WO2024140175A1 - Ultrasonic image processing method and apparatus, device, and storage medium - Google Patents

Abstract

Disclosed in the present application are an ultrasonic image processing method and apparatus, a device, and a storage medium. The method comprises: detecting a selection instruction for instructing to select a target object in an ultrasonic image, and using coordinates indicated by the selection instruction as starting point coordinates; and performing boundary diffusion identification all around by using the starting point coordinates as the center so as to identify the boundary contour of the target object in the ultrasonic image. According to the present application, the boundary contour of the target object is identified by using any point in the target object as the starting point coordinates and performing boundary diffusion all around by using the starting point coordinates as the center. The boundary of the target object is automatically identified, human intervention components are reduced, and the boundary identification efficiency and accuracy are improved. The boundary contour is identified on the basis of a change in an energy coefficient between pixel points, and the change in the energy coefficient conforms to a change of texture characteristics between inside of the target object and at a boundary part, thus the boundary contour can be accurately identified. It is also possible to display the whole boundary diffusion process on the ultrasonic image in an overlayed manner, achieving the visualization of the whole boundary diffusion process.

Description

Ultrasonic image processing method, device, equipment and storage medium

This application claims the priority of the Chinese patent application filed with the China Patent Office on December 29, 2022, with application number 202211710098.0 and invention name “Ultrasonic image processing method, device, equipment and storage medium”, all contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the field of medical imaging technology, and in particular to an ultrasonic image processing method, device, equipment and storage medium.

Background technique

At present, when doctors use ultrasound equipment to scan patients, they need to measure application indicators such as the area and perimeter of the target object such as the suspected lesion or human tissue to be examined. Before measuring the application indicators, the boundary contour of the target object needs to be determined first.

In the related art, doctors usually determine the boundary contour of the target object based on their experience and manually draw the boundary line of the target object contour. However, the doctor's operation is cumbersome, and the efficiency and accuracy of determining the boundary contour of the target object are very low.

Summary of the invention

To solve the above problems, the present application provides an ultrasonic image processing method, device, equipment and storage medium, which performs boundary diffusion from the starting point coordinates within the target object as the center, automatically identifies the boundary contour of the target object, reduces human intervention components, and improves the efficiency and accuracy of boundary contour recognition.

In a first aspect, an embodiment of the present application provides an ultrasound image processing method, comprising:

detecting a selection instruction for instructing selection of a target object in the ultrasound image;

Taking the coordinates indicated by the selection instruction as the starting point coordinates;

Boundary diffusion recognition is performed around the starting point coordinates to identify the boundary contour of the target object from the ultrasound image.

An embodiment of the second aspect of the present application provides an ultrasonic image processing device, comprising:

A detection module, configured to detect a selection instruction for instructing to select a target object in an ultrasound image;

A starting point determination module, used to use the coordinates indicated by the selection instruction as starting point coordinates;

The boundary recognition module is used to perform boundary diffusion recognition around the starting point coordinates as the center, so as to recognize the boundary contour of the target object from the ultrasonic image.

An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in the first aspect is implemented.

An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

An embodiment of the fifth aspect of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a processor to implement the method described in the first aspect above.

The technical solution provided in the embodiments of the present application has at least the following technical effects or advantages:

This application uses any point in the target object as the starting point coordinate, and spreads to the surrounding boundaries with the starting point coordinate as the center to identify the boundary contour of the target object. It realizes automatic identification of the boundary contour of the target object, reduces human intervention, and improves boundary Recognition efficiency and accuracy.

Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application.

BRIEF DESCRIPTION OF THE DRAWINGS

Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

FIG1 is a schematic diagram showing the structure of an ultrasound system provided in an embodiment of the present application;

FIG2 shows a functional structure block diagram of an ultrasound system provided in an embodiment of the present application;

FIG3 shows a flow chart of an ultrasound image processing method provided in an embodiment of the present application;

FIG4 is a schematic diagram showing the coordinates of the starting point within the target object provided by an embodiment of the present application;

FIG5 is a schematic diagram showing a waveform formed by superimposing and displaying boundary diffusion in an ultrasound image provided by an embodiment of the present application;

FIG6 is a schematic diagram showing the energy coefficient on each waveform marked on the basis of FIG5 ;

FIG. 7 is a schematic diagram showing a first waveform W1 formed by diffusion from a starting point coordinate to each pixel point adjacent thereto provided by an embodiment of the present application;

FIG8 is a schematic diagram showing a first waveform W1 formed by directly setting the starting point coordinates to diffuse outwards provided in an embodiment of the present application;

FIG. 9 is a schematic diagram showing the continued outward diffusion of a pixel point B on the first waveform W1 provided by an embodiment of the present application;

FIG10 is a schematic diagram showing a diffusion path from pixel point A to pixel point E provided by an embodiment of the present application;

FIG11 is a schematic diagram showing the structure of an ultrasonic image processing device provided in an embodiment of the present application;

FIG. 12 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.

Detailed ways

The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

When doctors use ultrasound equipment to examine patients, they need to determine the boundary contours of target objects such as lesions or human tissues. In related technologies, doctors determine the boundary contours of target objects based on their experience and manually draw the boundary lines of target objects using external devices such as keyboards or mice connected to the ultrasound equipment. However, such operations require a high level of personal experience from doctors, and the doctors' operations are cumbersome and highly subjective, resulting in low efficiency and accuracy in determining boundary contours.

Based on this, the embodiments of the present application provide an ultrasonic image processing method, device, equipment and storage medium, which are described below in conjunction with the accompanying drawings.

Fig. 1 shows a schematic diagram of the structure of an ultrasound system based on which the ultrasound image processing method according to an embodiment of the present application is improved. The ultrasound system comprises a host 1, an ultrasound probe 2, an operating device 3 and a display device 4.

According to different application scenarios, the doctor can place the ultrasound probe 2 on the body surface of the subject, or insert the ultrasound probe 2 into the subject's body, and the ultrasound wave is transmitted to the target detection area of the subject via the ultrasound probe 2. Then the ultrasound probe 2 receives the ultrasound echo formed by the ultrasound wave passing through the target detection area, and the ultrasound echo can reflect the target detection area. Tissue features. Ultrasonic echo data of the target detection area is obtained based on the ultrasonic echo, and the ultrasonic echo data is transmitted to the host 1.

The host 1 generates an ultrasonic image of the target detection area based on the ultrasonic echo data, and transmits the ultrasonic image to the display device 4 for display. The host 1 may also include a storage device, and the host 1 may store the ultrasonic image in the storage device.

The operating device 3 may include external devices such as a mouse and a keyboard connected to the host 1. When the physician uses the ultrasound probe to detect the target detection area of the subject and uses the display device 4 to display the ultrasound image in real time, the physician observes the displayed ultrasound image. If a target object such as a lesion or target tissue to be detected is found in the currently displayed ultrasound image, the physician presses the freeze button in the operating device 3 to stop scanning, and selects the ultrasound image of the best section from the scanned ultrasound images, so that the ultrasound image processing method provided in the embodiment of the present application can be used to automatically identify the boundary contour of the target object from the ultrasound image of the best section.

FIG2 shows a functional block diagram of the ultrasound system. The host 1 includes an image input unit, an ultrasound image processing unit, an ultrasound intelligent processing unit, a video encoding unit, a control unit and an operation unit. The ultrasound probe 2 includes a processing unit, a signal transceiver unit and an operation unit. The processing unit and the signal transceiver unit obtain the ultrasound echo signal and send it to the image input unit. The image input unit receives the ultrasound echo signal sent by the ultrasound probe 2, and performs analog transceiver, beam synthesis, signal conversion and other processing on the received ultrasound echo signal, and transmits it to the ultrasound image processing unit. The ultrasound image processing unit performs ISP (Image Signal Processing) operations on the ultrasound image transmitted by the image input unit, including but not limited to brightness conversion, sharpening, contrast enhancement, etc. The ultrasound image processed by the ultrasound image processing unit is transmitted to the ultrasound intelligent processing unit, the video encoding unit or the display device. The ultrasound intelligent processing unit performs intelligent analysis on the ultrasound image processed by the ultrasound image processing unit, including but not limited to target recognition, detection, segmentation based on deep learning, etc. The ultrasound image processed by the ultrasound intelligent processing unit is transmitted to the ultrasound image processing unit or the video encoding unit. The ultrasonic image processing unit processes the ultrasonic image processed by the ultrasonic intelligent processing unit in a manner including but not limited to contour detection, brightness conversion, frame stacking and scaling. The video encoding unit encodes and compresses the image processed by the ultrasonic image processing unit or the ultrasonic intelligent processing unit, and transmits it to the storage device. The control unit controls the various units of the ultrasonic system, and the control methods include but are not limited to interface operation methods, image processing methods, ultrasonic measurement methods and video encoding methods. The operating unit includes but is not limited to switches, buttons and touch panels, which are used to receive external indication signals and output the indication signals to the control unit.

Based on the ultrasound system shown in Figures 1 and 2, an embodiment of the present application provides an ultrasound image processing method, which uses a point in the ultrasound image located within the target object as a starting point to perform boundary diffusion to the surrounding area, and automatically identifies the boundary contour of the target object based on the change in pixel gradient during the boundary diffusion process, thereby reducing human intervention components and improving the efficiency and accuracy of boundary contour recognition.

See Figure 3, which is a flow chart of an ultrasound image processing method provided in an embodiment of the present application. The method specifically comprises the following steps:

Step 101: a selection instruction for instructing to select a target object in an ultrasound image is detected, and the coordinates indicated by the selection instruction are used as the starting point coordinates.

When the physician detects the target detection area of the subject through the ultrasound probe, the ultrasound system's display device displays the ultrasound image of the target detection area in real time. The physician observes the displayed ultrasound image, and when the target object appears in the ultrasound image, the physician can stop scanning and select the ultrasound image of the best section of the target object from the currently scanned ultrasound image. The target object may be a lesion, or may be a target tissue to be examined, such as the thyroid gland, liver, kidney, etc.

After the display device displays the ultrasound image containing the target object, the physician can operate the operation device of the ultrasound system and submit a selection instruction through a mouse or keyboard included in the operation device, and the selection instruction is used to select the target object in the ultrasound image. For example, the physician can click the target object in the currently displayed ultrasound image with a mouse.

The control unit of the ultrasound system host detects the selection instruction submitted by the operating device, determines the coordinates indicated by the selection instruction, and uses the coordinates as the starting coordinates, which are the coordinates of the position of the target object selected by the physician through the operating device in the ultrasound image.

Specifically, an image coordinate system is established in the currently displayed ultrasound image. For example, the coordinates of the upper left corner vertex of the currently displayed ultrasound image are taken as the origin, the horizontal side passing through the origin in the ultrasound image is taken as the x-axis, and the vertical side passing through the origin is taken as the y-axis. Based on the origin, the x-axis, and the y-axis, the image coordinate system is established. In actual applications, the image coordinate system can also be established with the coordinates of other vertices in the ultrasound image as the origin.

After the image coordinate system is established in the ultrasound image, the control unit determines the coordinates of the position where the physician selects the target object in the image coordinate system to obtain the starting point coordinates. For example, the coordinates of the position where the physician clicks the target object are determined in the coordinate system of the ultrasound image, and the coordinates are used as the starting point coordinates. The starting point coordinates may be any point in the area where the target object is located. In the ultrasound image schematic diagram shown in FIG4 , the non-shaded area is the target area where the target object is located, and the starting point coordinates may be any point in the target area.

In an embodiment of the present application, after detecting the selection instruction submitted by the operating device, the control unit can also obtain the detection frame of the target object indicated by the selection instruction from the ultrasonic intelligent processing unit, and the coordinates of the center position of the detection frame are the coordinates indicated by the selection instruction.

Although the accuracy of the boundary contour of the target object determined by the physician is very poor, the operation of the physician selecting any point in the area where the target object is located is relatively simple and has high accuracy. If the starting point coordinates selected by the physician are located on the boundary contour of the target object, or are located outside the area where the target object is located, the ultrasonic image processing method provided in the embodiment of the present application will not be able to identify the boundary contour of the target object. In this case, when the boundary contour of the target object is still not detected within the preset time length, a prompt message can be displayed through a display device, and the prompt message is used to prompt the physician to reselect a point in the area where the target object is located as the starting point coordinate. Among them, the preset time length can be 5s, 10s, 30s, etc. The embodiment of the present application does not limit the specific value of the preset time length, and it can be set according to demand in actual application.

After the starting point coordinates are determined in this step, the boundary contour of the target object is automatically identified through the following step 102 operation.

Step 102: Perform boundary diffusion recognition around the starting point coordinates to identify the boundary contour of the target object from the ultrasound image.

In the embodiment of the present application, diffusion is performed around the starting point coordinates, and the boundary pixel points of the target object are identified based on the change of pixel gradient in the same diffusion direction during the diffusion process, thereby obtaining the boundary contour of the target object. Specifically, the boundary contour of the target object is identified by the following operations S1 and S2.

S1: Based on the starting point coordinates, determine the energy coefficient of the pixel points on the waveform formed by each boundary diffusion, and the energy coefficient is associated with the gradient of the pixel points passed by the boundary diffusion.

In the embodiment of the present application, a boundary diffusion method is used to automatically identify the boundary contour of the target object. Multiple boundary diffusion operations are performed during the entire process, and each boundary diffusion operation will obtain a closed loop line surrounding the starting point coordinates. Therefore, the entire process is like generating a waveform that spreads from the inside to the outside with the starting point coordinates as the center, similar to water ripples. Therefore, the closed loop line generated in the boundary diffusion process is referred to as a waveform in the embodiment of the present application. Among them, the waveform generated in the boundary diffusion process can be a virtual waveform, which is not displayed in the currently displayed ultrasound image, or it can also be displayed in the currently displayed The waveform is displayed as a solid line in the ultrasound image.

After the starting point coordinates are detected in step 101, the waveform for boundary recognition is triggered and started, and the waveform diffuses outward from the starting point coordinates as the center, and boundary pixels are detected and marked during the diffusion process until the boundary contour of the target object is recognized. The boundary pixels are pixels on the boundary contour.

Since the processing operation of each boundary diffusion is the same, the embodiment of the present application only takes one boundary diffusion operation as an example to explain in detail the processing process of boundary diffusion. Specifically, the current waveform diffuses outward to form a new waveform as an example. Among them, the current waveform can be a waveform obtained by performing at least one boundary diffusion with the starting point coordinates as the center. In the embodiment of the present application, the starting point coordinates can be regarded as the initial waveform obtained by performing the first boundary diffusion with the starting point coordinates as the center, that is, there is only a pixel point corresponding to the starting point coordinates on the initial waveform. The current waveform can be the initial waveform, or any waveform among the waveforms obtained by performing at least one boundary diffusion outward from the initial waveform.

In the embodiment of the present application, the boundary diffusion can be performed from the pixel points on the current waveform to multiple diffusion directions to obtain a new waveform. The diffusion direction refers to the direction from the pixel point on the current waveform to the direction away from the starting point coordinates, and each pixel point on the current waveform corresponds to multiple diffusion directions.

From a pixel point on the current waveform, boundary diffusion is performed in each diffusion direction corresponding to the pixel point, and it can diffuse to multiple pixel points. Connect all the pixel points to which each pixel point on the current waveform diffuses, and a new waveform formed by boundary diffusion from the current waveform is obtained.

Since the diffusion operation of each pixel point on the current waveform is the same, and the diffusion operation of the pixel points in each diffusion direction is also the same. Therefore, the diffusion from the first pixel point to the first diffusion direction is used as an example to illustrate the process of boundary diffusion of the pixel points on the current waveform. The first pixel point is any pixel point on the current waveform, and the second pixel point is in the first diffusion direction of the first pixel point. The first diffusion direction is any diffusion direction of the multiple diffusion directions corresponding to the first pixel point. Based on the pixel gradient between the first pixel point of the current waveform and the second pixel point of the new waveform, the energy coefficient of the second pixel point is calculated respectively.

For example, the diffusion speed of the first pixel point on the current waveform in the first diffusion direction is obtained. The boundary diffusion is performed from the first pixel point to the first diffusion direction at the diffusion speed to obtain the second pixel point on the new waveform. Among them, the diffusion speed of the second pixel point in the first diffusion direction of the first pixel point can be understood as the diffusion step length, that is, the distance of one boundary diffusion from the first pixel point to the first diffusion direction.

In one implementation, a preset diffusion speed can be pre-configured in the ultrasound system, and each pixel performs boundary diffusion at the preset diffusion speed in each diffusion direction. The preset diffusion speed can be the distance of 1 pixel, the distance of 3 pixels, the distance of 5 pixels, etc. The embodiment of the present application does not limit the specific value of the preset diffusion speed, and it can be set according to needs in actual applications. In different diffusion directions, the preset diffusion speeds can be the same or different, and the preset diffusion speeds of different pixels can be the same or different.

Using a preset diffusion speed for boundary diffusion can reduce the amount of calculation in the boundary diffusion process and improve the efficiency of boundary diffusion. The smaller the preset diffusion speed is, the denser the waveform formed by the boundary diffusion is, and the higher the accuracy of identifying the boundary contour is. The larger the preset diffusion speed is, the faster the boundary diffusion operation can diffuse to the real boundary of the target object, and the boundary contour of the target object can be quickly identified, improving the efficiency of boundary identification. By pre-configuring the preset diffusion speed, the diffusion speed can be customized based on actual needs.

In another implementation, the preset diffusion speed is not pre-configured, but the diffusion speed of the first pixel in the first diffusion direction is obtained by calculation. Specifically, the energy coefficient of the first pixel, the energy coefficient of the third pixel, and the diffusion speed of the third pixel in the first diffusion direction are obtained. The third pixel is the upper pixel adjacent to the current waveform. The first pixel point in a waveform is obtained by boundary diffusion from the third pixel point to the first diffusion direction at the diffusion speed corresponding to the third pixel point. The diffusion speed of the first pixel point in the first diffusion direction is calculated based on the energy coefficient of the first pixel point, the energy coefficient of the third pixel point and the diffusion speed of the third pixel point in the first diffusion direction.

For example, we can first calculate the difference between the energy coefficient of the third pixel and the energy coefficient of the first pixel to obtain the energy attenuation caused by diffusion from the third pixel to the first pixel; then, based on the energy attenuation, determine the loss of diffusion speed, and calculate the difference between the diffusion speed of the third pixel in the first diffusion direction and the loss to obtain the diffusion speed of the first pixel in the first diffusion direction.

In the embodiment of the present application, the energy coefficient is related to the gradient of the pixel point, which is a form of expression for quantifying the gradient of the boundary. The gradient can be the difference between the characteristic values such as grayscale or brightness between the pixels. The gradient can represent the degree of difference between different pixels. The larger the gradient, the greater the difference between the pixels, and the smaller the gradient, the smaller the difference between the pixels. The difference between the pixels in the area where the target object is located will be smaller, while the difference between the pixels at the boundary of the target object is usually larger. Therefore, in the process of diffusion from the pixels in the target object to the outer boundary, the boundary contour of the target object can be accurately identified based on the change in the gradient.

There is a certain mapping relationship between the energy coefficient and the gradient. In the embodiment of the present application, a mapping function between the energy coefficient and the gradient can be set. The mapping function can be a linear function or a nonlinear function, wherein the nonlinear function includes but is not limited to a fitting curve, an S-shaped curve, a Log curve, etc. Assuming that _{Sn(i, j)_d} is the gradient of the pixel point at the coordinate position (i, j) in the dth direction, the mapping relationship between the energy coefficient _{en(i, j)} and the gradient Sn _{(i, j)_d} can be expressed as: _{en(i, j)} =F( _{Sn(i, j)_d} ), where F is the mapping function.

The first pixel point is obtained by boundary diffusion of the third pixel point toward the first diffusion direction, so the energy coefficient of the first pixel point is calculated by substituting the gradient between the third pixel point and the first pixel point into the mapping function. The third pixel point is obtained by boundary diffusion of the fourth pixel point in the previous waveform adjacent to the waveform where the third pixel point is located toward the first diffusion direction, so the energy coefficient of the third pixel point is calculated by substituting the gradient between the fourth pixel point and the third pixel point into the mapping function.

V _{n(i, j)_d} is used to identify the diffusion speed of the pixel point with coordinates (i, j) on the nth waveform in the dth direction, and the calculation formula of the diffusion speed can be shown as follows:
Vn _{(i,j)_d} = Vn _{-1(k,z)_d} - a*( _en-1(k,z) -en _(i,j) )

Wherein, V _{n-1(k, z)_d} is the diffusion speed of the pixel point with coordinates (k, z) on the n-1th waveform in the dth direction. The boundary diffusion is carried out from the pixel point with coordinates _{(k, z) on the n-1th waveform toward the dth direction at the diffusion speed V n-1(k, z)_d} , and diffuses to the pixel point with coordinates (i, j) on the n-1th waveform. _{en(i, j)} is the energy coefficient of the pixel point with coordinates (i, j) on the n-1th waveform, and _{en-1(k, z)} is the energy coefficient of the pixel point with coordinates (k, z) on the n-1th waveform. a is a preset coefficient. If a=0, the boundary diffusion is carried out at a uniform speed, and the waveform generated by each boundary diffusion is circular. If a is set not equal to 0, the diffusion speed of each pixel in different diffusion directions will be different. The diffusion speed is related to the attenuation degree of the energy coefficient. Boundary diffusion based on the diffusion speed calculated in this way is closer to the actual situation of the gradient change between pixels in the area where the target object is located, which can improve the accuracy of boundary recognition.

For the above calculation of the diffusion speed of the first pixel point in the first diffusion direction, the energy coefficient of the first pixel point, the energy coefficient of the third pixel point and the diffusion speed of the third pixel point in the first diffusion direction are substituted into the above calculation formula, so that the diffusion speed of the first pixel point in the first diffusion direction can be quickly calculated.

After obtaining the diffusion speed corresponding to the first pixel point, boundary diffusion is performed from the first pixel point on the current waveform to the first diffusion direction at the diffusion speed, and can be diffused to the second pixel point. In each diffusion direction, the diffusion speed of the first pixel point in each other diffusion direction is obtained respectively according to the above method, and boundary diffusion is performed respectively to obtain multiple pixel points corresponding to the first pixel point after diffusion.

Similarly, for each other pixel point on the current waveform, the same operation as the first pixel point is adopted, and each other pixel point on the current waveform is subjected to boundary diffusion respectively to obtain multiple pixel points corresponding to each other pixel point after boundary diffusion. All pixel points obtained by boundary diffusion of the current waveform are connected to obtain a new waveform.

Then, based on the pixel gradient between two corresponding pixels in each diffusion direction of the current waveform and the new waveform, the energy coefficient of each pixel on the new waveform is calculated. Since the calculation process of the energy coefficient of each pixel is the same, only the second pixel on the new waveform is used as an example for explanation. The second pixel is a pixel obtained by boundary diffusion from the first pixel on the current waveform, and the first pixel is any pixel on the current waveform.

Specifically, based on the characteristic value of the first pixel point on the current waveform and the characteristic value of the second pixel point on the new waveform, the pixel gradient corresponding to the second pixel point is calculated. The characteristic value may be the grayscale or brightness of the pixel point. The pixel gradient corresponding to the second pixel point may be the grayscale difference or brightness difference between the first pixel point and the second pixel point.

Based on the pixel gradient corresponding to the second pixel, the energy coefficient of the second pixel is determined. Specifically, the pixel gradient corresponding to the second pixel is substituted into the mapping function between the energy coefficient and the gradient to calculate the energy coefficient of the second pixel.

For each other pixel point on the new waveform, the energy coefficient of each other pixel point on the new waveform is determined according to the operation on the second pixel point.

S2: Based on the energy coefficient of each pixel point on the waveform, the boundary contour of the target object is identified from the ultrasound image.

The gradients of pixels at different positions in an ultrasound image are different. The gradients of pixels in areas with small changes in image texture are small, and the gradients of pixels in areas with large changes in image texture are large. The image texture changes greatly at the boundary of the target object, so the pixel gradient is also large. During the boundary diffusion process, energy attenuation occurs when the waveform diffuses from the inside to the outside, that is, the energy coefficient decreases. When the waveform diffuses from an area with a small gradient to an area with a large gradient, the attenuated energy is greater, and the energy coefficient attenuates more when it diffuses to an area with a larger gradient. When the energy coefficient decays to a certain extent, it indicates that the waveform has crossed the boundary of the target object during the diffusion process, and the boundary of the target object can be identified, so there is no need to continue to diffuse outward.

In the embodiment of the present application, a preset threshold is pre-configured for determining whether it is not necessary to continue diffusion, and the diffusion is stopped when the energy coefficient decays to the preset threshold. Specifically, in the boundary diffusion process, each time the energy coefficient of a pixel point on a waveform is determined, it is determined whether the energy coefficient of the pixel point is less than the preset threshold. If yes, the boundary diffusion of the pixel point will not be performed subsequently. If not, the boundary diffusion of the pixel point will continue in the above manner.

In the embodiment of the present application, the pixel point whose energy coefficient is less than the preset threshold is called the target pixel point, and for each target pixel point, a diffusion path from the starting point coordinate to each target pixel point is determined respectively. The diffusion path includes a plurality of node pixel points, and each node pixel point is at least one pixel point obtained in the process of diffusion from the starting point coordinate to the target pixel point.

Based on the energy coefficient of the node pixel points on each diffusion path, the boundary pixel points located on each diffusion path are determined respectively. The process of determining the boundary pixel points is described by taking the first diffusion path as an example, and the first diffusion path is any diffusion path in each diffusion path. Specifically, the absolute value of the difference between the energy coefficients of any two adjacent node pixel points on the first diffusion path is calculated respectively, and the maximum absolute value of the difference is determined from the multiple absolute values of the difference calculated. The node pixel point farthest from the starting point coordinates among the two node pixel points corresponding to the maximum absolute value of the difference is determined as the boundary pixel point.

For each other diffusion path, the boundary pixel points on each other diffusion path are determined in the same manner as above, and then each determined boundary pixel point is connected into a line, thus obtaining the boundary contour of the target object.

Since the energy coefficient of the waveform will drop a lot when crossing the boundary of the target object, if the energy coefficients of two adjacent node pixels in the diffusion path are very different, then these two node pixels are likely to be located on both sides of the boundary. By calculating the absolute value of the difference between the energy coefficients of any two adjacent node pixels on the diffusion path, the two node pixels corresponding to the largest absolute value of the difference are found. These two pixels are the two pixels on the diffusion path that are most likely to be located on both sides of the boundary. The pixel point farthest from the starting point coordinates of the two pixels is taken as the boundary pixel point, so that the determined boundary pixel point can be close to the real boundary of the target object, and the pixel point farthest from the starting point coordinates of the above two pixels is selected as the boundary pixel point, so that the boundary pixel point may be on the real boundary of the target object or outside the real boundary, and the probability of being inside the real boundary is very small, so that the boundary contour of the target object finally determined can include all areas of the target object.

In the embodiment of the present application, the boundary contour of the target object determined with the maximum probability can include all areas of the target object. After determining the two node pixel points corresponding to the maximum absolute value of the difference, the boundary pixel points are determined on the first diffusion path and in the direction away from the starting point coordinates, with the two node pixel points as the starting point, and the distance between the boundary pixel point and the two node pixel points is the preset distance. The preset distance can be set according to actual needs.

The embodiment of the present application takes any point in the area where the target object is located as the center, performs boundary diffusion to the surrounding area, and identifies the boundary contour of the target object based on the change of energy coefficient between pixel points during the diffusion process. The boundary contour of the target object is automatically identified, and there is no need for doctors to subjectively determine the boundary contour, which reduces manual operations and improves the efficiency and accuracy of identifying the boundary contour of the target object in ultrasonic testing.

In the embodiment of the present application, after the boundary contour of the target object is identified in the above manner, the boundary contour of the target object can also be marked in the currently displayed ultrasound image. Specifically, the boundary contour can be marked by using a preset color or bolding, and the preset color can be red or yellow. By marking the boundary contour of the target object, the physician can see the size and shape of the target object more intuitively, which helps the physician to perform subsequent size measurements of the target object and improve the accuracy and reference value of ultrasound detection.

After the boundary contour of the target object is identified in the above manner, the application index of the target object can also be measured based on the identified boundary contour, and the application index can include the perimeter, area, aspect ratio, etc. of the target object. The embodiment of the present application automatically and accurately identifies the boundary contour of the target object, which helps to improve the accuracy of the application index measurement and improve the clinical reference value of the measured application index.

In some embodiments of the present application, during the boundary diffusion process, the waveform formed by each boundary diffusion can also be superimposed and displayed in the currently displayed ultrasound image. In the schematic diagram of the ultrasound image shown in FIG5 , the starting point coordinates are displayed, the boundary contour of the target object is marked in bold, and each waveform generated during the boundary diffusion process is superimposed and displayed.

The schematic diagram of the ultrasound image shown in FIG6 is based on the ultrasound image shown in FIG5 and also marks the energy coefficients at multiple locations on each waveform, which enables the physician to intuitively see the recognition process of the boundary contour based on the ultrasound image, making the entire recognition process visual and explainable.

In some other embodiments of the present application, during the boundary diffusion process, a waveform diffusion animation is generated based on the waveform formed by the boundary diffusion. The waveform diffusion animation can be displayed at a certain frequency, such as water ripples spreading outward from the starting point coordinates. The waveform diffusion animation is superimposed and played on the currently displayed ultrasound image. For example, the previous circle of waveforms can disappear after being displayed, and the next circle of waveforms can be displayed.

The process of boundary diffusion identification of a target object is displayed in the currently displayed ultrasound image in the form of a waveform diffusion animation, which can make the entire identification process more intuitive and interesting.

In an embodiment of the present application, the selected position of the target object is selected as the starting point coordinate, and the boundary diffusion is performed around the starting point coordinate as the center, and the boundary contour of the target object is identified during the boundary diffusion process. Automatic recognition of the boundary contour of the target object is achieved, which greatly reduces the human intervention component in the entire process, improves the efficiency of boundary contour recognition, and the accuracy of boundary contour recognition is very high. Furthermore, during the boundary diffusion process, the boundary contour of the target object is identified based on the change of the energy coefficient between the pixel points. The change of the energy coefficient conforms to the change of the image texture characteristics inside and at the boundary of the target object, so the boundary contour of the target object can be accurately identified. Furthermore, the entire boundary diffusion process can also be superimposed and displayed on the currently displayed ultrasound image to achieve visualization of the entire boundary diffusion process.

In order to facilitate understanding of the ultrasound image processing process provided by the embodiment of the present application, the specific process of identifying the boundary contour of the target object is explained below by way of example. Taking the target object as a cyst as an example, assuming that the physician finds a cyst in the ultrasound image displayed in real time on the display screen of the ultrasound device during an ultrasound examination of the abdomen of the subject, the physician can click the mouse anywhere within the area where the cyst is located. The ultrasound device detects the click instruction input by the mouse, determines the coordinates of the click position in the ultrasound image, and uses the coordinates as the starting point coordinate A. After the ultrasound device detects the starting point coordinate A, it starts the boundary recognition waveform, and diffuses the boundary around the starting point coordinate A.

In one example, assuming that the diffusion speed is the distance of one pixel, the distance of one pixel is diffused from the starting coordinate A to the surrounding diffusion directions, as shown in Figure 7, from the starting coordinate A to the surrounding 8 adjacent pixels, the closed-loop waveform formed by these 8 pixels is the first waveform W1 formed in the boundary diffusion process. Based on the gradient between the starting coordinate A and the adjacent pixels, the energy coefficient of each pixel diffused to is calculated respectively.

In another example, the first waveform W1 may be directly set. The shape of the first waveform W1 may be circular. The distance between each pixel point on W1 and the starting coordinate A is v ₀ , that is, the diffusion speed from the starting coordinate A to each diffusion direction to the waveform W1 is v0. The energy coefficient of each pixel point on the waveform W1 may be set to 1. FIG8 shows a schematic diagram of directly setting the first waveform W1.

After the first waveform W1 is obtained according to any of the above examples, for each pixel point on the waveform W1, it is determined whether there is a target pixel point whose energy coefficient is less than the preset threshold value. If there is a target pixel point whose energy coefficient is less than the preset threshold value, the boundary diffusion of the target pixel point is no longer performed. For the pixel points whose energy coefficient is greater than or equal to the preset threshold value, the boundary diffusion of these pixel points is performed again.

As shown in FIG9 , the pixel point B on the waveform W1 is again diffused in multiple diffusion directions. Taking diffusion from pixel point B to pixel point C as an example, the diffusion speed of pixel point B is first calculated based on the energy coefficient of pixel point B, the diffusion speed of pixel point A, and the energy coefficient. Diffusion is performed from pixel point B to pixel point C at the diffusion speed of pixel point B.

According to the above method, it diffuses outward in circles until it reaches the target pixel E whose energy coefficient is less than the preset threshold, and then stops diffusing to the target pixel E. Determine the diffusion path from the starting coordinate A to the target pixel E. As shown in Figure 10, the diffusion path includes five node pixels, namely, pixels A, B, C, D, and E. The absolute value of the difference between the energy coefficients of pixels A and B, the absolute value of the difference between the energy coefficients of pixels B and C, the absolute value of the difference between the energy coefficients of pixels C and D, and the absolute value of the difference between the energy coefficients of pixels D and E are calculated respectively. The largest absolute value of the difference is determined from the four calculated absolute values of the difference. Assuming that the absolute value of the difference between the energy coefficients of pixels D and E is the largest, pixel E is determined as a boundary pixel of the cyst.

Each target pixel point whose energy coefficient is less than a preset threshold is processed in the above manner to determine all boundary pixel points of the cyst, and the closed loop formed by all boundary pixel points is the boundary contour of the cyst.

A point inside the cyst is used as the starting point coordinate, and the boundary diffusion is performed around the starting point coordinate. The boundary contour of the cyst is automatically identified during the boundary diffusion process. There is very little manual operation in the whole process, which improves the efficiency and accuracy of boundary identification. The boundary contour of the cyst is identified based on the change of the energy coefficient between the pixels. The change of the energy coefficient conforms to the change of the texture characteristics inside the cyst and at the boundary, so the boundary contour of the cyst can be accurately identified.

Referring to FIG. 11 , an embodiment of the present application further provides an ultrasonic image processing device, which is used to execute the ultrasonic image processing method described in the above embodiment, and the device includes:

A detection module 201 is used to detect a selection instruction for instructing to select a target object in an ultrasound image;

A starting point determination module 202, configured to use the coordinates indicated by the selection instruction as starting point coordinates;

The boundary recognition module 203 is used to perform boundary diffusion recognition around the starting point coordinates to recognize the boundary contour of the target object from the ultrasound image.

In some embodiments, the boundary recognition module 203 can be specifically used to determine the energy coefficient of the pixel points on the waveform formed by each boundary diffusion based on the starting point coordinates, and the energy coefficient is associated with the gradient of the pixel points through which the boundary diffusion passes; based on the energy coefficient of the pixel points on each waveform, the boundary contour of the target object is identified from the ultrasound image.

In some embodiments, the boundary recognition module 203 can be specifically used to perform boundary diffusion from the pixel points on the current waveform to multiple diffusion directions to obtain a new waveform; the current waveform is a waveform obtained by performing at least one boundary diffusion with the starting point coordinate as the center; based on the pixel gradient between the first pixel point of the current waveform and the second pixel point of the new waveform, the energy coefficient of the second pixel point is calculated respectively. Wherein, the second pixel point is in the first diffusion direction of the first pixel point, the first pixel point is any pixel point on the current waveform, and the first diffusion direction is any diffusion direction of the multiple diffusion directions corresponding to the first pixel point.

In some embodiments, the boundary recognition module 203 can be specifically used to obtain the diffusion speed of the first pixel point in the first diffusion direction; perform boundary diffusion from the first pixel point to the first diffusion direction at the diffusion speed to obtain the second pixel point, and multiple second pixel points form the new waveform.

In some embodiments, the boundary recognition module 203 can be specifically used to obtain the energy coefficient of the first pixel point, the energy coefficient of the third pixel point and the diffusion speed of the third pixel point in the first diffusion direction; the third pixel point is a pixel point in the previous waveform adjacent to the current waveform, and the first pixel point is obtained by boundary diffusion from the third pixel point to the first diffusion direction at the diffusion speed corresponding to the third pixel point; based on the energy coefficient of the first pixel point, the energy coefficient of the third pixel point and the diffusion speed of the third pixel point in the first diffusion direction, the diffusion speed of the first pixel point in the first diffusion direction is calculated.

In some embodiments, the boundary identification module 203 can be specifically used to calculate the difference between the energy coefficient of the third pixel point and the energy coefficient of the first pixel point, and obtain the energy attenuation generated by diffusion from the third pixel point to the first pixel point; based on the energy attenuation, determine the loss of diffusion speed; calculate the difference between the diffusion speed of the third pixel point in the first diffusion direction and the loss, and obtain the diffusion speed of the first pixel point in the first diffusion direction.

In some embodiments, the boundary recognition module 203 can be specifically used to calculate the pixel gradient corresponding to the second pixel point based on the characteristic value of the first pixel point on the current waveform and the characteristic value of the second pixel point on the new waveform; and determine the energy coefficient of the second pixel point based on the pixel gradient corresponding to the second pixel point.

In some embodiments, the boundary recognition module 203 can be specifically used to determine the diffusion path from the starting point coordinates to each target pixel point during the boundary diffusion process, wherein the target pixel point is a pixel point whose energy coefficient is less than a preset threshold, and the diffusion path includes a plurality of node pixel points, and the node pixel point is at least one pixel point obtained in the process of diffusion from the starting point coordinates to the target pixel point; based on the energy coefficient of the node pixel point on each diffusion path, respectively determine The boundary pixel points located on each diffusion path; each determined boundary pixel point is connected to form the boundary contour of the target object.

In some embodiments, the boundary identification module 203 can be specifically used to calculate the absolute value of the difference in energy coefficients between any two adjacent node pixel points on the first diffusion path, where the first diffusion path is any diffusion path in each diffusion path; and the node pixel point farthest from the starting point coordinates among the two node pixel points corresponding to the largest absolute value of the difference is determined as a boundary pixel point.

In some embodiments, the ultrasonic image processing device may further include: a display module, configured to superimpose and display a waveform formed by each boundary diffusion in the currently displayed ultrasonic image during the boundary diffusion process.

The display module can also be used to generate a waveform diffusion animation based on the waveform formed by the boundary diffusion during the boundary diffusion process; and to overlay and play the waveform diffusion animation on the currently displayed ultrasound image.

In some embodiments, the ultrasound image processing apparatus may further include: a marking module, configured to mark a boundary contour in the currently displayed ultrasound image.

In some embodiments, the ultrasonic image processing device may further include: a prompt module for displaying a prompt message if the boundary contour of the target object is not detected within a preset time period, wherein the prompt message is used to prompt the user to reselect any point within the area where the target object is located as the starting point coordinate.

The ultrasonic image processing device provided in the embodiment of the present application and the ultrasonic image processing method provided in the above embodiment are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

The embodiment of the present application also provides an electronic device corresponding to the ultrasonic image processing method provided in the aforementioned embodiment, and the electronic device may be an ultrasonic device. Please refer to Figure 12, which shows a schematic diagram of an electronic device provided in some embodiments of the present application. As shown in Figure 12, the electronic device 30 may include: a processor 300, a memory 301, a bus 302 and a communication interface 303, and the processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the processor 300, and the processor 300 executes the ultrasonic image processing method provided in any of the aforementioned embodiments of the present application when running the computer program.

The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one physical port 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

The bus 302 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 301 is used to store programs, and the processor 300 executes the program after receiving an execution instruction. The ultrasonic image processing method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 300, or implemented by the processor 300.

The processor 300 may be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 300 or instructions in the form of software. The above processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

The processor 300 can implement or execute the methods, steps and logic diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed.

The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

The electronic device provided in the embodiment of the present application and the ultrasound image processing method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

An embodiment of the present application also provides a computer-readable storage medium corresponding to the ultrasonic image processing method provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the ultrasonic image processing method provided in any of the aforementioned embodiments.

It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

An embodiment of the present application also provides a computer program product corresponding to the ultrasound image processing method provided in the aforementioned embodiment, including a computer program, which is executed by a processor to implement the ultrasound image processing method provided in the aforementioned embodiments.

The computer-readable storage medium and computer program product provided in the above-mentioned embodiments of the present application are based on the same inventive concept as the ultrasound image processing method provided in the embodiments of the present application, and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

It should be noted:

The algorithm and display provided herein are not inherently related to any particular computer, virtual device or other equipment. Various general purpose devices can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the application is not directed to any specific programming language. It should be understood that the content of the application described herein can be realized by various programming languages, and the description of the specific language above is to disclose the best mode of implementation of the application.

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

Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than those expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all of the features of a single embodiment disclosed above. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself being herein incorporated by reference. All of them are considered as separate embodiments of this application.

Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and/or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

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

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

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

The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims (25)

1. An ultrasonic image processing method, characterized by comprising:

   detecting a selection instruction for instructing selection of a target object in the ultrasound image;

   Taking the coordinates indicated by the selection instruction as the starting point coordinates;

   Boundary diffusion recognition is performed around the starting point coordinates to identify the boundary contour of the target object from the ultrasound image.
2. The method according to claim 1, characterized in that the boundary diffusion recognition is performed around the starting point coordinates to identify the boundary contour of the target object from the ultrasonic image, comprising:

   Based on the starting point coordinates, determining an energy coefficient of a pixel point on a waveform formed by each boundary diffusion, wherein the energy coefficient is associated with a gradient of the pixel point through which the boundary diffusion passes;

   Based on the energy coefficient of each pixel point on the waveform, a boundary contour of the target object is identified from the ultrasound image.
3. The method according to claim 2, characterized in that the step of determining the energy coefficient of the pixel point on the waveform formed by each boundary diffusion based on the starting point coordinates comprises:

   Perform boundary diffusion in multiple diffusion directions from pixel points on the current waveform to obtain a new waveform; the current waveform is a waveform obtained by performing boundary diffusion at least once with the starting point coordinate as the center;

   Based on the pixel gradient between the first pixel point of the current waveform and the second pixel point of the new waveform, the energy coefficient of the second pixel point is calculated respectively, wherein the second pixel point is in the first diffusion direction of the first pixel point, the first pixel point is any pixel point on the current waveform, and the first diffusion direction is any diffusion direction of multiple diffusion directions corresponding to the first pixel point.
4. The method according to claim 3 is characterized in that the step of performing boundary diffusion in multiple diffusion directions from pixel points on the current waveform to obtain a new waveform comprises:

   Acquire a diffusion speed of the first pixel point in the first diffusion direction;

   Boundary diffusion is performed from the first pixel point to the first diffusion direction at the diffusion speed to obtain the second pixel point, and a plurality of the second pixel points form the new waveform.
5. The method according to claim 4, characterized in that obtaining the diffusion speed of the first pixel in the first diffusion direction comprises:

   Obtaining an energy coefficient of the first pixel point, an energy coefficient of a third pixel point, and a diffusion speed of the third pixel point in the first diffusion direction; the third pixel point is a pixel point in a previous waveform adjacent to the current waveform, and the first pixel point is obtained by boundary diffusion from the third pixel point to the first diffusion direction at a diffusion speed corresponding to the third pixel point;

   The diffusion speed of the first pixel in the first diffusion direction is calculated based on the energy coefficient of the first pixel, the energy coefficient of the third pixel, and the diffusion speed of the third pixel in the first diffusion direction.
6. The method according to claim 5, characterized in that the calculating the diffusion speed of the first pixel in the first diffusion direction based on the energy coefficient of the first pixel, the energy coefficient of the third pixel and the diffusion speed of the third pixel in the first diffusion direction comprises:

   Calculating a difference between an energy coefficient of the third pixel and an energy coefficient of the first pixel to obtain an energy attenuation caused by diffusion from the third pixel to the first pixel;

   Determining a loss in diffusion speed based on the energy attenuation;

   The difference between the diffusion speed of the third pixel point in the first diffusion direction and the loss amount is calculated to obtain the diffusion speed of the first pixel point in the first diffusion direction.
7. The method according to claim 3, characterized in that the step of calculating the energy coefficient of the second pixel point based on the pixel gradient between the first pixel point of the current waveform and the second pixel point of the new waveform comprises:

   Calculating a pixel gradient corresponding to a first pixel point on the current waveform and a second pixel point on the new waveform based on a characteristic value of the first pixel point on the current waveform and a characteristic value of the second pixel point on the new waveform;

   An energy coefficient of the second pixel is determined based on a pixel gradient corresponding to the second pixel.
8. The method according to any one of claims 2 to 7, characterized in that the step of identifying the boundary contour of the target object from the ultrasound image based on the energy coefficient of each pixel point on the waveform comprises:

   In the process of boundary diffusion, a diffusion path from the starting point coordinate to each target pixel point is determined respectively, wherein the target pixel point is a pixel point whose energy coefficient is less than a preset threshold, and the diffusion path includes a plurality of node pixel points, and the node pixel point is at least one pixel point obtained in the process of diffusion from the starting point coordinate to the target pixel point;

   Based on the energy coefficient of the node pixel points on each diffusion path, the boundary pixel points on each diffusion path are determined respectively;

   Each determined boundary pixel point is connected to form a boundary contour of the target object.
9. The method according to claim 8, characterized in that the step of determining the boundary pixel points located on each diffusion path based on the energy coefficient of the node pixel points on each diffusion path comprises:

   respectively calculating the absolute value of the difference between the energy coefficients of any two adjacent node pixels on a first diffusion path, where the first diffusion path is any diffusion path in each of the diffusion paths;

   The node pixel point farthest from the starting point coordinates among the two node pixel points corresponding to the largest absolute value of the difference is determined as the boundary pixel point.
10. The method according to any one of claims 1 to 7, characterized in that the method further comprises at least one of the following:

    During the boundary diffusion process, a waveform formed by each boundary diffusion is superimposed and displayed on the currently displayed ultrasound image;

    In the process of boundary diffusion, a waveform diffusion animation is generated based on the waveform formed by the boundary diffusion; and the waveform diffusion animation is superimposed and played on the currently displayed ultrasound image;

    After the boundary contour of the target object is identified, the boundary contour is marked in the currently displayed ultrasound image.
11. The method according to any one of claims 1 to 7, characterized in that the method further comprises:

    If the boundary contour of the target object is not detected within the preset time period, a prompt message is displayed, and the prompt message is used to prompt to reselect any point in the area where the target object is located as the starting point coordinate.
12. An ultrasonic image processing device, characterized by comprising:

    A detection module, configured to detect a selection instruction for instructing to select a target object in an ultrasound image;

    A starting point determination module, used to use the coordinates indicated by the selection instruction as starting point coordinates;

    The boundary recognition module is used to perform boundary diffusion recognition around the starting point coordinates as the center, so as to recognize the boundary contour of the target object from the ultrasonic image.
13. The device according to claim 12, characterized in that the boundary identification module is specifically used to:

    Based on the starting point coordinates, determining an energy coefficient of a pixel point on a waveform formed by each boundary diffusion, wherein the energy coefficient is associated with a gradient of the pixel point through which the boundary diffusion passes;

    Based on the energy coefficient of each pixel point on the waveform, a boundary contour of the target object is identified from the ultrasound image.
14. The device according to claim 13, characterized in that the boundary identification module is specifically used to:

    Perform boundary diffusion in multiple diffusion directions from pixel points on the current waveform to obtain a new waveform; the current waveform is a waveform obtained by performing boundary diffusion at least once with the starting point coordinate as the center;

    Based on the pixel gradient between the first pixel point of the current waveform and the second pixel point of the new waveform, the energy coefficient of the second pixel point is calculated respectively, wherein the second pixel point is in the first diffusion direction of the first pixel point, the first pixel point is any pixel point on the current waveform, and the first diffusion direction is any diffusion direction of multiple diffusion directions corresponding to the first pixel point.
15. The device according to claim 14, characterized in that the boundary identification module is specifically used to:

    Acquire a diffusion speed of the first pixel point in the first diffusion direction;

    Boundary diffusion is performed from the first pixel point to the first diffusion direction at the diffusion speed to obtain the second pixel point, and a plurality of the second pixel points form the new waveform.
16. The device according to claim 15, characterized in that the boundary identification module is specifically used to:

    Obtaining an energy coefficient of the first pixel point, an energy coefficient of a third pixel point, and a diffusion speed of the third pixel point in the first diffusion direction; the third pixel point is a pixel point in a previous waveform adjacent to the current waveform, and the first pixel point is obtained by boundary diffusion from the third pixel point to the first diffusion direction at a diffusion speed corresponding to the third pixel point;

    The diffusion speed of the first pixel in the first diffusion direction is calculated based on the energy coefficient of the first pixel, the energy coefficient of the third pixel, and the diffusion speed of the third pixel in the first diffusion direction.
17. The device according to claim 16, characterized in that the boundary identification module is specifically used to:

    Calculating a difference between an energy coefficient of the third pixel and an energy coefficient of the first pixel to obtain an energy attenuation caused by diffusion from the third pixel to the first pixel;

    Determining a loss in diffusion speed based on the energy attenuation;

    The difference between the diffusion speed of the third pixel point in the first diffusion direction and the loss amount is calculated to obtain the diffusion speed of the first pixel point in the first diffusion direction.
18. The device according to claim 14, characterized in that the boundary identification module is specifically used to:

    Calculating a pixel gradient corresponding to a first pixel point on the current waveform and a second pixel point on the new waveform based on a characteristic value of the first pixel point on the current waveform and a characteristic value of the second pixel point on the new waveform;

    An energy coefficient of the second pixel is determined based on a pixel gradient corresponding to the second pixel.
19. The device according to any one of claims 13 to 18, wherein the boundary recognition module is specifically used to:

    In the process of boundary diffusion, a diffusion path from the starting point coordinate to each target pixel point is determined respectively, wherein the target pixel point is a pixel point whose energy coefficient is less than a preset threshold, and the diffusion path includes a plurality of node pixel points, and the node pixel point is at least one pixel point obtained in the process of diffusion from the starting point coordinate to the target pixel point;

    Based on the energy coefficient of the node pixel points on each diffusion path, the boundary image on each diffusion path is determined respectively. Plain Points;

    Each determined boundary pixel point is connected to form a boundary contour of the target object.
20. The device according to claim 19, characterized in that the boundary identification module is specifically used to:

    respectively calculating the absolute value of the difference between the energy coefficients of any two adjacent node pixels on a first diffusion path, where the first diffusion path is any diffusion path in each of the diffusion paths;

    The node pixel point farthest from the starting point coordinates among the two node pixel points corresponding to the largest absolute value of the difference is determined as the boundary pixel point.
21. The device according to any one of claims 12 to 18, characterized in that the device further comprises at least one of the following: a display module and a marking module;

    A display module is used for superimposing and displaying a waveform formed by each boundary diffusion in the currently displayed ultrasound image during the boundary diffusion process; or

    A display module is used to generate a waveform diffusion animation based on the waveform formed by the boundary diffusion during the boundary diffusion process; and to overlay and play the waveform diffusion animation on the currently displayed ultrasound image;

    The marking module is used to mark the boundary contour in the currently displayed ultrasound image after identifying the boundary contour of the target object.
22. The device according to any one of claims 12-18 is characterized in that the device also includes: a prompt module, which is used to display a prompt message if the boundary contour of the target object is not detected within a preset time period, and the prompt message is used to prompt to reselect any point in the area where the target object is located as the starting point coordinate.
23. An electronic device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of claims 1 to 11 is implemented.
24. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.
25. A computer program product, comprising a computer program, characterized in that the computer program is executed by a processor to implement the method according to any one of claims 1 to 11.