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

Abstract

The application discloses an ultrasonic image processing method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: obtaining an initial target ultrasonic contrast image from an ultrasonic video stream, and determining initial lesion region information of the initial target ultrasonic contrast image; obtaining target lesion region information of each ultrasonic contrast video frame in the ultrasonic video stream based on the initial lesion region information and by using a lesion tracking model; and generating a target lesion time intensity curve corresponding to the ultrasonic video stream based on the target lesion region information of each ultrasonic contrast video frame in the ultrasonic video stream. The target lesion time intensity curve generated by the method is more accurate.

Description

Technical Field

[0001] This application relates to the field of ultrasound technology, and in particular to an ultrasound image processing method, an ultrasound image processing device, an electronic device, and a computer-readable storage medium. Background Technology

[0002] Initially used in cardiac imaging, contrast-enhanced ultrasound has, with technological advancements, achieved sensitivity and specificity comparable to CT (Computed Tomography) and MRI (Magnetic Resonance Imaging), and is now widely used in abdominal imaging. The application of contrast-enhanced ultrasound in abdominal examinations is significant. The Time Intensity Curve (TIC) refers to the change in contrast agent intensity over time after it enters an organ, and is an indispensable reference indicator for analyzing contrast results. Clinically, quantitative TIC analysis comparing lesions and normal tissues can provide specific information about suspicious tissues, assisting doctors in diagnosis. Currently, ideally, after defining the ROI (region of interest) to locate the lesion, the ultrasound probe and patient should remain stationary. However, a single contrast-enhanced examination typically takes 4-6 minutes, making ideal stillness impossible, which reduces the accuracy of the TIC curve. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide an ultrasound image processing method, an ultrasound image processing device, an electronic device, and a computer-readable storage medium, which generates a more accurate time-intensity curve of the target lesion.

[0004] To address the aforementioned technical problems, this application provides an ultrasound image processing method, comprising:

[0005] An initial target ultrasound contrast image is acquired from the ultrasound video stream, and the initial lesion region information of the initial target ultrasound contrast image is determined.

[0006] Based on the initial lesion region information, the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream is obtained using the lesion tracking model.

[0007] Based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream, a time-intensity curve of the target lesion corresponding to the ultrasound video stream is generated.

[0008] Optionally, obtaining the target lesion region information for each ultrasound contrast-enhanced video frame in the ultrasound video stream based on the initial lesion region information and using a lesion tracking model includes:

[0009] A first target ultrasound contrast image and a second target ultrasound contrast image are obtained from each of the ultrasound contrast video frames in the ultrasound video stream; wherein, the first target ultrasound contrast image includes the initial target ultrasound contrast image;

[0010] Obtain information about the first lesion region corresponding to the first target ultrasound contrast image; wherein, the information about the first lesion region is obtained based on the initial lesion region information;

[0011] Based on the first lesion area information, and using the lesion tracking model, the second lesion area information corresponding to the second target ultrasound image is obtained;

[0012] The target lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream is determined by using the first lesion region information and the second lesion region information.

[0013] Optionally, acquiring the first target ultrasound contrast image and the second target ultrasound contrast image from each of the ultrasound contrast video frames in the ultrasound video stream includes:

[0014] Get the preset time interval;

[0015] Based on the preset time interval, the first target ultrasound contrast image and the second target ultrasound contrast image are extracted from the ultrasound video stream in chronological order.

[0016] Optionally, determining the target lesion region information corresponding to each ultrasound contrast-enhanced video frame in the ultrasound video stream using the first lesion region information and the second lesion region information includes:

[0017] The first lesion region information of the first target ultrasound contrast image is determined as the target lesion region information corresponding to each ultrasound contrast video frame between the first target ultrasound contrast image and the second target ultrasound contrast image.

[0018] Optionally, obtaining the target lesion region information for each ultrasound contrast-enhanced video frame in the ultrasound video stream based on the initial lesion region information and using a lesion tracking model includes:

[0019] All the ultrasound contrast imaging video frames in the ultrasound video stream are input into the lesion tracking model to determine the target lesion region information of each ultrasound contrast imaging video frame in the ultrasound video stream.

[0020] Optionally, generating the time-intensity curve of the target lesion corresponding to the ultrasound video stream based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream includes:

[0021] Based on the target lesion area information, the average pixel value of the lesion area corresponding to the ultrasound contrast imaging video frame is obtained using the ultrasound contrast imaging video frame.

[0022] The average pixel value of the lesion region is used to generate the time intensity curve of the target lesion corresponding to the ultrasound video stream.

[0023] Optionally, obtaining the average pixel value of the lesion region corresponding to the ultrasound contrast-enhanced video frame based on the target lesion region information includes:

[0024] Based on the target lesion area information, the location of the target lesion area is determined on the ultrasound contrast video frame; using the pixel value corresponding to each lesion pixel in the target lesion area and the number of lesion pixels, the average pixel value of the lesion area is generated.

[0025] Optionally, generating the target lesion time-intensity curve corresponding to the ultrasound video stream using the pixel mean of the lesion region includes:

[0026] Determine the curve points corresponding to each of the ultrasound contrast imaging video frames; wherein, the curve points are plotted with the sampling time of the ultrasound contrast imaging video frame as the abscissa and the average pixel value of the lesion region as the ordinate;

[0027] The time-intensity curve of the target lesion is obtained based on the curve points.

[0028] Optionally, obtaining the time-intensity curve of the target lesion based on the curve points includes:

[0029] Connecting the points on the curve yields the initial lesion time-intensity curve;

[0030] The initial lesion time-intensity curve is subjected to curve fitting to obtain the target lesion time-intensity curve.

[0031] Optionally, it also includes:

[0032] Based on the initial lesion area information, the initial non-lesion area information corresponding to the initial target ultrasound contrast image is generated;

[0033] Based on the initial non-lesion area information, target non-lesion area information corresponding to each of the ultrasound contrast video frames is generated;

[0034] Based on the target non-lesion area information, the corresponding non-lesion area pixel mean is generated using the ultrasound contrast video frame;

[0035] The baseline time-intensity curve corresponding to the ultrasound video stream is generated using the pixel mean of the non-lesion area.

[0036] Optionally, it also includes:

[0037] Obtain preset detection data corresponding to the time-intensity curve of the target lesion and the reference time-intensity curve, respectively;

[0038] A visual analysis report is generated using the preset detection data, the time-intensity curve of the target lesion, and the baseline time-intensity curve.

[0039] Optionally, generating a visualization analysis report using the preset detection data, the target lesion time-intensity curve, and the baseline time-intensity curve includes:

[0040] A difference time-intensity curve is generated using the target lesion time-intensity curve and the baseline time-intensity curve;

[0041] Anomaly detection data is generated based on the difference time-intensity curve;

[0042] A visual analysis report is generated using the abnormal detection data, the preset detection data, the difference time-intensity curve, the target lesion time-intensity curve, and the baseline time-intensity curve.

[0043] Optionally, it also includes:

[0044] Generate the positional relationship information between the initial non-lesion area information and the initial lesion area information;

[0045] The step of generating target non-lesion region information corresponding to each of the ultrasound contrast-enhanced video frames based on the initial non-lesion region information includes:

[0046] Based on the location relationship information, the target non-lesion area information corresponding to each of the ultrasound modeling video frames is generated using the target lesion area information.

[0047] This application also provides an ultrasound image processing apparatus, comprising:

[0048] The initial information acquisition module is used to acquire an initial target ultrasound contrast image from the ultrasound video stream and determine the initial lesion area information of the initial target ultrasound contrast image;

[0049] The model processing module is used to obtain the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream based on the initial lesion region information and using the lesion tracking model.

[0050] The curve generation module is used to generate a time-intensity curve of the target lesion corresponding to the ultrasound video stream based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream.

[0051] This application also provides an electronic device, including a memory and a processor, wherein:

[0052] The memory is used to store computer programs;

[0053] The processor is used to execute the computer program to implement the ultrasound image processing method described above.

[0054] This application also provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the above-described ultrasound image processing method.

[0055] The ultrasound image processing method provided in this application acquires an initial target ultrasound contrast image from an ultrasound video stream and determines the initial lesion region information of the initial target ultrasound contrast image; based on the initial lesion region information, and using a lesion tracking model, obtains the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream; based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream, generates the target lesion time-intensity curve corresponding to the ultrasound video stream.

[0056] As can be seen, this method identifies an initial target ultrasound contrast image within the entire ultrasound video stream and obtains its corresponding initial lesion region information. Using a lesion tracking model, it can track and identify the corresponding lesion in each ultrasound contrast video frame of the ultrasound video stream based on the initial lesion region information and generate corresponding target lesion region information. Since the ultrasound probe and patient cannot remain completely still during actual ultrasound video stream acquisition, the lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream may be different. Therefore, the target lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream can be determined based on the initial lesion region information and the lesion tracking model. After obtaining the lesion region information of all ultrasound contrast video frames, it uses this information to generate a lesion time-intensity curve. This method tracks the lesion based on the initial lesion region information, generating accurate target lesion region information for each ultrasound contrast video frame individually, making the generated target lesion time-intensity curve more accurate.

[0057] In addition, this application also provides an ultrasound image processing device, an electronic device, and a computer-readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0059] Figure 1 A flowchart of an ultrasound image processing method provided in this application embodiment;

[0060] Figure 2 A schematic diagram of a visualization analysis report provided for this application;

[0061] Figure 3 A flowchart of ultrasonic video stream processing is provided for an embodiment of this application;

[0062] Figure 4 This is a schematic diagram of the structure of an ultrasound image processing device provided in an embodiment of this application;

[0063] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0065] It should be noted that the steps in this application can be performed by a specified electronic device, the specific form of which is not limited. For example, it can be an ultrasound device, a computer for processing ultrasound images, or a smart terminal, such as a tablet computer or a smartphone.

[0066] Please refer to Figure 1 , Figure 1 A flowchart illustrating an ultrasound image processing method provided in this application embodiment. The method includes:

[0067] S101: Obtain the initial target ultrasound contrast image from the ultrasound video stream and determine the initial lesion area information of the initial target ultrasound contrast image.

[0068] An ultrasound video stream refers to a video stream composed of multiple ultrasound contrast imaging video frames arranged in chronological order of sampling time. An ultrasound contrast imaging video frame refers to a contrast image obtained using ultrasound data, which refers to ultrasound echo data acquired through the ultrasound probe of an ultrasound device. The length and frame rate of the ultrasound video stream are not limited. The initial target ultrasound contrast imaging image refers to the first ultrasound contrast imaging video frame processed at the start of time-intensity curve plotting. Specifically, it can be any ultrasound contrast imaging video frame in the ultrasound video stream, and can be arbitrarily selected. For example, in one implementation, the user can interact with the electronic device and input unique identification information of the initial target ultrasound contrast imaging image, such as a frame number, to select the target ultrasound contrast imaging image. Alternatively, the electronic device can visualize the ultrasound video stream, detect the user's selection command during the display process, and determine the ultrasound contrast imaging video frame corresponding to the selection command as the initial target ultrasound contrast imaging image.

[0069] Initial lesion region information refers to the lesion region information corresponding to the initial target ultrasound contrast image, indicating the location of the lesion on the initial target ultrasound contrast image. The specific method of obtaining the initial lesion region information is not limited. For example, the electronic device can interact with the user, allowing the user to input the initial lesion region information into the electronic device through various optional methods. Alternatively, the initial lesion region information can be obtained by using a lesion recognition model to identify and process the initial target ultrasound image. Alternatively, the lesion recognition model can obtain candidate information after identifying and processing the initial target ultrasound image; the user can adjust this candidate information, and the electronic device can adjust the candidate information according to the adjustment operation to obtain the initial lesion region information.

[0070] S102: Based on the initial lesion area information, the target lesion area information of each ultrasound contrast video frame in the ultrasound video stream is obtained using the lesion tracking model.

[0071] A lesion tracking model is a network model used to identify and track lesion regions in ultrasound contrast-enhanced video frames. Its specific form is not limited; for example, it can be a deep neural network-based instance segmentation model, semantic segmentation model, or other image segmentation algorithm model based on machine learning or image processing methods, such as U-Net or DeepLab. The lesion tracking model is pre-trained, and the training set and training process are not limited. After obtaining the target ultrasound contrast-enhanced image and initial lesion region information, all or part of the ultrasound contrast-enhanced video frames in the ultrasound video stream can be input into the lesion tracking model. Based on the description of the lesion location using the initial lesion region information, the lesion tracking model can identify the lesion regions in each input ultrasound contrast-enhanced video frame and output target lesion region information representing the location of the lesion region within it. Specifically, the ultrasound contrast-enhanced video frame input into the lesion tracking model can be called the target ultrasound contrast-enhanced image. Target lesion region information refers to the regional information of the location of the lesion region in the ultrasound contrast-enhanced video frame. It should be noted that the initial lesion region information is the same as the target lesion region information of the initial target ultrasound contrast-enhanced image.

[0072] The number of target contrast-enhanced ultrasound images is not limited. In one embodiment, all contrast-enhanced ultrasound video frames in the ultrasound video stream are identified as target contrast-enhanced ultrasound images. Subsequently, the lesion region information of each contrast-enhanced ultrasound video frame is detected individually, maximizing the accuracy of the lesion region information. In another embodiment, a sampling method can be used to select a portion of the contrast-enhanced ultrasound video frames in the ultrasound video stream as target contrast-enhanced ultrasound images. Specifically, since the time interval between adjacent contrast-enhanced ultrasound video frames is small, and the ultrasound probe and patient typically do not experience sudden, violent movements, it can be assumed that the contrast-enhanced ultrasound video frames within the preset time interval will not undergo significant changes. When acquiring target contrast-enhanced ultrasound images, the preset time interval is first acquired, and target contrast-enhanced ultrasound images are extracted from the ultrasound video stream in chronological order.

[0073] It should be noted that the method of acquiring the ultrasound video stream is not limited. For example, in one embodiment, the ultrasound video stream is pre-generated, and the complete ultrasound video stream can be acquired at once. Accordingly, when determining the target ultrasound contrast image, all target ultrasound contrast images can be determined at once. In another embodiment, the ultrasound video stream is generated in real time, and each ultrasound contrast video frame in the ultrasound video stream can be acquired sequentially. Accordingly, when determining the target ultrasound contrast image, each target ultrasound contrast image can be determined sequentially. The method of determining the target ultrasound contrast image is not limited; for example, the frame number or other unique identification information of the target ultrasound contrast image can be recorded.

[0074] The lesion tracking model requires a tracking standard for lesion tracking. In this application, this standard is the target lesion region information of the ultrasound contrast-enhanced video frame with an earlier sampling time. Specifically, a first target ultrasound contrast-enhanced image and a second target ultrasound contrast-enhanced image are obtained from each ultrasound contrast-enhanced video frame in the ultrasound video stream. The sampling times of each target ultrasound contrast-enhanced image are different. Specifically, two target ultrasound contrast-enhanced images with adjacent sampling times can be referred to as the first target ultrasound contrast-enhanced image and the second target ultrasound contrast-enhanced image, with the first target ultrasound contrast-enhanced image having an earlier sampling time. It should be noted that the above-mentioned "adjacent sampling times" means that there is no other target ultrasound contrast-enhanced image between the two sampling times. The two sampling times themselves can be adjacent sampling times, that is, there is no ultrasound contrast-enhanced video frame between them, or the two sampling times themselves are not adjacent sampling times, that is, there is no target ultrasound contrast-enhanced image between them, but there are other ultrasound contrast-enhanced video frames. The first target ultrasound contrast-enhanced image may include the initial target ultrasound contrast-enhanced image. After determining the first target ultrasound contrast-enhanced image, the first lesion region information corresponding to the first target ultrasound contrast-enhanced image is obtained. Understandably, if the first target ultrasound contrast image is the same as the initial target ultrasound contrast image, then the first lesion region information is the same as the initial lesion region information. If the first target ultrasound contrast image is not the initial ultrasound contrast image, then the first lesion region information is the lesion region information obtained based on the initial lesion region information, which can be obtained through subsequent specific generation processes. After obtaining the first lesion region information, based on the first lesion region information, the second lesion region information corresponding to the second target ultrasound image is obtained using a lesion tracking model. Furthermore, the first and second lesion region information are used to determine the target lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream.

[0075] The specific process for generating the second lesion region information is described below. In one embodiment, if each ultrasound contrast-enhanced video frame in the ultrasound video stream is a target ultrasound contrast-enhanced image, then after all ultrasound contrast-enhanced video frames have been processed by the lesion tracking model, the target lesion region information corresponding to all ultrasound contrast-enhanced video frames can be determined. Therefore, by inputting all ultrasound contrast-enhanced video frames in the ultrasound video stream into the lesion tracking model, the target lesion region information of each ultrasound contrast-enhanced video frame in the ultrasound video stream can be determined. The target lesion region information may include unique identification information of the corresponding target ultrasound contrast-enhanced image (which is the ultrasound contrast-enhanced video frame in this embodiment), such as frame number information, to indicate the correspondence with the target ultrasound contrast-enhanced image.

[0076] In another embodiment, the target ultrasound contrast image can be a portion of ultrasound contrast video frames in an ultrasound video stream. For example, a preset time interval can be obtained, and based on the preset time interval, a first target ultrasound contrast image and a second target ultrasound contrast image can be extracted from the ultrasound video stream in chronological order. When generating target lesion region information, the first lesion region information of the first target ultrasound contrast image can be determined as the target lesion region information corresponding to each ultrasound contrast video frame between the first target ultrasound contrast image and the second target ultrasound contrast image. In this embodiment, the first lesion region information can be the aforementioned initial lesion region information, or it can be the target lesion region information obtained by processing other first target ultrasound contrast images and second target ultrasound contrast images using this method. This embodiment can achieve the reuse of target lesion region information. It can be considered that the differences between each ultrasound contrast video frame between the first target ultrasound contrast image and the second target ultrasound contrast image and the first target ultrasound contrast image are small. Therefore, by reusing the first target lesion region information, the time required to generate the target lesion region information can be reduced, and the image processing speed can be improved. The specific method of reuse is not limited. For example, the unique identifier of the first target lesion area information can be modified to the unique identifier of other ultrasound contrast video frames to obtain the target lesion area information corresponding to these ultrasound contrast video frames.

[0077] It is understandable that each ultrasound contrast-enhanced video frame can contain one or more lesion regions. If each target lesion region information can identify a lesion region, then the number of target lesion region information corresponding to each ultrasound contrast-enhanced video frame can be multiple. The specific form of the target lesion region information is not limited. For example, it can be in coordinate form, where the coordinates are the position coordinates of each pixel in the lesion region within the ultrasound contrast-enhanced video frame; or it can be in coordinate + range form, where the coordinates are the position coordinates of the reference pixel of the lesion region within the ultrasound contrast-enhanced video frame, and the range is the relative range of the lesion region based on the reference pixel. Furthermore, it can also contain contour information; specifically, for both target lesion region information and initial lesion region information, this can be the contour information of the lesion region.

[0078] S103: Based on the target lesion area information of each ultrasound contrast video frame in the ultrasound video stream, generate the target lesion time intensity curve corresponding to the ultrasound video stream.

[0079] Specifically, by utilizing the target lesion region information, the location of the target lesion region can be determined on the ultrasound contrast imaging video frame. Each target lesion region contains lesion pixels, and each lesion pixel has a corresponding pixel value. Using the pixel values ​​and the number of lesion pixels within the target lesion region, the average pixel value of the lesion region is generated. This average pixel value can be obtained using a simple average calculation or a weighted average calculation. It should be noted that the average pixel value of the lesion region reflects the average intensity of the contrast agent in the lesion region. The curve showing the change of the average contrast agent intensity at the lesion region over time is the time-intensity curve of the target lesion. By analyzing this time-intensity curve, lesion detection can be achieved. Therefore, the more accurate the time-intensity curve of the target lesion, the more accurate the lesion detection.

[0080] After obtaining the average pixel value of the lesion region corresponding to each ultrasound contrast-enhanced video frame, the target lesion time-intensity curve can be generated using the average pixel value and the sampling time of the corresponding ultrasound contrast-enhanced video frame as the horizontal and vertical axes, in order to characterize the change of contrast agent intensity in the lesion region over time. Specifically, the curve points corresponding to each ultrasound contrast-enhanced video frame can be determined. These curve points are the points on the target lesion time-intensity curve corresponding to the ultrasound contrast-enhanced video frame. Connecting these curve points with the sampling time of the ultrasound contrast-enhanced video frame as the horizontal axis and the average pixel value of the lesion region as the vertical axis yields the target lesion time-intensity curve. Furthermore, to make the target lesion time-intensity curve easier to analyze statistically, the curve points can be connected to obtain the initial lesion time-intensity curve. By performing curve fitting on the initial lesion time-intensity curve, the target lesion time-intensity curve is obtained, resulting in a target lesion time-intensity curve with fewer spikes.

[0081] Furthermore, in one feasible implementation, since the baseline time-intensity curves of contrast agent intensity changes over time may differ in normal areas of different sites and patients, this application can also generate a baseline time-intensity curve to accurately assess the lesion area. Specifically, the following steps can be performed:

[0082] Step 11: Based on the initial lesion area information, generate the initial non-lesion area information corresponding to the initial target ultrasound contrast image.

[0083] Step 12: Generate target non-lesion area information for each ultrasound contrast-enhanced video frame based on the initial non-lesion area information.

[0084] Step 13: Based on the information of the target non-lesion area, generate the corresponding pixel mean of the non-lesion area using ultrasound contrast imaging video frames.

[0085] Step 14: Generate the baseline time intensity curve corresponding to the ultrasound video stream using the pixel mean of the non-lesion area.

[0086] In this application, after determining the initial lesion area information corresponding to the initial target ultrasound contrast image, a non-lesion area can be selected on the initial target ultrasound contrast image. The non-lesion area refers to the region of interest (ROI) corresponding to normal tissue, which can be randomly selected and used as the reference area. The non-lesion area information is used to characterize the position of the non-lesion area on the target ultrasound contrast image.

[0087] This embodiment does not limit the specific method of generating the initial non-lesion area information. For example, in one implementation, a visualization graphic corresponding to the initial lesion area information can be generated and superimposed on the initial target ultrasound contrast image for visualization output. After viewing the visualized image, the user performs an interactive operation on the electronic device through an interactive component. After recognizing the interactive operation, the electronic device generates the initial non-lesion area information based on the interactive operation. The method of generating the initial non-lesion area information varies depending on the type of interactive operation. For example, if the interactive operation is a user clicking on the visualized image, the electronic device can detect the coordinate position of the click and generate the initial non-lesion area information based on the preset non-lesion area shape and the coordinate position. Alternatively, if the interactive operation is a user drawing or selecting a closed area on the visualized image, the electronic device detects the coordinate information of the drawn closed area and encapsulates the coordinate information as the initial non-lesion area information.

[0088] In another implementation, the electronic device can automatically select the non-lesion region corresponding to the initial target ultrasound contrast image according to preset rules, thereby generating corresponding initial non-lesion region information. For example, after determining the initial lesion region information, a non-lesion region can be selected outside the range defined by the initial lesion region information according to preset rules, such as distance rules or one or more rules.

[0089] After the initial non-lesion region information is determined, it is used to obtain the target non-lesion region information corresponding to each ultrasound contrast-enhanced video frame. Similar to the lesion region information, the non-lesion region information can be used to determine the non-lesion region in the ultrasound contrast-enhanced video frame, and the pixel mean of the non-lesion region can be calculated based on the pixel value of each pixel in the non-lesion region, thereby generating a baseline time-intensity curve.

[0090] To improve the accuracy of the baseline time-intensity curve, positional relationship information between the initial non-lesion region information and the initial lesion region information can be generated. Positional relationship information refers to information that indicates the relative positional relationship between the initial non-lesion region and at least one lesion region in the initial target ultrasound contrast-enhanced image. When generating target non-lesion region information for each ultrasound contrast-enhanced video frame based on the initial non-lesion region information, the non-lesion region information for each ultrasound contrast-enhanced video frame can be generated using the positional relationship information and the target lesion region information, based on the target lesion region information. Even if the position of the lesion region in other ultrasound contrast-enhanced video frames changes relative to the lesion region in the initial target ultrasound contrast-enhanced image, the non-lesion region can be repositioned using the positional relationship information based on the new lesion region position, thus obtaining the target non-lesion region information for each ultrasound contrast-enhanced video frame. It is understood that the target non-lesion region information and the target lesion region information can have the same form, either coordinates or including tissue contour information of normal tissue.

[0091] Furthermore, after obtaining the target lesion time-intensity curve and the baseline time-intensity curve, preset detection data corresponding to the target lesion time-intensity curve and the baseline time-intensity curve can also be obtained. The specific content of the preset detection data is not limited, but may include, for example:

[0092] BI (Base Intensity): The basic intensity before the contrast agent arrives;

[0093] AT (Arrival Time): The time at which the contrast intensity begins to appear, actually taken as the time value when it is 110% higher than the baseline;

[0094] TTP (Time To Peak): The time point at which the contrast agent reaches its peak value;

[0095] PI (Peak Intensity): Peak intensity of the contrast agent;

[0096] AS (Aescending Slope): The slope of the curve as it rises;

[0097] DT / 2: Time to half the peak intensity; the point in time when the intensity drops to half of the peak intensity after the peak intensity has passed.

[0098] DS (Descending Slope): The slope of the curve's descent.

[0099] MTT (Mean Transmit Time): In TIC curves, it is calculated by measuring the time difference between the perfusion curve and the decay curve when the peak intensity reaches half the intensity.

[0100] AUC (Area Under Curve): The area under the time-intensity curve during imaging.

[0101] Further, a visual analysis report is generated using preset detection data, the target lesion time-intensity curve, and the baseline time-intensity curve, allowing users to directly extract valuable information from the time-intensity curves. Specifically, a difference time-intensity curve can be generated using the target lesion time-intensity curve and the baseline time-intensity curve. The difference time-intensity curve represents the difference in contrast agent intensity between the lesion area and the non-lesion area, and can be obtained by subtracting the baseline time-intensity curve from the target lesion time-intensity curve, or vice versa. Abnormal detection data is generated based on the difference time-intensity curve. This abnormal detection data corresponds to the detection data of the difference time-intensity curve, and its specific content can be the same as or different from the preset detection data, or partially the same. For example, in one implementation, the abnormal detection data may include the maximum abnormal contrast increment, rapidly changing increment segments, etc. A visual analysis report is generated using the abnormal detection data, preset detection data, difference time-intensity curve, target lesion time-intensity curve, and baseline time-intensity curve. The specific generation method is not limited; for example, a client-side smooth analysis can be generated according to a preset template. It should be noted that the visualization analysis report can represent the above curves and data in various forms. For example, it can represent anomaly detection data and preset detection data in the form of text, or it can represent them on the curve using color, interval highlighting, etc. For example, the corresponding part of the incremental rapid change section on the above three types of curves can be marked in yellow, or the incremental rapid change section can be represented in the form of time interval.

[0102] Please refer to Figure 2 , Figure 2 This application provides a schematic diagram of a visualization analysis report. It includes a parameter area and a curve area. The parameter area displays the aforementioned preset detection data, while the curve area displays the target lesion's time-intensity curve and the baseline time-intensity curve. Specifically, the user can send a ROI (Region of Interest, specifically the lesion area or non-lesion area in this application) selection command to the electronic device, and the electronic device selects the imaging curve according to the ROI selection command. For example, continue to refer to... Figure 2Users can send ROI selection commands to the electronic device by clicking the boxes before text such as ROI1 and ROI2 in the lower left corner. Different lesion ROIs and baseline ROI regions can be selected for visualization and quantitative analysis. Examples include comparing and displaying TIC curves of different ROIs in the same coordinate system, obtaining the TIC curve of abnormal contrast enhancement by subtracting the corresponding time axis intensity of the TIC curves of the lesion ROI and the baseline ROI, obtaining the maximum abnormal contrast enhancement, identifying rapidly changing segments of the enhancement, and marking warnings for curves in areas of abnormal change.

[0103] The ultrasound image processing method provided in this application determines an initial target ultrasound contrast image in the entire ultrasound video stream and obtains its corresponding initial lesion region information. Using a lesion tracking model, based on the initial lesion region information, the corresponding lesion can be identified in each ultrasound noise video frame of the ultrasound video stream, and corresponding target lesion region information can be generated. Since the ultrasound probe and patient cannot remain completely still during actual ultrasound video stream acquisition, the lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream may be different. However, the ultrasound probe and patient will not experience sudden and violent movement, and the lesion region information corresponding to ultrasound contrast video frames within a short period is basically the same. Therefore, the target lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream can be obtained based on the initial lesion region information and the lesion tracking model. After obtaining the lesion region information of all ultrasound contrast video frames, the target lesion time-intensity curve is generated using it. This method tracks the lesion based on the initial lesion region information, generating accurate lesion region information corresponding to each ultrasound contrast video frame individually, making the generated target lesion time-intensity curve more accurate.

[0104] Please refer to Figure 3 , Figure 3This application provides a flowchart of an ultrasound video stream processing procedure. First, a contrast agent is injected into the patient. When the acquisition time is reached, the user activates the electronic device. Upon detecting the activation, the electronic device initiates the TIC automatic analysis function. The TIC automatic analysis function utilizes a deep neural network model (i.e., a lesion identification model). The electronic device acquires the ultrasound video stream in real time and selects ultrasound contrast video frames from it. It then processes these frames using the deep neural network model to obtain the lesion ROI (i.e., the lesion region). A normal tissue ROI (i.e., a non-lesion region) is selected outside the lesion ROI as a control monitoring area. The electronic device records the location information corresponding to the lesion ROI as the target lesion region information and records the location information corresponding to the normal tissue ROI as the target non-lesion region information. In this application, each ultrasound contrast video frame of the ultrasound video stream is designated as the target ultrasound image. Therefore, for the (N+1)th frame, the electronic device continues to process the image using the deep neural network model to obtain lesion region information and dynamically adjusts the non-lesion region information of the current frame by comparing it with the target non-lesion region information of the previous frame. This process is repeated until all ultrasound contrast video frames have been processed. The electronic device calculates the average grayscale value (i.e., the average pixel value of the lesion region) of each ROI in each frame of the image (i.e., the ultrasound contrast video frame) based on the lesion region information. It also calculates the average grayscale value of the corresponding normal tissue ROI (i.e., the average pixel value of the non-lesion region), and uses the average grayscale values ​​of each region to plot curves, obtaining the TIC curve for each region. The electronic device compares and analyzes the TIC curves of each lesion region and non-lesion region, comparing preset detection data such as curve peak value, peak slope, and fading slope with preset detection data of the same category as the benchmark TIC. If there is a mismatch, it indicates an abnormality, identifies the abnormal lesion and the corresponding abnormal TIC curve segment, and generates and outputs an analysis report.

[0105] The ultrasonic image processing apparatus provided in the embodiments of this application is described below. The ultrasonic image processing apparatus described below and the ultrasonic image processing method described above can be referred to in correspondence.

[0106] Please refer to Figure 4 , Figure 4 A schematic diagram of an ultrasound image processing device provided in this application embodiment includes:

[0107] The initial information acquisition module 110 is used to acquire the initial target ultrasound contrast image from the ultrasound video stream and determine the initial lesion area information of the initial target ultrasound contrast image.

[0108] The model processing module 120 is used to obtain the target lesion area information of each ultrasound contrast video frame in the ultrasound video stream based on the initial lesion area information and by using the lesion tracking model.

[0109] The curve generation module 130 is used to generate the time intensity curve of the target lesion corresponding to the ultrasound video stream based on the target lesion area information of each ultrasound contrast video frame in the ultrasound video stream.

[0110] Optionally, the model processing module 120 includes:

[0111] An image selection unit is used to acquire a first target ultrasound contrast image and a second target ultrasound contrast image from each ultrasound contrast video frame in an ultrasound video stream; wherein the first target ultrasound contrast image includes an initial target ultrasound contrast image.

[0112] The information acquisition unit is used to acquire information about the first lesion region corresponding to the ultrasound contrast-enhanced image of the first target; wherein, the information about the first lesion region is obtained based on the initial lesion region information;

[0113] The tracking processing unit is used to obtain the second lesion region information corresponding to the second target ultrasound image based on the first lesion region information and using the lesion tracking model;

[0114] The target lesion area information determination unit is used to determine the target lesion area information corresponding to each ultrasound contrast video frame in the ultrasound video stream using the first lesion area information and the second lesion area information.

[0115] Optionally, the image selection unit includes:

[0116] Interval acquisition sub-unit, used to acquire preset time intervals;

[0117] The extraction subunit is used to extract the first target ultrasound contrast image and the second target ultrasound contrast image from the ultrasound video stream based on a preset time interval and in chronological order.

[0118] Optionally, the target lesion area information determination unit includes:

[0119] The information multiplexing subunit is used to determine the first lesion region information of the first target ultrasound contrast image as the target lesion region information corresponding to each ultrasound contrast video frame between the first target ultrasound contrast image and the second target ultrasound contrast image.

[0120] Optionally, the target lesion area information determination unit includes:

[0121] The model processing subunit is used to input all ultrasound contrast imaging video frames in the ultrasound video stream into the lesion tracking model to determine the target lesion area information of each ultrasound contrast imaging video frame in the ultrasound video stream.

[0122] Optionally, the curve generation module 130 includes:

[0123] The mean calculation unit is used to obtain the mean pixel value of the lesion area corresponding to the ultrasound contrast imaging video frame based on the target lesion area information and the ultrasound contrast imaging video frame.

[0124] The curve plotting unit is used to generate the time-intensity curve of the target lesion corresponding to the ultrasound video stream using the pixel mean of the lesion area.

[0125] Optionally, the mean calculation unit includes:

[0126] The location determination unit is used to determine the location of the target lesion area on the ultrasound contrast video frame based on the target lesion area information;

[0127] The mean generation unit is used to generate the mean pixel value of the lesion area by using the pixel value corresponding to each lesion pixel in the target lesion area and the number of lesion pixels.

[0128] Optionally, the curve drawing unit includes:

[0129] The curve point determination unit is used to determine the curve point corresponding to each ultrasound contrast imaging video frame; wherein, the curve point is based on the sampling time of the ultrasound contrast imaging video frame as the abscissa and the average pixel value of the lesion area as the ordinate.

[0130] The generation unit is used to obtain the time-intensity curve of the target lesion based on the curve points.

[0131] Optionally, the generating unit includes:

[0132] Connecting sub-units are used to connect curve points to obtain the initial lesion time-intensity curve;

[0133] The fitting subunit is used to perform curve fitting on the initial lesion time-intensity curve to obtain the target lesion time-intensity curve.

[0134] Optionally, it also includes:

[0135] The target non-lesion information generation module is used to generate initial non-lesion area information corresponding to the initial target ultrasound contrast image based on the initial lesion area information.

[0136] The non-lesion information generation module is used to generate target non-lesion area information corresponding to each ultrasound contrast video frame based on the initial non-lesion area information.

[0137] The non-lesion mean calculation module is used to generate the corresponding non-lesion region pixel mean based on the target non-lesion region information and using ultrasound contrast video frames.

[0138] The baseline curve generation module is used to generate a baseline time-intensity curve corresponding to the ultrasound video stream using the pixel mean value of non-lesion areas.

[0139] Optionally, it also includes:

[0140] The preset detection data acquisition module is used to acquire preset detection data corresponding to the target lesion time-intensity curve and the baseline time-intensity curve, respectively.

[0141] The report generation module is used to generate a visual analysis report using preset detection data, target lesion time-intensity curves, and baseline time-intensity curves.

[0142] Optionally, the report generation module includes:

[0143] The difference curve generation unit is used to generate a difference time intensity curve using the target lesion time intensity curve and the baseline time intensity curve;

[0144] An anomaly detection data determination unit is used to generate anomaly detection data based on the difference time intensity curve;

[0145] The report generation unit is used to generate a visual analysis report using abnormal detection data, preset detection data, difference time-intensity curves, target lesion time-intensity curves, and baseline time-intensity curves.

[0146] Optionally, it also includes:

[0147] The location relationship information determination module is used to generate location relationship information between the initial non-lesion area information and the initial lesion area information;

[0148] The non-lesion information generation module includes:

[0149] The non-lesion location adjustment unit is used to generate target non-lesion area information corresponding to each ultrasound modeling video frame based on positional relationship information and using information about each target lesion area.

[0150] The electronic device provided in the embodiments of this application is described below. The electronic device described below can be referred to in correspondence with the ultrasound image processing method described above.

[0151] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 100 may include a processor 101 and a memory 102, and may further include one or more of a multimedia component 103, an information input / output (I / O) interface 104, and a communication component 105.

[0152] The processor 101 controls the overall operation of the electronic device 100 to complete all or part of the steps in the ultrasound image processing method described above. The memory 102 stores various types of data to support the operation of the electronic device 100. This data may include, for example, instructions for any application or method operating on the electronic device 100, as well as application-related data. The memory 102 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0153] Multimedia component 103 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 102 or transmitted via communication component 105. The audio component also includes at least one speaker for outputting audio signals. I / O interface 104 provides an interface between processor 101 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 105 is used for wired or wireless communication between electronic device 100 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 105 may include a Wi-Fi component, a Bluetooth component, or an NFC component.

[0154] The electronic device 100 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the ultrasonic image processing method given in the above embodiments.

[0155] The following describes the computer-readable storage medium provided in the embodiments of this application. The computer-readable storage medium described below can be referred to in correspondence with the ultrasound image processing method described above.

[0156] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the ultrasound image processing method described above.

[0157] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0159] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0160] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0161] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "include," "contain," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0162] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An ultrasound image processing method, characterized in that, include: An initial target ultrasound contrast image is acquired from the ultrasound video stream, and the initial lesion region information of the initial target ultrasound contrast image is determined. Based on the initial lesion region information, the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream is obtained using a pre-trained lesion tracking model based on a deep neural network. Based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream, a target lesion time intensity curve corresponding to the ultrasound video stream is generated. The method further includes: generating initial non-lesion area information corresponding to the initial target ultrasound contrast image based on the initial lesion area information; The process involves generating positional relationship information between the initial non-lesion region information and the initial lesion region information; based on the positional relationship information, generating target non-lesion region information corresponding to each of the target lesion region information using the ultrasound contrast-enhanced video frames; generating the corresponding non-lesion region pixel mean using the ultrasound contrast-enhanced video frames based on the target non-lesion region information; generating a reference time-intensity curve corresponding to the ultrasound video stream using the non-lesion region pixel mean; acquiring preset detection data corresponding to the target lesion time-intensity curve and the reference time-intensity curve respectively; and generating a visualization analysis report using the preset detection data, the target lesion time-intensity curve, and the reference time-intensity curve.

2. The ultrasound image processing method according to claim 1, characterized in that, The step of obtaining target lesion region information for each ultrasound contrast-enhanced video frame in the ultrasound video stream based on the initial lesion region information and using a lesion tracking model includes: A first target ultrasound contrast image and a second target ultrasound contrast image are obtained from each of the ultrasound contrast video frames in the ultrasound video stream; wherein, the first target ultrasound contrast image includes the initial target ultrasound contrast image; Obtain information about the first lesion region corresponding to the first target ultrasound contrast image; wherein, the information about the first lesion region is obtained based on the initial lesion region information; Based on the first lesion area information, and using the lesion tracking model, the second lesion area information corresponding to the second target ultrasound contrast image is obtained; The target lesion region information corresponding to each ultrasound contrast video frame in the ultrasound video stream is determined by using the first lesion region information and the second lesion region information.

3. The ultrasound image processing method according to claim 2, characterized in that, The step of obtaining the first target ultrasound contrast image and the second target ultrasound contrast image from each of the ultrasound contrast video frames in the ultrasound video stream includes: Get the preset time interval; Based on the preset time interval, the first target ultrasound contrast image and the second target ultrasound contrast image are extracted from the ultrasound video stream in chronological order.

4. The ultrasound image processing method according to claim 3, characterized in that, The step of determining the target lesion region information corresponding to each ultrasound contrast-enhanced video frame in the ultrasound video stream using the first lesion region information and the second lesion region information includes: The first lesion region information of the first target ultrasound contrast image is determined as the target lesion region information corresponding to each ultrasound contrast video frame between the first target ultrasound contrast image and the second target ultrasound contrast image.

5. The ultrasound image processing method according to claim 1, characterized in that, The step of obtaining target lesion region information for each ultrasound contrast-enhanced video frame in the ultrasound video stream based on the initial lesion region information and using a lesion tracking model includes: All the ultrasound contrast imaging video frames in the ultrasound video stream are input into the lesion tracking model to determine the target lesion region information of each ultrasound contrast imaging video frame in the ultrasound video stream.

6. The ultrasound image processing method according to claim 1, characterized in that, The step of generating a time-intensity curve of the target lesion corresponding to the ultrasound video stream based on the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream includes: Based on the target lesion area information, the average pixel value of the lesion area corresponding to the ultrasound contrast imaging video frame is obtained using the ultrasound contrast imaging video frame. The average pixel value of the lesion region is used to generate the time intensity curve of the target lesion corresponding to the ultrasound video stream.

7. The ultrasound image processing method according to claim 6, characterized in that, The step of obtaining the average pixel value of the lesion region corresponding to the ultrasound contrast-enhanced video frame based on the target lesion region information includes: Based on the target lesion area information, the location of the target lesion area is determined on the ultrasound contrast video frame; The average pixel value of the lesion region is generated by using the pixel value and the number of lesion pixels corresponding to each lesion pixel in the target lesion region.

8. The ultrasound image processing method according to claim 6, characterized in that, The step of generating the target lesion time-intensity curve corresponding to the ultrasound video stream using the pixel mean of the lesion region includes: Determine the curve points corresponding to each of the ultrasound contrast imaging video frames; wherein, the curve points are plotted with the sampling time of the ultrasound contrast imaging video frame as the abscissa and the average pixel value of the lesion region as the ordinate; The time-intensity curve of the target lesion is obtained based on the curve points.

9. The ultrasound image processing method according to claim 8, characterized in that, The process of obtaining the time-intensity curve of the target lesion based on the curve points includes: Connecting the points on the curve yields the initial lesion time-intensity curve; The initial lesion time-intensity curve is subjected to curve fitting to obtain the target lesion time-intensity curve.

10. The ultrasound image processing method according to claim 1, characterized in that, The process of generating a visual analysis report using the preset detection data, the target lesion time-intensity curve, and the baseline time-intensity curve includes: A difference time-intensity curve is generated using the target lesion time-intensity curve and the baseline time-intensity curve; Anomaly detection data is generated based on the difference time-intensity curve; A visual analysis report is generated using the abnormal detection data, the preset detection data, the difference time-intensity curve, the target lesion time-intensity curve, and the baseline time-intensity curve.

11. An ultrasonic image processing device, characterized in that, include: The initial information acquisition module is used to acquire an initial target ultrasound contrast image from the ultrasound video stream and determine the initial lesion area information of the initial target ultrasound contrast image. The model processing module is used to obtain the target lesion region information of each ultrasound contrast video frame in the ultrasound video stream based on the initial lesion region information and using a pre-trained lesion tracking model based on a deep neural network. The curve generation module is used to generate the target lesion time intensity curve corresponding to the ultrasound video stream based on the target lesion area information of each ultrasound contrast video frame in the ultrasound video stream. The device is further configured to: generate initial non-lesion region information corresponding to the initial target ultrasound contrast image based on the initial lesion region information; generate positional relationship information between the initial non-lesion region information and the initial lesion region information; generate target non-lesion region information corresponding to each of the ultrasound contrast video frames based on the positional relationship information and using each of the target lesion region information; generate corresponding non-lesion region pixel mean values ​​using the ultrasound contrast video frames based on the target non-lesion region information; generate a reference time-intensity curve corresponding to the ultrasound video stream using the non-lesion region pixel mean values; acquire preset detection data corresponding to the target lesion time-intensity curve and the reference time-intensity curve respectively; and generate a visualization analysis report using the preset detection data, the target lesion time-intensity curve, and the reference time-intensity curve.

12. An electronic device, characterized in that, Includes memory and processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program to implement the ultrasound image processing method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements the ultrasound image processing method as described in any one of claims 1 to 10.

Images