Ultrasound image processing method, apparatus, device, and storage medium

Abstract

The application discloses an ultrasonic image processing method, device, equipment and storage medium, and the method comprises the steps of detecting a selection instruction for indicating selection of a target object in an ultrasonic image, taking a coordinate indicated by the selection instruction as a starting point coordinate; and performing boundary diffusion identification around the starting point coordinate to identify a boundary contour of the target object from the ultrasonic image. The application takes any point in the target object as the starting point coordinate, and performs boundary diffusion around the starting point coordinate to identify the boundary contour of the target object. The application automatically identifies the boundary of the target object, reduces human intervention, improves the efficiency and accuracy of boundary identification. The boundary contour is identified based on the change of energy coefficients between pixel points, and the change of the energy coefficients conforms to the change of texture features at the internal and boundary parts of the target object, so that the boundary contour can be accurately identified. The whole boundary diffusion process can be superimposed and displayed in the ultrasonic image, and the visualization of the whole boundary diffusion process is realized.

Description

Technical Field

[0001] This application relates to the field of medical imaging technology, specifically to an ultrasound image processing method, apparatus, device, and storage medium. Background Technology

[0002] Currently, when physicians use ultrasound equipment to scan patients, they need to measure the area, perimeter, and other applicable parameters of the target object, such as suspicious lesions or human tissue, for examination. Before measuring these parameters, the outline of the target object must first be determined.

[0003] In related techniques, physicians typically determine the outline of the target object based on experience and manually draw its boundary lines. However, subjectively determining the outline of the target object based on experience and manually drawing the boundary lines is cumbersome for physicians, resulting in low efficiency and accuracy in determining the outline of the target object. Summary of the Invention

[0004] To address the above issues, this application provides an ultrasound image processing method, apparatus, device, and storage medium that diffuses the boundary from the starting point coordinates within the target object, automatically identifying the boundary contour of the target object, reducing human intervention, and improving the efficiency and accuracy of boundary recognition.

[0005] In a first aspect, embodiments of this application provide an ultrasound image processing method, including:

[0006] A selection instruction was detected to indicate the selection of a target object in the ultrasound image.

[0007] Use the coordinates indicated by the selection command as the starting coordinates;

[0008] Boundary diffusion identification is performed outward from the starting point coordinates to identify the boundary contour of the target object from the ultrasound image.

[0009] An embodiment of the second aspect of this application provides an ultrasound image processing apparatus, comprising:

[0010] The detection module is used to detect selection instructions that indicate the selection of a target object in an ultrasound image;

[0011] The starting point determination module is used to take the coordinates indicated by the selection instruction as the starting point coordinates;

[0012] The boundary recognition module is used to perform boundary diffusion recognition from the starting point coordinates in all directions to identify the boundary contour of the target object from the ultrasound image.

[0013] An embodiment of the third aspect of this 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, it implements the method described in the first aspect above.

[0014] An embodiment of the fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0015] An embodiment of the fifth aspect of this application provides a computer program product including a computer program that is executed by a processor to implement the method described in the first aspect above.

[0016] The technical solutions provided in this application embodiment have at least the following technical effects or advantages:

[0017] This application identifies the boundary contour of the target object by using any point within the target object as the starting point coordinate and expanding outwards from the starting point coordinate to the surrounding boundaries. This achieves automatic boundary identification of the target object, reduces human intervention, and improves the efficiency and accuracy of boundary identification.

[0018] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0020] Figure 1 A schematic diagram of the structure of the ultrasound system provided in the embodiment of this application is shown;

[0021] Figure 2 A functional block diagram of the ultrasound system provided in an embodiment of this application is shown;

[0022] Figure 3 A flowchart of an ultrasound image processing method provided in an embodiment of this application is shown;

[0023] Figure 4 A schematic diagram showing the starting point coordinates within the target object provided in the embodiments of this application is shown;

[0024] Figure 5This illustration shows a schematic diagram of a waveform formed by boundary diffusion superimposed on an ultrasound image, as provided in an embodiment of this application.

[0025] Figure 6 It shows in Figure 5 Based on this, a schematic diagram of the energy coefficient on each waveform is drawn;

[0026] Figure 7 This illustration shows a schematic diagram of the first waveform W1 formed by the diffusion of the starting point coordinates to each adjacent pixel, as provided in an embodiment of this application.

[0027] Figure 8 This illustration shows a schematic diagram of the first waveform W1 formed by directly setting the starting point coordinates outward and diffusing, as provided in an embodiment of this application.

[0028] Figure 9 This illustration shows a schematic diagram of the outward diffusion from pixel B on the first waveform W1, provided in an embodiment of this application.

[0029] Figure 10 This diagram illustrates the diffusion path from pixel A to pixel E provided in an embodiment of this application.

[0030] Figure 11 A schematic diagram of the structure of an ultrasound image processing apparatus provided in an embodiment of this application is shown;

[0031] Figure 12 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0032] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0033] When physicians use ultrasound equipment to examine patients, they need to determine the boundary contours of target objects such as lesions or human tissues. In some techniques, physicians rely on experience to judge the contours of the target object and manually trace the corresponding boundary lines using external devices such as keyboards or mice connected to the ultrasound equipment. However, this operation requires a high level of personal experience from the physician, is cumbersome, and is highly subjective, resulting in low efficiency and accuracy in determining the boundary contours.

[0034] Based on this, embodiments of this application provide an ultrasound image processing method, apparatus, device, and storage medium, which will be described below with reference to the accompanying drawings.

[0035] Figure 1 A schematic diagram of the ultrasound system on which the improved ultrasound image processing method according to an embodiment of this application is based is shown. The ultrasound system includes a host 1, an ultrasound probe 2, an operating device 3, and a display device 4.

[0036] Depending on the application scenario, the physician can place the ultrasound probe 2 on the patient's skin or insert it into the patient's body. Ultrasound waves are emitted by the ultrasound probe 2 to the target detection area. The ultrasound probe 2 then receives the ultrasound echo formed by the ultrasound waves passing through the target detection area. This ultrasound echo reflects the tissue characteristics of the target detection area. Based on this ultrasound echo, ultrasound echo data of the target detection area is obtained and transmitted to the host computer 1.

[0037] The host 1 generates an ultrasound image of the target detection area based on the ultrasound echo data, and transmits the ultrasound image to the display device 4 for display. The host 1 also includes a storage device, in which the host 1 stores the ultrasound image.

[0038] The aforementioned operating device 3 includes external devices such as a mouse and keyboard connected to the host 1. When a physician uses an ultrasound probe to detect the target detection area of ​​the patient and displays the ultrasound image in real time on the display device 4, 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 the scanning and selects the ultrasound image with the best cross-section from the scanned ultrasound images so that the boundary contour of the target object can be automatically identified from the ultrasound image with the best cross-section using the ultrasound image processing method provided in this application embodiment.

[0039] Figure 2A functional block diagram of the aforementioned ultrasound system is shown. The host unit 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 image input unit receives ultrasound echo signals transmitted from the ultrasound probe 2, processes the received ultrasound echo signals through analog transmission and reception, beamforming, signal conversion, etc., and transmits them to the ultrasound image processing unit. The ultrasound image processing unit performs ISP (Image Signal Processing) operations on the ultrasound images transmitted from the image input unit, including but not limited to brightness transformation, sharpening, and contrast enhancement. The processed image is transmitted to the ultrasound intelligent processing unit, the video encoding unit, or a display device. The ultrasound intelligent processing unit performs intelligent analysis on the processed image, including but not limited to target recognition, detection, and segmentation based on deep learning. The processed image is transmitted to the ultrasound image processing unit or the video encoding unit. The processing methods of the processed image by the ultrasound intelligent processing unit include, but are not limited to, contour detection, brightness transformation, frame overlay, and scaling. The video encoding unit encodes and compresses the processed image by the ultrasound image processing unit or the ultrasound intelligent processing unit and transmits it to a storage device. The control unit controls various modules of the ultrasound system, and the control methods include, but are not limited to, interface operation, image processing, ultrasound measurement, and video encoding. The operation unit includes, but is not limited to, switches, buttons, and touch panels, used to receive external indication signals and output these signals to the control unit.

[0040] based on Figure 1 and 2 The ultrasound system shown in this application provides an ultrasound image processing method that uses a point located within the target object in the ultrasound image as a starting point to diffuse the boundary outwards. Based on the changes in pixel gradients during the boundary diffusion process, the method automatically identifies the boundary contour of the target object, thereby improving the efficiency and accuracy of boundary recognition.

[0041] See Figure 3 The method specifically includes the following steps:

[0042] Step 101: A selection command for indicating the selection of a target object in the ultrasound image is detected, and the coordinates indicated by the selection command are used as the starting coordinates.

[0043] During the process of a physician examining a patient's target area using an ultrasound probe, the ultrasound system's display device shows real-time ultrasound images of the target area. The physician observes the displayed ultrasound images and can stop scanning when the target object appears in the image, selecting the best cross-section of the target object from the currently scanned images. The target object can be a lesion or a specific tissue to be examined, such as the thyroid gland, liver, or kidney.

[0044] After the display device shows an ultrasound image containing the target object, the physician can operate the ultrasound system's control device, including a mouse or keyboard, to submit selection commands for choosing the target object in the ultrasound image. For example, the physician can click on the target object in the currently displayed ultrasound image using the mouse.

[0045] The control unit of the ultrasound system detects the selection command submitted by the operating device, determines the coordinates indicated by the command, and uses these coordinates as the starting point coordinates. These starting point coordinates are the coordinates of the location of the target object selected by the physician through the operating device within the ultrasound image. Specifically, an image coordinate system is established within the currently displayed ultrasound image. For example, the origin can be the coordinates of the top-left corner of the currently displayed ultrasound image, the x-axis can be the horizontal edge passing through the origin, and the y-axis can be the vertical edge passing through the origin. In practical applications, other vertices in the ultrasound image can also be used as the origin to establish a coordinate system.

[0046] After establishing a coordinate system within the ultrasound image, the coordinates of the location where the physician selected the target object are determined within that coordinate system, thus obtaining the starting coordinates. For example, the coordinates of the location where the physician clicked on the target object are determined within the ultrasound image's coordinate system, and these coordinates are used as the starting coordinates. The starting coordinates can be any point within the area where the target object is located. Figure 4 In the ultrasound image diagram shown, the non-shaded area is the target area where the target object is located, and the starting point coordinates can be any point within the target area.

[0047] While the accuracy of manually determining the boundary contour of a target object by a physician is poor, selecting any point within the target object's area by the physician is relatively simple and highly accurate. If the physician's selected starting point coordinates are located on the target object's boundary contour or outside the target object's area, the ultrasound image processing method provided in this application will be unable to identify the target object's boundary contour. In this case, if the target object's boundary contour is not detected within a preset time period, a prompt message can be displayed on the display device. This prompt message prompts the physician to reselect a point within the target object's area as the starting point coordinates. The preset time period can be 5 seconds, 10 seconds, 30 seconds, etc., and this application does not limit the specific value of the preset time period; it can be set according to needs in practical applications.

[0048] After determining the starting point coordinates in this step, the boundary contour of the target object is automatically identified through the following step 102.

[0049] Step 102: Perform boundary diffusion recognition from the starting point coordinates outwards to identify the boundary contour of the target object from the ultrasound image.

[0050] This application uses the starting coordinates as the center to diffuse outwards. During the diffusion process, the boundary pixels of the target object are identified based on the changes in pixel gradients along the same diffusion direction, thereby obtaining the boundary contour of the target object. Specifically, the boundary contour of the target object is identified through the following steps S1 and S2.

[0051] S1: Based on the starting coordinates, determine the energy coefficient of the pixel on the waveform formed by each boundary diffusion. This energy coefficient is related to the gradient of the pixel through which the boundary diffusion passes.

[0052] This application employs a boundary diffusion method to automatically identify the boundary contour of the target object. Multiple boundary diffusion operations are performed throughout the process, each resulting in a closed loop enclosing the starting point coordinates. Therefore, the entire process resembles a waveform spreading outwards from the starting point coordinates, similar to water ripples. Thus, in this embodiment, the closed loop generated during the boundary diffusion process is referred to as a waveform. This waveform can be a virtual waveform, not displayed in the currently shown ultrasound image. Alternatively, it can be displayed as a solid line in the currently shown ultrasound image.

[0053] After the starting point coordinates are detected in step 101, a waveform for boundary recognition is triggered and spreads outward from the starting point coordinates. During the diffusion process, boundary pixels are detected and marked until the boundary contour of the target object is recognized.

[0054] Since the boundary diffusion process is identical for each operation, this embodiment uses only one boundary diffusion operation as an example to illustrate the process in detail. Specifically, it uses the example of the current waveform diffusing outwards to form a new waveform. The current waveform can be a waveform obtained by at least one boundary diffusion operation centered on the starting coordinates. In this embodiment, the starting coordinates can be considered as the initial waveform, meaning the initial waveform has only one pixel corresponding to the starting coordinates. The current waveform can be either the initial waveform or any waveform obtained by at least one boundary diffusion operation outwards from the initial waveform.

[0055] First, the current waveform is diffused outwards in multiple directions from its pixels to obtain a new waveform. The diffusion direction refers to the direction from the current pixel on the waveform away from the starting coordinates; each pixel on the current waveform corresponds to multiple diffusion directions.

[0056] Boundary diffusion can be performed from a single pixel on the current waveform in each of its corresponding diffusion directions, reaching multiple pixels. Connecting all the pixels reached by each pixel on the current waveform yields a new waveform formed by performing one boundary diffusion from the current waveform.

[0057] Since the diffusion operation is identical for every pixel on the current waveform, and the diffusion operation is also identical for each pixel in each diffusion direction, we will take the process of boundary diffusion of pixels on the current waveform from the first pixel to the first diffusion direction as an example. The first pixel is any pixel on the current waveform, and the first diffusion direction is any one of the multiple diffusion directions corresponding to the first pixel.

[0058] Specifically, the diffusion velocity of the first pixel on the current waveform in the first diffusion direction is obtained. At this diffusion velocity, boundary diffusion occurs from the first pixel in the first diffusion direction to obtain a second pixel on the new waveform. Here, the diffusion velocity of the second pixel in the first diffusion direction of the first pixel can be understood as the diffusion step size, that is, the distance the boundary diffusion occurs from the first pixel in the first diffusion direction.

[0059] In one implementation, a preset diffusion speed can be pre-configured in the ultrasound system, and each pixel diffuses along its boundary in each diffusion direction at this preset speed. The preset diffusion speed can be a distance of 1 pixel, 3 pixels, 5 pixels, etc. This application does not limit the specific value of the preset diffusion speed; it can be set according to requirements in practical applications.

[0060] Using a preset diffusion rate for boundary diffusion reduces computational load and improves efficiency. A lower preset diffusion rate results in a denser waveform and higher accuracy in boundary contour recognition. Conversely, a higher preset diffusion rate allows for faster diffusion to the actual boundary of the target object, leading to quicker contour recognition and improved efficiency. By pre-configuring the diffusion rate, users can customize the diffusion speed based on specific needs.

[0061] In another implementation, instead of pre-configuring a preset diffusion rate, the diffusion rate of the first pixel in the first diffusion direction is calculated. Specifically, the energy coefficient of the first pixel, the energy coefficient of the third pixel, and the diffusion rate of the third pixel in the first diffusion direction are obtained. Here, the third pixel is a pixel in the previous waveform adjacent to the current waveform, and the first pixel is obtained by boundary diffusion from the third pixel towards the first diffusion direction at the diffusion rate corresponding to the third pixel. Based on the energy coefficients of the first and third pixels and the diffusion rate of the third pixel in the first diffusion direction, the diffusion rate of the first pixel in the first diffusion direction is calculated.

[0062] First, the difference between the energy coefficient of the third pixel and the energy coefficient of the first pixel is calculated to obtain the energy attenuation caused by diffusion from the third pixel to the first pixel. Then, based on this energy attenuation, the loss of diffusion velocity is determined, and the difference between the diffusion velocity of the third pixel in the first diffusion direction and this loss is calculated to obtain the diffusion velocity of the first pixel in the first diffusion direction.

[0063] In this embodiment, the energy coefficient is related to the pixel gradient and is a quantified representation of the gradient at the boundary. The gradient can be the difference in grayscale or brightness between pixels, representing the degree of difference between different pixels. A larger gradient indicates a greater difference between pixels, and a smaller gradient indicates a smaller difference. The difference between pixels within the target object's region is relatively small, while the difference between pixels at the target object's boundary is typically larger. Therefore, during the diffusion process from a point within the target object to the outer boundary, the gradient-based change can accurately identify the target object's boundary contour.

[0064] There is a certain mapping relationship between the energy coefficient and the gradient. This application embodiment sets a mapping function between the energy coefficient and the gradient. This mapping function can be a linear function or a nonlinear function, where nonlinear functions include, but are not limited to, fitting curves, sigmoid curves, and log curves. Assume S... n(i,j)_d Let be the gradient of the pixel at coordinate (i, j) along the d-th direction, then the energy coefficient e n(i,j) With gradient S n(i,j)_d The mapping relationship can be represented as: e n(i,j) =F(S) n(i,j)_d ), where F is the mapping function.

[0065] The first pixel is obtained by boundary diffusion of the third pixel towards the first diffusion direction. Therefore, the energy coefficient of the first pixel is calculated by substituting the gradient between the third pixel and the first pixel into the mapping function. The third pixel is obtained by boundary diffusion of the fourth pixel in the previous waveform adjacent to the third pixel towards the first diffusion direction. Therefore, the energy coefficient of the third pixel is calculated by substituting the gradient between the fourth pixel and the third pixel into the mapping function.

[0066] With V n(i,j)_d To identify the diffusion velocity of the pixel with coordinates (i, j) on the nth waveform in the d-th direction, the formula for calculating the diffusion velocity is as follows:

[0067] V n(i,j)_d =V n-1(k,z)_d -a*(e n-1(k,z) -e n(i,j) )

[0068] Among them, V n-1(k,z)_d Let V be the diffusion velocity of the pixel with coordinates (k, z) on the (n-1)th waveform in the d-th direction. n-1(k,z)_d The diffusion starts from the pixel at coordinates (k, z) on the (n-1)th waveform and proceeds in the d-th direction, eventually reaching the pixel at coordinates (i, j) on the nth waveform. n(i,j) Let e ​​be the energy coefficient of the pixel at coordinate (i, j) on the nth waveform. n-1(k,z) Let be the energy coefficient of the pixel at coordinates (k, z) on the (n-1)th waveform. 'a' is a preset coefficient. If a = 0, the boundary diffusion proceeds at a uniform rate, and each boundary diffusion produces a circular waveform. If a is not equal to 0, the diffusion speed of each pixel will differ in different diffusion directions. The diffusion speed is related to the degree of energy coefficient decay. Boundary diffusion based on this calculated diffusion speed more closely resembles the actual gradient changes between pixels in the target object's region, thus improving the accuracy of boundary recognition.

[0069] To calculate the diffusion velocity of the first pixel in the first diffusion direction, the energy coefficient of the first pixel, the energy coefficient of the third pixel, and the diffusion velocity of the third pixel in the first diffusion direction are substituted into the above calculation formula, and the diffusion velocity of the first pixel in the first diffusion direction can be calculated quickly.

[0070] After obtaining the aforementioned diffusion velocity corresponding to the first pixel, boundary diffusion is performed from the first pixel on the current waveform towards the first diffusion direction at this diffusion velocity, which can diffuse to the second pixel. For each other diffusion direction corresponding to the first pixel, the diffusion velocity of the first pixel in each other diffusion direction is obtained in the above manner, and boundary diffusion is performed respectively to obtain multiple pixels corresponding to the first pixel after diffusion.

[0071] Similarly, for each other pixel on the current waveform, the same operation as for the first pixel is performed, and boundary diffusion is applied to each of the other pixels on the current waveform to obtain multiple pixels corresponding to each pixel after boundary diffusion. Connecting all the pixels obtained by boundary diffusion of the current waveform yields a new waveform.

[0072] Then, based on the pixel gradient between the 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.

[0073] Specifically, based on the feature values ​​of the first pixel on the current waveform and the feature values ​​of the second pixel on the new waveform, the pixel gradient corresponding to the second pixel is calculated. The feature values ​​can be the grayscale or brightness of the pixel, etc. The pixel gradient corresponding to the second pixel can be the grayscale difference or brightness difference between the first and second pixels, etc.

[0074] The energy coefficient of the second pixel is determined based on the pixel gradient corresponding to the second pixel. Specifically, the pixel gradient of 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.

[0075] For each other pixel on the new waveform, the energy coefficient of each other pixel on the new waveform is determined by the same operation as that of the second pixel.

[0076] S2: Based on the energy coefficient of each pixel on the waveform, identify the boundary contour of the target object from the ultrasound image.

[0077] In ultrasound images, pixels at different locations exhibit varying gradients. Pixels show smaller gradients in areas with minimal texture variation and larger gradients in areas with significant texture variation. Texture variations are more pronounced at the boundaries of the target object, resulting in larger pixel gradients. During boundary diffusion, energy attenuation occurs as the waveform spreads from the inside out, meaning the energy coefficient decreases. The energy attenuation is greater when the waveform diffuses from areas of low gradient to areas of high gradient, and the energy coefficient decreases even more as it diffuses towards areas with even higher gradients. Once the energy coefficient attenuates to a certain level, it indicates that the waveform has crossed the target object's boundary and the boundary can be identified; therefore, further outward diffusion is unnecessary.

[0078] In this embodiment, a preset threshold is pre-configured to determine whether further diffusion is unnecessary. Diffusion stops when the energy coefficient decays to this preset threshold. Specifically, during boundary diffusion, after determining the energy coefficient of a pixel on a waveform, it is determined whether the energy coefficient of that pixel is less than the preset threshold. If so, boundary diffusion is no longer performed on that pixel. If not, boundary diffusion continues on that pixel in the manner described above.

[0079] In this embodiment, pixels with energy coefficients less than a preset threshold are referred to as target pixels. For each target pixel, a diffusion path is determined from the starting coordinates to each target pixel. The diffusion path includes multiple node pixels, each of which is at least one pixel obtained during the diffusion process from the starting coordinates to the target pixel.

[0080] Based on the energy coefficients of the nodes on each diffusion path, the boundary pixels located on each diffusion path are determined. Taking the first diffusion path as an example, the process of determining the boundary pixels is illustrated. The first diffusion path is any diffusion path within the first diffusion path. Specifically, the absolute value of the difference between the energy coefficients of any two adjacent nodes on the first diffusion path is calculated, and the largest absolute value of the difference is determined from the calculated values. The node farthest from the starting point coordinates among the two nodes corresponding to the largest absolute value of the difference is determined as the boundary pixel.

[0081] For each of the other diffusion paths, the boundary pixels on each path are determined in the same way. Then, each determined boundary pixel is connected to form a line, thus obtaining the boundary contour of the target object.

[0082] Since the waveform's energy coefficient drops significantly when crossing the target object's boundary, if the energy coefficients of two adjacent pixels in the diffusion path differ greatly, these two pixels are likely located on opposite sides of the boundary. By calculating the absolute value of the difference in energy coefficients between any two adjacent pixels in the diffusion path, the two pixels corresponding to the largest absolute difference are identified. These two pixels are the most likely to be located on opposite sides of the boundary. The pixel farthest from the starting point coordinates among these two is designated as the boundary pixel. This ensures that the determined boundary pixel closely approximates the true boundary of the target object. Furthermore, by selecting the pixel farthest from the starting point coordinates as the boundary pixel, it is likely to be on or outside the true boundary of the target object, with a very low probability of being inside the true boundary. This ensures that the final determined boundary contour of the target object encompasses the entire area of ​​the target object.

[0083] This application embodiment uses any point within the target object's region as the center to expand outwards along the boundary. During the diffusion process, the boundary contour of the target object is identified based on the changes in the energy coefficients between pixels. This achieves automatic identification of the target object's boundary contour, eliminating the need for physicians to subjectively determine the boundary, reducing manual operation, and improving the efficiency and accuracy of identifying the target object's boundary in ultrasound examinations.

[0084] In this embodiment, after identifying the boundary contour of the target object using the above method, the boundary contour of the target object can be marked on the currently displayed ultrasound image. Specifically, the boundary contour can be marked using a preset color or by bolding, such as red or yellow. By marking the boundary contour of the target object, physicians can more intuitively see the size and shape of the target object, which helps them to perform subsequent size measurements and improves the accuracy and reference value of ultrasound examination.

[0085] After identifying the boundary contour of the target object using the above method, the application indicators of the target object are measured based on the identified boundary contour. These application indicators may include the perimeter, area, aspect ratio, etc., of the target object. This embodiment of the application automatically and accurately identifies the boundary contour of the target object, which helps improve the accuracy of application indicator measurements and enhances the clinical reference value of the measured application indicators.

[0086] In some embodiments of this application, during the boundary diffusion process, the waveforms formed by each boundary diffusion can also be superimposed on the currently displayed ultrasound image. For example... Figure 5 The schematic diagram of the ultrasound image shows the starting point coordinates, the boundary outline of the target object is marked in bold, and each waveform generated during the boundary diffusion process is superimposed.

[0087] Figure 6 The schematic diagram of the ultrasound image shown is in Figure 5 Based on the ultrasound image shown, the energy coefficients at multiple points on each waveform are also marked, enabling physicians to intuitively see the boundary contour recognition process based on the ultrasound image, making the entire recognition process visual and interpretable.

[0088] In other embodiments of this application, during the boundary diffusion process, a waveform diffusion animation is generated based on the waveform formed by the boundary diffusion. This waveform diffusion animation can diffuse outwards from the starting coordinates at a certain display frequency, like ripples on water. The waveform diffusion animation is then overlaid on the currently displayed ultrasound image. For example, the previous waveform can disappear after it is displayed, and the next waveform can be displayed.

[0089] By using waveform diffusion animation to demonstrate the process of boundary diffusion identification of target object boundaries in the currently displayed ultrasound image, the entire identification process can be made more intuitive, vivid and interesting.

[0090] In this embodiment, the selected location of the target object is used as the starting coordinate, and the boundary diffusion proceeds outward from this starting coordinate. During the boundary diffusion process, the boundary contour of the target object is identified. This achieves automatic identification of the target object's boundary, significantly reducing human intervention throughout the process, improving the efficiency of boundary identification, and ensuring high accuracy. Furthermore, during the boundary diffusion process, the boundary contour of the target object is identified based on the change in energy coefficients between pixels. The change in energy coefficients corresponds to the change in image texture features within the target object and at its boundary, thus accurately identifying the target object's boundary contour. Furthermore, the entire boundary diffusion process can be overlaid and displayed on the currently displayed ultrasound image, achieving visualization of the entire boundary diffusion process.

[0091] To facilitate understanding of the ultrasound image processing process provided in this application embodiment, the specific process of identifying the boundary contour of a target object is illustrated below using an example. Taking a cyst as an example, suppose that during an ultrasound examination of a patient's abdomen, a physician discovers a cyst in the real-time ultrasound image displayed on the ultrasound device's screen. The physician can then click on any location within the area where the cyst is located using a mouse. The ultrasound device detects the click command input by the mouse and determines the coordinates of the clicked location in the ultrasound image, using these coordinates as the starting point coordinate A. After detecting the starting point coordinate A, the ultrasound device initiates a boundary recognition waveform, expanding outwards from the starting point coordinate A as the center.

[0092] In one example, assuming the diffusion speed is a distance of 1 pixel, then the diffusion from the starting coordinate A outwards in all directions is a distance of 1 pixel, such as... Figure 7 As shown, the diffusion extends from the starting point A to eight adjacent pixels. The closed-loop waveform formed by these eight pixels is the first waveform W1 formed during the boundary diffusion process. Based on the gradient between the starting point A and its adjacent pixels, the energy coefficient of each pixel diffused to is calculated.

[0093] In another example, the first waveform W1 can be set directly. The shape of the first waveform W1 can be circular, and the distance between each pixel on W1 and the starting coordinate A is v0. That is, the diffusion speed from the starting coordinate A to the waveform W1 in each diffusion direction is v0. The energy coefficient of each pixel on the waveform W1 can be set to 1. Figure 8 A schematic diagram showing the direct setting of the first waveform W1 is shown.

[0094] After obtaining the first waveform W1 according to any of the above examples, for each pixel on waveform W1, it is determined whether there is a target pixel with an energy coefficient less than a preset threshold. If there is a target pixel with an energy coefficient less than the preset threshold, boundary diffusion is not performed on that target pixel. For pixels with an energy coefficient greater than or equal to the preset threshold, boundary diffusion is performed on these pixels again.

[0095] like Figure 9 As shown, pixel B on waveform W1 undergoes boundary diffusion in multiple diffusion directions. Taking diffusion from pixel B to pixel C as an example, the diffusion velocity of pixel B is first calculated based on the energy coefficient of pixel B, the diffusion velocity of pixel A, and its energy coefficient. Diffusion then proceeds from pixel B to pixel C at the diffusion velocity of pixel B.

[0096] The diffusion proceeds outwards in concentric circles as described above, stopping at the target pixel E where the energy coefficient is less than a preset threshold. This determines the diffusion path from the starting point A to the target pixel E. Figure 10 As shown, the diffusion path includes five nodes: A, B, C, D, and E. The absolute values ​​of the energy coefficient differences between pixels A and B, B and C, C and D, and D and E are calculated. The largest absolute value is determined from these four calculated differences. Assuming that the absolute value of the energy coefficient difference between pixels D and E is the largest, pixel E is then identified as a boundary pixel of the cyst.

[0097] For each target pixel with an energy coefficient less than a preset threshold, the above method is used to process it to determine all boundary pixels of the cyst. The closed loop formed by connecting all boundary pixels is the boundary contour of the cyst.

[0098] Using a point within the cyst as the starting point, the boundary expands outwards from this point. During this expansion, the cyst's boundary contour is automatically identified, requiring minimal human intervention and improving efficiency and accuracy. Furthermore, the cyst's boundary contour is identified based on changes in the energy coefficients between pixels. These changes in energy coefficients correspond to variations in texture features within and at the cyst's boundaries, thus enabling accurate identification of the cyst's boundary contour.

[0099] See Figure 11 This application also provides an ultrasound image processing apparatus for performing the ultrasound image processing method described in the above embodiments. The apparatus includes:

[0100] Detection module 201 is used to detect a selection command that indicates the selection of a target object in an ultrasound image;

[0101] The starting point determination module 202 is used to take the coordinates indicated by the selection command as the starting point coordinates;

[0102] The boundary recognition module 203 is used to perform boundary diffusion recognition from the starting point coordinates to identify the boundary contour of the target object from the ultrasound image.

[0103] The boundary recognition module 203 is used to determine the energy coefficient of the pixel points on the waveform formed by each boundary diffusion based on the starting point coordinates. 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.

[0104] The boundary recognition module 203 is used to perform boundary diffusion from pixels on the current waveform in multiple diffusion directions to obtain a new waveform; the current waveform is obtained by performing at least one boundary diffusion with the starting coordinates as the center; based on the pixel gradient between the first pixel of the current waveform and the second pixel of the new waveform, the energy coefficient of the second pixel is calculated. The second pixel is located in the first diffusion direction of the first pixel, where the first pixel is any pixel on the current waveform, and the first diffusion direction is any one of the multiple diffusion directions corresponding to the first pixel.

[0105] The boundary recognition module 203 is used to obtain the diffusion speed of the first pixel in the first diffusion direction; to diffuse the boundary from the first pixel in the first diffusion direction at the diffusion speed to obtain the second pixel, and multiple second pixels form the new waveform.

[0106] The boundary recognition module 203 is used to obtain 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; the third pixel is a pixel in the previous waveform adjacent to the current waveform, and the first pixel is obtained by boundary diffusion from the third pixel to the first diffusion direction with the diffusion speed corresponding to the third pixel; 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, the diffusion speed of the first pixel in the first diffusion direction is calculated.

[0107] The boundary recognition module 203 is used to 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; based on the energy attenuation, the loss of diffusion velocity is determined; and the difference between the diffusion velocity of the third pixel in the first diffusion direction and the loss is calculated to obtain the diffusion velocity of the first pixel in the first diffusion direction.

[0108] The boundary recognition module 203 is used to calculate the pixel gradient corresponding to the second pixel point based on the feature value of the first pixel point on the current waveform and the feature value of the second pixel point on the new waveform; and to determine the energy coefficient of the second pixel point based on the pixel gradient corresponding to the second pixel point.

[0109] The boundary recognition module 203 is used to determine the diffusion path from the starting coordinates to each target pixel during the boundary diffusion process. The target pixel is a pixel with an energy coefficient less than a preset threshold. The diffusion path includes multiple node pixels, and each node pixel is at least one pixel obtained during the diffusion process from the starting coordinates to the target pixel. Based on the energy coefficient of the node pixels on each diffusion path, the boundary pixels located on each diffusion path are determined. The determined boundary pixels are then connected to form the boundary contour of the target object.

[0110] The boundary recognition module 203 is used to calculate the absolute value of the difference between the energy coefficients of any two adjacent node pixels on the first diffusion path, where the first diffusion path is any diffusion path in each diffusion path; and to determine the node pixel that is farthest from the starting point coordinates among the two node pixels corresponding to the largest absolute value of the difference as the boundary pixel.

[0111] The device also includes a display module for superimposing the waveform formed by each boundary diffusion onto the currently displayed ultrasound image during the boundary diffusion process.

[0112] This display module is also used to generate a waveform diffusion animation based on the waveform formed by the boundary diffusion during the boundary diffusion process; and to overlay the waveform diffusion animation onto the currently displayed ultrasound image.

[0113] The device also includes a labeling module for labeling boundary contours in the currently displayed ultrasound image.

[0114] The device also includes a prompting module, which displays a prompt message if the boundary contour of the target object is not detected within a preset time period. The prompt message prompts the user to reselect any point within the area where the target object is located as the starting point coordinates.

[0115] The ultrasonic image processing apparatus provided in this application embodiment 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 used, operated or implemented.

[0116] This application also provides an electronic device corresponding to the ultrasound image processing method provided in the foregoing embodiments. This electronic device can be an ultrasound device. Please refer to... Figure 12 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 12 As shown, the electronic device 30 may include: a processor 300, a memory 301, a bus 302, and a communication interface 303. 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 run on the processor 300. When the processor 300 runs the computer program, it executes the ultrasound image processing method provided in any of the foregoing embodiments of this application.

[0117] The memory 301 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one physical port 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0118] Bus 302 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs. After receiving an execution instruction, the processor 300 executes the program. The ultrasound image processing method disclosed in any of the foregoing embodiments of this application can be applied to the processor 300, or implemented by the processor 300.

[0119] The processor 300 may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 300 or by instructions in software form. The processor 300 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 301. The processor 300 reads the information in memory 301 and, in conjunction with its hardware, completes the steps of the above method.

[0120] The electronic device provided in this application embodiment and the ultrasonic image processing method provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate or implement.

[0121] This application also provides a computer-readable storage medium corresponding to the ultrasound image processing method provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon, and the computer program, when run by a processor, executes the ultrasound image processing method provided in any of the foregoing embodiments.

[0122] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change 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 and magnetic storage media, which will not be elaborated here.

[0123] This application also provides a computer program product corresponding to the ultrasound image processing method provided in the foregoing embodiments, including a computer program that is executed by a processor to implement the ultrasound image processing method provided in the above embodiments.

[0124] The computer-readable storage medium and computer program product provided in the above embodiments of this application are based on the same inventive concept as the ultrasound image processing method provided in the embodiments of this application, and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0125] It should be noted that:

[0126] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings herein. The required structure for constructing such devices is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0127] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0128] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0129] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0130] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0131] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation apparatus according to embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0132] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0133] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An ultrasound image processing method, characterized by, The method comprises: detecting a selection instruction for indicating selection of a target object in an ultrasound image; taking a coordinate indicated by the selection instruction as a starting coordinate; performing boundary diffusion around the starting coordinate to identify a boundary contour of the target object from the ultrasound image; the boundary diffusion comprises generating a new wave form from a current wave form; wherein a second pixel point on the new wave form is obtained by performing boundary diffusion from a first pixel point on the current wave form to a first diffusion direction at a diffusion speed corresponding to the first pixel point; the first pixel point is obtained by performing boundary diffusion from a third pixel point in a wave form adjacent to the current wave form to the first diffusion direction at a diffusion speed corresponding to the third pixel point; and the diffusion speed corresponding to the first pixel point is related to an attenuation degree of an energy coefficient of the first pixel point and the third pixel point.

2. The method of claim 1, wherein, performing boundary diffusion around the starting coordinate to identify a boundary contour of the target object from the ultrasound image, comprises: determining an energy coefficient of a pixel point on a wave form formed by each boundary diffusion based on the starting coordinate, the energy coefficient being associated with a gradient of a pixel point passed by the boundary diffusion; identifying the boundary contour of the target object from the ultrasound image based on the energy coefficient of each pixel point on the wave form.

3. The method of claim 2, wherein, the determining of the energy coefficient of the pixel point on the wave form formed by each boundary diffusion based on the starting coordinate, comprises: performing boundary diffusion from a pixel point on a current wave form to multiple diffusion directions to obtain a new wave form; the current wave form is a wave form obtained by performing at least one boundary diffusion with the starting coordinate as the center; calculating an energy coefficient of a second pixel point based on a pixel gradient between a first pixel point on the current wave form and the second pixel point, wherein the first pixel point is any pixel point on the current wave form, and the first diffusion direction is any diffusion direction corresponding to the first pixel point.

4. The method of claim 3, wherein, the performing of the boundary diffusion from the pixel point on the current wave form to the multiple diffusion directions to obtain the new wave form, comprises: obtaining a diffusion speed of the first pixel point in the first diffusion direction; performing boundary diffusion from the first pixel point to the first diffusion direction at the diffusion speed corresponding to the first pixel point to obtain the second pixel point, and multiple second pixel points form the new wave form.

5. The method of claim 4, wherein, the obtaining of the diffusion speed of the first pixel point 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; calculating the diffusion speed of the first pixel point in the first diffusion direction 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.

6. The method of claim 5, wherein, The energy coefficient of the third pixel point and the energy coefficient of the first pixel point are calculated, and an energy attenuation amount generated from the third pixel point to the first pixel point is obtained. The loss amount of the diffusion speed is determined based on the energy attenuation amount. The diffusion speed of the first pixel point in the first diffusion direction is obtained by calculating the difference between the diffusion speed of the third pixel point in the first diffusion direction and the loss amount. The energy coefficient of the second pixel point is calculated based on the pixel gradient between the first pixel point on the current waveform and the second pixel point on the new waveform.

7. The method of claim 3, wherein, The pixel gradient corresponding to the second pixel point is calculated based on the eigenvalue of the first pixel point on the current waveform and the eigenvalue of the second pixel point on the new waveform. The energy coefficient of the second pixel point is determined based on the pixel gradient corresponding to the second pixel point. The boundary contour of the target object is identified from the ultrasound image based on the energy coefficient of each pixel point on each waveform.

8. The method according to any one of claims 2 to 7, characterized in that, In the boundary diffusion process, a diffusion path from the starting point coordinate to each target pixel point is determined, wherein the target pixel point is a pixel point with an energy coefficient less than a preset threshold, and the diffusion path includes a plurality of node pixel points, which are at least one pixel point obtained during the diffusion from the starting point coordinate to the target pixel point. Boundary pixel points located on each diffusion path are determined based on the energy coefficient of the node pixel points on each diffusion path. Each boundary pixel point is connected to form the boundary contour of the target object. The boundary pixel points located on each diffusion path are determined based on the energy coefficient of the node pixel points on each diffusion path.

9. The method of claim 8, wherein, The absolute value of the difference between the energy coefficients of any two adjacent node pixel points on the first diffusion path is calculated, and the first diffusion path is any diffusion path in the each diffusion path. The node pixel point farthest from the starting point coordinate among the two node pixel points corresponding to the maximum difference absolute value is determined as the boundary pixel point. The method further includes at least one of the following:

10. The method according to any one of claims 1 to 7, characterized in that, During the boundary diffusion process, the waveforms formed by each boundary diffusion are superimposed and displayed in the currently displayed ultrasound image. During the boundary diffusion process, a waveform diffusion animation is generated based on the waveforms formed by the boundary diffusion, and the waveform diffusion animation is 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. The method further includes:

11. The method according to any one of claims 1 to 7, characterized in that, If the boundary contour of the target object is not detected within a preset time period, a prompt information is displayed, and the prompt information is used to prompt to reselect any point in the region where the target object is located as the starting point coordinate. The method further includes:

12. An ultrasound image processing apparatus, characterized by, The detection module is configured to detect a selection instruction for indicating selection of a target object in an ultrasound image. ​ A starting point determination module is configured to determine the coordinate indicated by the selection instruction as a starting point coordinate; A boundary identification module is configured to perform boundary diffusion around the starting point coordinate to identify a boundary contour of the target object from the ultrasound image. The boundary diffusion includes generating a new wave form from a current wave form; wherein a second pixel point on the new wave form is obtained by performing boundary diffusion from a first pixel point on the current wave form to a first diffusion direction at a diffusion speed corresponding to the first pixel point; the first pixel point is obtained by performing boundary diffusion from a third pixel point in a wave form adjacent to the current wave form to the first diffusion direction at a diffusion speed corresponding to the third pixel point; and the diffusion speed corresponding to the first pixel point is related to an attenuation degree of an energy coefficient of the first pixel point and the third pixel point.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1-11.

14. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-11.

15. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-11.

Images