transverse section plane of both eyeballs as the initial section planes from the three-dimensional fetal volume data. Correspondingly, the point determination sub-module is specifically configured to determine three key points corresponding to the horizontal transverse section plane of both eyeballs from the three-dimensional ultrasound volume data; the three key points include the centroid of the left eye part, the centroid of the right eye part, and the centroid of the nose part; the plane determination sub-module is specifically configured to use the connection line between the centroid of the left eye part and the centroid of the right eye part as the axis, rotate the centroid of the nose part clockwise around the axis by a preset angle to obtain a rotated point; and determine the plane where the centroid of the left eye part, the centroid of the right eye part, and the rotated point are located as the horizontal transverse section plane of both eyeballs.

[0124] The parameter determination module 12 can specifically include:

[0125] The translation parameter determination sub-module is configured to calculate a translation parameter based on the initial point and the ideal position;

[0126] The rotation parameter determination sub-module is configured to calculate a rotation parameter based on the initial section plane, the normal vector of the target section plane, and the point that the target section plane passes through.

[0127] Optionally, the pose adjustment module 13 is configured to use the initial point as the rotation point, rotate the three-dimensional ultrasound volume data according to the rotation parameter to obtain a rotated three-dimensional ultrasound volume data; and translate the rotated three-dimensional ultrasound volume data according to the translation parameter;

[0128] Optionally, the pose adjustment module 13 is configured to translate the three-dimensional ultrasound volume data according to the translation parameter to obtain a translated three-dimensional ultrasound volume data; and use the translated initial point as the rotation point, rotate the translated three-dimensional ultrasound volume data according to the rotation parameter.

[0129] See Figure 6As shown in the figure, an embodiment of the present application discloses an ultrasonic device 20, including a processor 21 and a memory 22; wherein, the memory 22 is used to store computer programs; the processor 21 is used to execute the computer programs, and the three-dimensional ultrasonic volume data pose adjustment method disclosed in the foregoing embodiments.

[0130] For the specific process of the above three-dimensional ultrasonic volume data pose adjustment method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0131] Moreover, as a carrier for resource storage, the memory 22 can be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc., and the storage method can be temporary storage or permanent storage.

[0132] In addition, the ultrasonic device 20 further includes a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26; wherein, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and specific limitations are not imposed here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application needs, and specific limitations are not imposed here.

[0133] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing computer programs, wherein the computer programs, when executed by a processor, implement the three-dimensional ultrasonic volume data pose adjustment method disclosed in the foregoing embodiments.

[0134] For the specific process of the above three-dimensional ultrasonic volume data pose adjustment method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0135] In this specification, the embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and reference can be made to the description of the method part for related parts.

[0136] The steps of the methods or algorithms described in combination with the embodiments disclosed in this article can be directly implemented by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well-known in the technical field.

[0137] The above has introduced in detail a three-dimensional ultrasonic volume data pose adjustment method, device, equipment and medium provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for adjusting the pose of three-dimensional ultrasonic volume data, characterized in that, Including: Determining an initial point and an initial section plane from three-dimensional ultrasound volume data; Determining pose adjustment parameters based on the initial point, the initial section plane, and optimal viewing angle information; The pose adjustment parameters include translation parameters and / or rotation parameters; the optimal viewing angle information includes the ideal position to which the initial point is to be adjusted and the normal vector of the target section plane; the target section plane is the section plane to which the initial section plane is to be adjusted; If the pose adjustment condition is met, adjusting the pose of the three-dimensional ultrasound volume data on the screen based on the pose adjustment parameters.

2. The three-dimensional ultrasound volume data pose adjustment method according to claim 1, characterized in that Determining an initial point from three-dimensional ultrasound volume data includes: Performing feature analysis on the three-dimensional ultrasound volume data, and inferring a first reference key region where the first target part is located based on the volume data features of the first target part; Performing a maximum connected component processing on the first reference key region to obtain a first target key region uniquely corresponding to the first target part; Calculating the centroid coordinates of the first target key region to obtain the initial point.

3. The three-dimensional ultrasonic volume data pose adjustment method according to claim 1, characterized in that Determining an initial point from three-dimensional ultrasound volume data includes: Performing feature analysis on the three-dimensional ultrasound volume data, inferring a second reference key region where the second target part is located based on the volume data features of the second target part, and inferring a third reference key region where the third target part is located based on the volume data features of the third target part; Performing a maximum connected component processing on the second reference key region to obtain a second target key region uniquely corresponding to the second target part, and calculating the centroid coordinates of the second target key region to obtain a first reference point; Performing a maximum connected component processing on the third reference key region to obtain a third target key region uniquely corresponding to the third target part, and calculating the centroid coordinates of the third target key region to obtain a second reference point; Determining the initial point based on the first reference point and the second reference point.

4. The three-dimensional ultrasonic volume data pose adjustment method according to claim 1, characterized in that Determining an initial section plane from three-dimensional ultrasound volume data includes: Determining at least three key points from the three-dimensional ultrasound volume data; Calculating a normal vector based on at least two of the at least three key points, and determining the initial section plane by using the normal vector and the remaining key points; Or, Directly determining the initial section plane by using the at least three key points.

5. The three-dimensional ultrasonic volume data pose adjustment method according to claim 1, characterized in that The determining the initial point and the initial section plane from three-dimensional ultrasound volume data includes: Determining an initial point and two mutually perpendicular initial section planes from the three-dimensional ultrasound volume data; wherein, the initial point passes through the straight line where the two initial section planes intersect.

6. The three-dimensional ultrasound volume data pose adjustment method according to claim 5, wherein The three-dimensional ultrasound volume data is three-dimensional fetal volume data, and the determining the initial point and the initial section plane from the three-dimensional ultrasound volume data includes: Determining the facial centroid from the three-dimensional fetal volume data as the initial point; Determining the median sagittal section plane of the face and the horizontal transverse section plane of both eyeballs from the three-dimensional fetal volume data as the initial section planes.

7. The three-dimensional ultrasound volume data pose adjustment method according to claim 6, characterized in that Determining the horizontal transverse section plane of both eyeballs from the three-dimensional fetal volume data as the initial section plane includes: Determining three key points corresponding to the horizontal transverse section plane of both eyeballs from the three-dimensional ultrasound volume data; the three key points include the centroid of the left eye part, the centroid of the right eye part, and the centroid of the nose part; Taking the line connecting the centroid of the left eye part and the centroid of the right eye part as the axis, rotate the centroid of the nose part clockwise around the axis by a preset angle to obtain a rotated point; Determine the plane where the centroid of the left eye part, the centroid of the right eye part, and the rotated point are located as the horizontal cross-section of the two eyeballs.

8. The three-dimensional ultrasound volume data pose adjustment method according to any one of claims 1 to 7, characterized in that When the pose adjustment parameters include translation parameters and rotation parameters, determining the pose adjustment parameters based on the initial point, the initial section plane, and the optimal viewing angle information includes: Calculating the translation parameters based on the initial point and the ideal position; Calculating the rotation parameters based on the normal vectors of the initial section plane and the target section plane, and the point passed by the target section plane.

9. The three-dimensional ultrasonic volume data pose adjustment method according to claim 8, characterized in that Adjusting the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters includes: Taking the initial point as the rotation point, rotating the three-dimensional ultrasonic volume data according to the rotation parameters to obtain a rotated three-dimensional ultrasonic volume data; translating the rotated three-dimensional ultrasonic volume data according to the translation parameters; Or, translating the three-dimensional ultrasonic volume data according to the translation parameters to obtain a translated three-dimensional ultrasonic volume data; taking the translated initial point as the rotation point, and rotating the translated three-dimensional ultrasonic volume data according to the rotation parameters.

10. A three-dimensional ultrasonic volume data pose adjustment device, characterized in that, Including: A point and plane determination module, configured to determine an initial point and an initial section plane from the three-dimensional ultrasonic volume data; A parameter determination module, configured to determine pose adjustment parameters based on the initial point, the initial section plane, and the optimal viewing angle information; the pose adjustment parameters include translation parameters and / or rotation parameters; the optimal viewing angle information includes the ideal position to which the initial point is to be adjusted and the normal vector of the target section plane; the target section plane is the section plane to which the initial section plane is to be adjusted; A pose adjustment module, configured to, if the pose adjustment condition is met, adjust the pose of the three-dimensional ultrasonic volume data on the screen based on the pose adjustment parameters.

11. An ultrasonic device, characterized in that, Including a memory and a processor, wherein: The memory is used to store a computer program; The processor is configured to execute the computer program to implement the three-dimensional ultrasonic volume data pose adjustment method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, For storing a computer program, wherein the computer program, when executed by a processor, implements the three-dimensional ultrasonic volume data pose adjustment method according to any one of claims 1 to 9.

Images