Ultrasound image processing method, system, device and program product

Abstract

The application discloses an ultrasonic image processing method, system, device and program product, and relates to the technical field of ultrasonic imaging, and in particular relates to an ultrasonic image processing method, system, device and program product. The method comprises the following steps: collecting first ultrasonic echo signals corresponding to a target object based on an ultrasonic probe; performing beamforming processing on the first ultrasonic echo signals to obtain a first beam matrix; performing interpolation processing on the first beam matrix based on a target beam interpolation model to obtain a second beam matrix; and constructing an ultrasonic image corresponding to the target object based on the second beam matrix. The method can enrich image details, improve the definition and resolution of ultrasonic imaging, and realize accurate restoration of the internal structure of the target object.

Description

Technical Field

[0001] This invention relates to the field of ultrasound data optimization technology, and in particular to an ultrasound image processing method, system, device, and program product. Background Technology

[0002] Ultrasound imaging, with its advantages of being non-invasive and safe, providing real-time imaging, and being easy to operate, is widely used in clinical diagnosis, industrial non-destructive testing, and other fields.

[0003] In related technologies, ultrasound imaging typically involves first sampling multiple echo signals and constructing an echo matrix, then using beamforming algorithms and signal processing techniques for image reconstruction. This imaging method is often limited by hardware configurations and sampling conditions such as ultrasound probe element density and signal sampling frequency, resulting in ultrasound images with low resolution and blurred details, making it difficult to meet the needs of high-precision detection and diagnosis. Therefore, there is an urgent need for an ultrasound image processing method to improve image resolution and signal-to-noise ratio, enabling accurate reconstruction of the internal structure of the target object. Summary of the Invention

[0004] This invention provides an ultrasound image processing method, system, device, and program product to solve problems such as insufficient resolution and blurred details in reconstructed images caused by factors such as probe array density and sampling frequency in related technologies.

[0005] According to one aspect of the present invention, an ultrasound image processing method is provided, the method comprising: The first ultrasonic echo signal corresponding to the target object is acquired based on the ultrasonic probe; The first ultrasonic echo signal is subjected to beamforming processing to obtain a first beam matrix; The first beam matrix is ​​interpolated based on the target beam interpolation model to obtain the second beam matrix; An ultrasound image corresponding to the target object is constructed based on the second beam matrix.

[0006] According to another aspect of the present invention, an ultrasound image processing system is provided, the system comprising: An ultrasonic probe is used to acquire the first ultrasonic echo signal corresponding to the target object. An ultrasonic circuit board is used to perform beamforming processing on the first ultrasonic echo signal to obtain a first beam matrix. An ultrasound image processing module is used to interpolate the first beam matrix based on a target beam interpolation model to obtain a second beam matrix; and to construct an ultrasound image corresponding to the target object based on the second beam matrix.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the ultrasound image processing method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the ultrasound image processing method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, embodiments of the present disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the ultrasound image processing method as described in any of the embodiments of the present disclosure.

[0010] The technical solution of this invention firstly acquires a first ultrasonic echo signal corresponding to the target object based on an ultrasonic probe; this echo signal reflects the acoustic impedance distribution information inside the target object, providing data support for subsequent ultrasonic image construction; next, the first ultrasonic echo signal is beamformed to obtain a first beam matrix; the echo signal is regularized into a structured beam matrix to achieve dynamic focusing and deflection of the sound beam, optimizing signal quality; then, the first beam matrix is ​​interpolated based on a target beam interpolation model to obtain a second beam matrix; interpolation based on the target beam interpolation model refines the signal dimension, achieving super-resolution reconstruction of the beam space and significantly improving the horizontal and vertical resolution of the final generated image; finally, an ultrasonic image corresponding to the target object is constructed based on the second beam matrix; the ultrasonic image constructed based on the interpolated beam matrix clearly restores the anatomical structure of the target object, enriches the details of the ultrasonic image, and improves the clarity and resolution of the ultrasonic imaging.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of an ultrasound image processing method provided according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of an ultrasound image processing method provided according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the training of a target beam interpolation model for an ultrasound image processing method according to Embodiment 2 of the present invention; Figure 4 This is a schematic diagram illustrating the construction of an ultrasound image of a target object using an ultrasound image processing method according to Embodiment 2 of the present invention. Figure 5 This is a schematic diagram of ultrasound images generated before and after processing by the target beam interpolation model of an ultrasound image processing method according to Embodiment 2 of the present invention; Figure 6 This is a schematic diagram of the structure of an ultrasound image processing system according to Embodiment 3 of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device that implements the ultrasound image processing method of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," "target," "initial," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0017] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0018] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0019] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0020] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0021] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0022] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0023] Example 1 Figure 1 This is a flowchart of an ultrasound image processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving the processing of ultrasound images. The method can be executed by an ultrasound image processing system, which can be implemented in hardware and / or software, optionally through an electronic device, such as a mobile terminal, PC, or server. Figure 1 As shown, the method may specifically include: S110. Acquire the first ultrasonic echo signal corresponding to the target object based on the ultrasonic probe.

[0024] In this embodiment of the invention, an ultrasonic probe can be understood as an ultrasonic detection hardware device capable of emitting ultrasonic waves and receiving ultrasonic wave reflection echo signals. The target object can be understood as the object to be detected by ultrasonic imaging, such as, but not limited to, human tissues, biological organs, and other objects that can be detected by ultrasonic waves. The first ultrasonic echo signal can be the original electrical signal that returns to the probe after the ultrasonic probe emits ultrasonic waves towards the target object, is reflected and scattered by the internal tissue structure of the target object, and then returns to the probe.

[0025] Based on the above scheme, optionally, the step of acquiring the first ultrasonic echo signal corresponding to the target object based on the ultrasonic probe includes: transmitting a first ultrasonic wave to the target object based on a first scanning density, and receiving the first ultrasonic echo signal based on a first sampling frequency.

[0026] Here, the first ultrasonic wave can be understood as the ultrasonic signal emitted by the ultrasonic probe towards the target object according to the first scanning density. The first ultrasonic echo signal can be the electrical signal obtained after conversion of the ultrasonic wave reflected back from the target object and collected by the ultrasonic probe according to the first sampling frequency.

[0027] Specifically, the first scan density can be the scan density in the normal operating mode of the ultrasonic probe, adapted to the sound velocity propagation characteristics of conventional ultrasonic testing. Since the propagation speed of ultrasound in the medium is a constant, it can fully meet the frame rate requirements of conventional ultrasonic imaging, balancing detection efficiency and basic imaging accuracy. The first scan density can cover multiple scan densities in conventional testing scenarios. The first sampling frequency can be the maximum sampling frequency that the ultrasonic probe can stably achieve under standard operating conditions without additional function development or hardware modification in its hardware structure, supporting software, and inherent firmware. This can maximize the preservation of the detailed features of the original ultrasonic signal and reduce signal sampling loss and distortion. The first ultrasonic echo signal can be the collection of echo signals received by each element of the ultrasonic probe under conventional first scan density and first conventional sampling frequency sampling.

[0028] Specifically, a first ultrasonic wave can be emitted towards the target object based on a first scanning density. The ultrasonic wave propagates continuously within the target object's organ or tissue. When it reaches a tissue interface with a difference in acoustic impedance, some of the sound waves will be reflected, forming an echo signal carrying the tissue's location, material, and structural characteristics. This echo signal is transmitted back to the ultrasonic probe along the original propagation path or scattering direction. Then, the echo signal is acquired and converted into an electrical signal based on a first sampling frequency to obtain the first ultrasonic echo signal. .

[0029] S120. Beamforming is performed on the first ultrasonic echo signal to obtain a first beam matrix.

[0030] The first beam matrix can be understood as the data matrix obtained after beamforming the first ultrasonic echo signal.

[0031] Optionally, the first ultrasonic echo signal can be... Beamforming processes such as phase compensation, delay superposition, and signal focusing are performed to integrate the dispersed echo signals into a focused beam signal, resulting in the first beam matrix. .

[0032] Based on the above scheme, optionally, the step of performing beamforming processing on the first ultrasonic echo signal to obtain a first beam matrix includes: performing beamforming processing on the first ultrasonic echo signal to obtain a first initial beam matrix; performing preprocessing operations on the first initial beam matrix to obtain a first beam matrix; wherein the preprocessing operations include at least one of the following: bandpass filtering, sampling, interpolation, modulation, and demodulation.

[0033] The first initial beam matrix can be the original beam matrix after the first ultrasonic echo signal has completed beamforming processing without preprocessing. The original beam data can be retained in the initial beam matrix, but there may be problems such as clutter interference, large amount of redundant data, local phase deviation, and irregular data format.

[0034] Specifically, the first ultrasonic echo signal can be acquired using classical beamforming technology to construct a first initial beam matrix in a two-dimensional detection plane or a three-dimensional detection space. Without any additional dimension-up or down processing in the intermediate process, if the ultrasonic probe completes scanning acquisition on the two-dimensional plane of the target object, the corresponding first initial beam matrix is ​​a two-dimensional data matrix; if the ultrasonic probe completes stereoscopic scanning acquisition on the three-dimensional space of the target object, the corresponding first initial beam matrix is ​​a three-dimensional data matrix.

[0035] Furthermore, preprocessing operations can be performed on the first initial beam matrix to remove signal interference, unify the data format, and optimize signal quality to obtain the first beam matrix, providing reliable basic data for subsequent beam interpolation processing. Simultaneously, the preprocessing operation does not change the core dimensional attributes of the matrix; if the first initial beam matrix is ​​a two-dimensional matrix, then the preprocessed first beam matrix will be the corresponding sampling dimension. If the first initial beam matrix is ​​a three-dimensional matrix, then the preprocessed first beam matrix is ​​the corresponding sampling dimension. A three-dimensional matrix.

[0036] The preprocessing operations include at least one of the following: bandpass filtering, sampling, interpolation, modulation, demodulation, and other classic acoustic processing methods. Bandpass filtering can be used to retain the effective frequency range of the ultrasonic signal, complete frequency screening, effectively filter out low-frequency motion interference and high-frequency environmental noise, and retain effective signal characteristics. Sampling can be used to simplify the sampling of repetitive and invalid redundant data in the first initial beam matrix, compress the amount of invalid data, regularize the data dimensions, and improve the efficiency of subsequent data processing. Interpolation can be used to complete the missing data points of the first initial beam matrix and optimize data integrity. Modulation can be used to precisely modulate and optimize the amplitude, frequency, and phase parameters of the beam signal and correct signal parameter deviations. Demodulation can be used to analyze and decompose the beam signal, remove the modulation carrier information in the signal, accurately restore the original effective beam signal characteristics, and retain the core imaging data to the greatest extent.

[0037] S130. Based on the target beam interpolation model, the first beam matrix is ​​interpolated to obtain the second beam matrix.

[0038] The target beam interpolation model can be a model used to interpolate and complete the beam matrix data and optimize its resolution. The second beam matrix can be a beam data matrix with more complete data dimensions and higher resolution after the first beam matrix has been interpolated and optimized by the target beam interpolation model.

[0039] Specifically, the first beam matrix can be input into the target beam interpolation model for interpolation processing. Through multi-layer feature extraction, data completion, and dimensional refinement operations, missing data points in the beam matrix are completed, and the sparse data dimensions are refined, achieving super-resolution upgrade of the beam data, and finally outputting the second beam matrix. Among them, the second beam matrix It may be that the dimension is A two-dimensional matrix or a matrix with dimensions of A three-dimensional matrix.

[0040] For example, the second beam matrix can be represented based on the following formula: ; in, Indicates the second beam matrix; The first beam matrix is ​​represented; the model parameters of the target beam interpolation model are: , , The parameters of the input coding layer, intermediate feature processing layer, and output decoding layer of the target beam interpolation model; The parameters in the target beam interpolation model are: The output decoding layer; The parameters in the target beam interpolation model are: Feature processing layer, ; The parameters in the target beam interpolation model are: The input encoding layer.

[0041] Furthermore, if the first beam matrix For dimension The two-dimensional matrix, then the corresponding second beam matrix For dimension A two-dimensional matrix, and If the first beam matrix For dimension The two-dimensional matrix, then the corresponding second beam matrix For dimension A three-dimensional matrix, and Dimensions of the second beam matrix Compared to the high-resolution beam matrix dimension used in the model training phase same.

[0042] S140. Construct an ultrasound image of the target object based on the second beam matrix.

[0043] The ultrasound image can be a visualization image of the target object generated based on the optimized second beam matrix through data conversion, pixel mapping and other operations.

[0044] Optionally, ultrasound imaging can be performed based on the second beam matrix, converting the optimized beam data into a visualized pixel image to construct the ultrasound image corresponding to the target object. Simultaneously, to facilitate effect comparison and accuracy verification, ultrasound imaging can also be performed on the first beam matrix before the target beam interpolation model processing, converting it into a final pixel image available for user viewing, thus enabling a direct comparison of the imaging effects before and after optimization.

[0045] Based on the above scheme, optionally, the step of constructing the ultrasound image corresponding to the target object based on the second beam matrix includes: performing post-processing operations based on the second beam matrix to construct the ultrasound image; wherein the post-processing operations include at least one of the following: signal envelope processing, pixel image conversion processing, velocity image conversion processing, and time-domain filtering processing.

[0046] Specifically, post-processing operations can be performed based on the second beam matrix, such as data adaptation, noise reduction optimization, and image transformation, to generate ultrasound images. The post-processing operations include at least one of the following: signal envelope calculation, pixel map conversion, velocity map conversion, time-domain filtering, and pixel map enhancement. Signal envelope calculation can be used to extract the amplitude envelope curve of the ultrasonic beam signal, filter high-frequency oscillation noise in the signal, eliminate invalid fluctuation interference, retain the effective amplitude characteristics of the beam signal, and avoid flickering and artifact problems in imaging. Pixel map conversion can be used to accurately map the numerical second beam matrix data into the corresponding pixel grayscale and color values ​​of the image, completing the core transformation from numerical data to visualized pixel images and realizing the intuitive presentation of the target object structure. Velocity map conversion can be used to calculate the propagation speed distribution law of ultrasonic waves inside the target object based on the time delay and phase information of the beam signal, generate the corresponding velocity imaging spectrum, expand the detection dimension of the ultrasonic image, so that it can not only present the structural morphology, but also reflect the acoustic characteristics of the tissue. Time-domain filtering can be used to filter and reduce noise of the beam signal in the time dimension, filter out temporal random noise and interference signals, improve the overall signal-to-noise ratio of the ultrasonic image, and enhance the stability and clarity of the image.

[0047] Optionally, preprocessing can be performed after beamforming of the first ultrasonic echo signal to improve the data quality of the first beam matrix. Alternatively, preprocessing can be omitted, or postprocessing can be performed after the second beam matrix is ​​generated, with the same postprocessing operation as the preprocessing operation. For example, postprocessing operations can include various processing operations such as bandpass filtering, sampling, interpolation, modulation, and demodulation, thus moving the preprocessing steps to the postprocessing operation. The above preprocessing or postprocessing operations can be flexibly executed according to the actual business scenario requirements. There are no specific limitations on the specific content of the preprocessing and postprocessing operations or whether they are performed.

[0048] The technical solution of this invention firstly acquires a first ultrasonic echo signal corresponding to the target object based on an ultrasonic probe; this echo signal reflects the acoustic impedance distribution information inside the target object, providing data support for subsequent ultrasonic image construction; next, the first ultrasonic echo signal is beamformed to obtain a first beam matrix; the echo signal is regularized into a structured beam matrix to achieve dynamic focusing and deflection of the sound beam, optimizing signal quality; then, the first beam matrix is ​​interpolated based on a target beam interpolation model to obtain a second beam matrix; interpolation based on the target beam interpolation model refines the signal dimension, achieving super-resolution reconstruction of the beam space and significantly improving the horizontal and vertical resolution of the final generated image; finally, an ultrasonic image corresponding to the target object is constructed based on the second beam matrix; the ultrasonic image constructed based on the interpolated beam matrix clearly restores the anatomical structure of the target object, enriches the details of the ultrasonic image, and improves the clarity and resolution of the ultrasonic imaging.

[0049] Example 2 Figure 2 This is a flowchart illustrating an ultrasound image processing method according to Embodiment 2 of the present invention, further describing the method for determining the target beam interpolation model. Detailed implementation methods can be found in the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 2 As shown, the method may specifically include: S210. Acquire the first ultrasonic echo signal corresponding to the target object based on the ultrasonic probe.

[0050] S220. Beamforming is performed on the first ultrasonic echo signal to obtain a first beam matrix.

[0051] S230. Obtain the first scan density and the first sampling frequency used when acquiring the first ultrasonic echo signal.

[0052] The first scanning density can be the distribution density of the ultrasonic wave emission scanning points of the ultrasonic probe when acquiring the first ultrasonic echo signal. The first scanning density can be used to characterize the spatial sampling density of the ultrasonic scanning process. The first sampling frequency can be the time-domain sampling rate of the ultrasonic probe on the echo electrical signal when acquiring the first ultrasonic echo signal. The first sampling frequency can be used to characterize the time sampling accuracy of the echo signal.

[0053] Optionally, the first scanning density and first sampling frequency of the ultrasound probe during the acquisition of the first ultrasound echo signal can be obtained through methods such as firmware reading of the ultrasound image processing system and hardware parameter calibration interface, so as to provide parameter basis for subsequent accurate matching of beam interpolation model and ensure the accuracy of model matching.

[0054] The model training phase covers all combinations of first scan density and first sampling frequency in the application phase, and different first scan density and first sampling frequency can be matched with the corresponding beam interpolation model.

[0055] S240. Based on the first scanning density and the first sampling frequency, a target beam interpolation model is selected from multiple beam interpolation models, wherein the first scanning density or the first sampling frequency corresponding to different beam interpolation models is different.

[0056] The beam interpolation model can be multiple pre-trained interpolation models, each adapted to different scan densities and sampling frequencies. Different beam interpolation models correspond to different first scan densities or first sampling frequencies, and a single beam interpolation model can only enhance a combination of one first scan density and one first sampling frequency.

[0057] Optionally, since the first scan density or first sampling frequency corresponding to different beam interpolation models is different, the obtained first scan density and first sampling frequency can be compared with the combination of the first scan density and first sampling frequency corresponding to multiple beam interpolation models to select a matching target beam interpolation model from multiple beam interpolation models.

[0058] Optionally, based on the above method, the training method for the target beam interpolation model includes: acquiring second ultrasound echo signals corresponding to multiple sample objects based on a second scanning density and a second sampling frequency, wherein the second scanning density is greater than the first scanning density and the second sampling frequency is greater than the first sampling frequency; performing beamforming processing on the second ultrasound echo signals to obtain a third beam matrix; and determining a first sampling dimension based on the first scanning density and the first sampling frequency; performing sampling processing on multiple third beam matrices based on the first sampling dimension to obtain a fourth beam matrix corresponding to the third beam matrix; and training a machine learning model based on the fourth beam matrix and the third beam matrix corresponding to multiple sample objects to obtain the target beam interpolation model.

[0059] The second scan density is the high-resolution scan density used to acquire sample object signals during model training, and it is greater than the first scan density. The second sampling frequency is the high-frequency sampling frequency used to acquire sample object signals during model training, and it is greater than the first sampling frequency. The sample object can be the object being tested used for model training. The second ultrasonic echo signal can be a high-resolution ultrasonic echo signal acquired from the sample object using a high-precision second scan density and second sampling frequency. The third beam matrix can be a high-resolution beam matrix obtained after beamforming processing of the second ultrasonic echo signal. The first sampling dimension can be a low-precision data dimension determined based on the first scan density and the first sampling frequency, which may include parameters such as the number of rows and columns of data and the pixel dimension of the beam matrix. The fourth beam matrix can be a beam matrix with the same matrix dimension as the one obtained in the actual application stage, obtained by sampling and dimensionality reduction of the third beam matrix.

[0060] Specifically, second ultrasound echo signals corresponding to multiple sample objects can be acquired based on the second scanning density and the second sampling frequency. The second scan density is greater than the first scan density, and the second sampling frequency is greater than the first sampling frequency. That is, the second scan density can be understood as a high-resolution scan density that exceeds the normal range of use, and the second sampling frequency can be understood as a high-frequency sampling frequency that exceeds the normal range of use.

[0061] Since ultrasound probes may detect various types and structures of objects in practical applications, data from a single sample object can easily lead to one-sided model training and weak generalization ability. Therefore, during the training phase, data from multiple categories of sample objects, such as different organs and different sections, can be acquired to enrich the coverage of the training dataset and improve the comprehensiveness and versatility of model training. At the same time, all training samples are acquired based on a unified and fixed second scan density and second sampling frequency. As a result, the overall data dimension of the second ultrasound echo signals corresponding to multiple sample objects is completely consistent, with differences only in internal tissue features and structural data content. This ensures the uniformity of the dataset specifications. For example, for heart sample objects, multiple sections such as the left ventricular long axis section and the apical four-chamber section can be acquired to achieve data coverage of the same organ in multiple scenarios and improve the model's ability to optimize fine tissue structures.

[0062] Because the propagation speed of ultrasound in a medium is a constant and is not affected by scanning or sampling parameters, directly using a high-resolution second scanning density for scanning acquisition at the first scanning density within the conventional range of the ultrasound probe would significantly increase the amount of data acquired per frame and the scanning time, resulting in a substantial decrease in the imaging frame rate. Ultimately, the frame rate would be lower than the standard frame rate required for conventional use, failing to meet the application requirements of real-time ultrasound imaging. Furthermore, the extremely high second sampling frequency would generate massive amounts of raw data in a single acquisition, significantly consuming system storage, computing power, and transmission bandwidth, resulting in severe hardware resource overhead. The software and hardware configuration of conventional ultrasound image processing systems cannot support the continuous and stable operation of such ultra-high parameters. Consequently, the ultra-high precision second scanning density and second sampling frequency cannot be directly applied to conventional imaging scenarios and are only suitable for model training scenarios. High-precision acquisition of the second scanning density and second sampling frequency can be achieved by developing dedicated parameter programs, customized software modules, or high-configuration hardware versions for the training phase. Moreover, the specific parameter values ​​of the second scanning density and second sampling frequency can be flexibly set according to the actual business scenario requirements.

[0063] Based on the second ultrasonic echo signal and the classical sound field propagation laws, the second ultrasonic echo signal can be analyzed. Classical beamforming techniques are used to perform beamforming processing, converting the raw echo electrical signal into structured beam matrix data to obtain the corresponding third beam matrix. The third beam matrix may have dimensions of... A two-dimensional matrix, or a matrix with dimension 1. A three-dimensional matrix.

[0064] The data dimension of the third beam matrix is ​​determined by the scanning acquisition dimension of the ultrasound probe. Without any additional dimensionality upscaling or downscaling during the entire data processing, the dimension specification remains unchanged from the original acquisition state. That is, if the second ultrasound echo signal... It is generated by a two-dimensional planar scan of the target object by an ultrasonic probe, then Dimensions If the second ultrasonic echo signal Generated by a three-dimensional spatial scan of the target object using an ultrasonic probe, then Dimensions The second ultrasound echo signals corresponding to multiple sets of sample objects can all be used to generate a third beam matrix, for example. Based on the second ultrasonic echo signal produce, Based on the second ultrasonic echo signal Generate, and so on, Based on the second ultrasonic echo signal The generated third beam matrices have the same dimension.

[0065] Optionally, in obtaining the third beam matrix, the second ultrasonic echo signal can first be beamformed to obtain the third initial beam matrix, and then preprocessed to obtain a high-quality third beam matrix. The preprocessing operations used in the training phase can be consistent with those in the application phase, or they can be adaptively adjusted according to the characteristics of the training data. The preprocessing operations include at least one of the following: bandpass filtering, sampling, interpolation, modulation, demodulation, and other classical acoustic processing methods.

[0066] Simultaneously, multiple third initial beam matrices have the same dimension, and each third initial beam matrix corresponds one-to-one with the preprocessed third beam matrix. Without additional dimension-up or down processing in the intermediate stages, if the third initial beam matrix has a dimension of... If the matrix is ​​a two-dimensional matrix, then the third beam matrix is ​​of dimension 2. A two-dimensional matrix; if the third initial beam matrix is ​​a two-dimensional matrix; If the matrix is ​​a three-dimensional matrix, then the third beam matrix is ​​of dimension 1. The three-dimensional matrix maintains its dimensionality, effectively ensuring the standardization of the training dataset.

[0067] Due to the third beam matrix High-precision echo signals acquired by high scan density and high sampling frequency The processed result is therefore the third beam matrix. It has a resolution that exceeds the requirements of normal working conditions. In order to achieve a high degree of matching between the training phase and the actual application phase, and to ensure that the model can accurately adapt to the sampling parameters used in normal use, the first sampling dimension under normal use can be determined based on the first scan density and the first sampling frequency, so as to determine the input dimension corresponding to the current beam interpolation model.

[0068] Based on the determination of the first sampling dimension, multiple third beam matrices can be processed according to the first sampling dimension. Sampling is performed separately to simulate a real low-precision acquisition scenario in order to obtain the fourth beam matrix corresponding to the third beam matrix. This simulates the data state during the application phase. The fourth beam matrix is ​​generated by sampling and dimensionality reduction of the corresponding third beam matrix, such as... based on Sampling based on Generate by sampling, and so on. based on Sampling, in the wrong If additional dimension scaling operations are performed, For dimension A two-dimensional matrix, then For dimension A two-dimensional matrix, if For dimension A two-dimensional matrix, then For dimension The dimensions of the third-dimensional matrix and the fourth beam matrix are completely consistent with the dimensions of the beam matrix generated using the first scanning density and the first sampling frequency in the actual application stage, to ensure that the data distribution corresponds between the training stage and the application stage. .

[0069] Finally, the low-precision fourth beam matrix corresponding to multiple sample objects can be... As model input, a high-precision, high-resolution third beam matrix As model output, each set of fourth beam matrices and its corresponding third beam matrix together constitute a set of training samples, for example... and Together they form a training sample. and Together they form a training sample, and so on. and These multiple sample objects together form a training sample. The machine learning model is iteratively trained, its parameters are updated, and its features are learned based on the training sample constructed from multiple sample objects. This allows the model to fully grasp the mapping rules from low-precision sparse beam data to high-precision dense beam data, the rules for detail completion, and the logic for noise suppression, so as to obtain the target beam interpolation model.

[0070] Based on the above scheme, optionally, during the training process of the target beam interpolation model, the target beam interpolation model is parameter adjusted based on the following loss function: ; in, Represents the loss function; The model parameters represent the target beam interpolation model, which may include core variables such as weights and biases that can be iteratively updated within the target beam interpolation model. This represents the loss kernel function, which is used to accurately measure the deviation characteristics between two sets of beam matrix data, thereby improving the targeting of loss calculation. This represents the difference metric operator, used to calculate the difference and error between the model-predicted beam data and the actual beam data; The model parameters are: The target beam interpolation model; Indicates the first The fourth beam matrix of each sample object; Indicates the first The third beam matrix of each sample object; Indicates the first The weight matrix of each sample object is used to balance the training contribution of different sample objects; Represents the regularization coefficient; The model parameters are: The regularization term; Indicates the number of sample objects.

[0071] The model parameters can be expressed by the following formula: Target beam interpolation model: ; in, Indicates based on the first The third beam matrix of each sample object is obtained through training, and the model parameters are: Target beam interpolation model; Indicates the first A third beam matrix; This is the output decoding layer of the target beam interpolation model; This represents the intermediate feature processing layer of the target beam interpolation model. ; This represents the input coding layer of the target beam interpolation model.

[0072] Optionally, the target beam interpolation model can adopt at least one of the following network structures: Transformer network, ConvNext convolutional next-generation network, UNet U-shaped semantic segmentation network, and other deep learning network structures, which can be flexibly determined according to the actual business scenario requirements.

[0073] The model is trained using the fourth and third beam matrices corresponding to the aforementioned multiple sample objects, along with the loss function, to continuously reduce the error between the model's predicted data and the actual data. The parameters are determined by finding a minimum or near-minimum value across the entire parameter space. The model parameters can be represented by the following formula. : ; Substituting the loss function into the final model parameter formula yields the mathematical expression for the model training process: ; The model parameters of the target beam interpolation model obtained through training are as follows: , , Corresponding to the parameters of the input coding layer, intermediate feature processing layer, and output decoding layer of the target beam interpolation model, the optimal model parameters are... Substituting these values ​​into the expression of the target beam interpolation model, we get: ; in, The parameters in the target beam interpolation model are: The output decoding layer; The parameters in the target beam interpolation model are: The intermediate feature processing layer ; The parameters in the target beam interpolation model are: The input encoding layer.

[0074] like Figure 5 As shown, Figure 5 The image on the left is the original ultrasound image of the left ventricle without target beam interpolation model processing. The image suffers from low resolution, blurred tissue edges, loss of texture details, and significant random noise interference. Figure 5 The image on the right is a long-axis ultrasound image of the left ventricle of the heart after processing with the target beam interpolation model. As can be seen from the comparison, the target beam interpolation model can significantly improve the overall resolution of the ultrasound echo signal, effectively suppress imaging noise, remove clutter interference, greatly enrich the texture details and boundary features of human tissues, and significantly improve the clarity of ultrasound images.

[0075] S250. Based on the target beam interpolation model, the first beam matrix is ​​interpolated to obtain the second beam matrix.

[0076] S260. Construct an ultrasound image of the target object based on the second beam matrix.

[0077] The technical solution of this invention firstly acquires the first scanning density and the first sampling frequency used when acquiring the first ultrasonic echo signal; accurately acquires the sampling parameters during the signal acquisition stage, providing an accurate matching basis for subsequent model matching; then, based on the first scanning density and the first sampling frequency, a target beam interpolation model is selected from multiple beam interpolation models, wherein different beam interpolation models correspond to different first scanning densities or first sampling frequencies; and the corresponding model is matched according to the actual sampling parameters to achieve accurate matching of the interpolation scheme, thereby improving the rationality and adaptability of data interpolation.

[0078] Example 3 Figure 6 This is a schematic diagram of an ultrasound image processing system provided in Embodiment 3 of the present invention. This system is used to execute the ultrasound image processing method provided in any of the above embodiments. This system and the ultrasound image processing methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the ultrasound image processing system can be found in the embodiments of the ultrasound image processing methods described above. Figure 6As shown, the system includes: an ultrasonic probe 310, an ultrasonic circuit board 320, and an ultrasonic image processing module 330.

[0079] The system includes an ultrasonic probe for acquiring a first ultrasonic echo signal corresponding to a target object; an ultrasonic circuit board for performing beamforming processing on the first ultrasonic echo signal to obtain a first beam matrix; an ultrasonic image processing module for interpolating the first beam matrix based on a target beam interpolation model to obtain a second beam matrix; and an ultrasonic image corresponding to the target object constructed based on the second beam matrix.

[0080] The technical solution of this invention involves the following steps: First, an ultrasound probe 310 acquires a first ultrasound echo signal corresponding to the target object; this echo signal reflects the acoustic impedance distribution information within the target object, providing data support for subsequent ultrasound image construction. Next, an ultrasound circuit board 320 performs beamforming processing on the first ultrasound echo signal to obtain a first beam matrix; the echo signal is regularized into a structured beam matrix, achieving dynamic focusing and deflection of the sound beam and optimizing signal quality. Then, an ultrasound image processing module 330 interpolates the first beam matrix based on a target beam interpolation model to obtain a second beam matrix; interpolation based on the target beam interpolation model refines the signal dimensions, achieving super-resolution reconstruction of the beam space and significantly improving the horizontal and vertical resolution of the final generated image. Finally, the ultrasound image processing module 330 constructs an ultrasound image corresponding to the target object based on the second beam matrix; the ultrasound image constructed based on the interpolated beam matrix clearly restores the anatomical structure of the target object, enriches ultrasound image details, and improves the clarity and resolution of ultrasound imaging.

[0081] Optionally, based on the above scheme, the system further includes a first sampling information acquisition module and a model filtering module. The first sampling information acquisition module is used to acquire the first scanning density and the first sampling frequency used when acquiring the first ultrasonic echo signal before interpolating the first beam matrix based on the target beam interpolation model to obtain the second beam matrix. The model filtering module is used to filter out a target beam interpolation model from multiple beam interpolation models based on the first scanning density and the first sampling frequency, wherein different beam interpolation models correspond to different first scanning densities or first sampling frequencies.

[0082] Optionally, based on the above scheme, the system further includes a second sampling information acquisition module, a sampling dimension determination module, a sampling module, and a model training module. The second sampling information acquisition module is used to acquire second ultrasound echo signals corresponding to multiple sample objects based on a second scanning density and a second sampling frequency, wherein the second scanning density is greater than a first scanning density, and the second sampling frequency is greater than the first sampling frequency. The sampling dimension determination module is used to perform beamforming processing on the second ultrasound echo signals to obtain a third beam matrix, and to determine a first sampling dimension based on the first scanning density and the first sampling frequency. The sampling module is used to perform sampling processing on multiple third beam matrices based on the first sampling dimension to obtain a fourth beam matrix corresponding to the third beam matrix. The model training module is used to train a machine learning model based on the fourth beam matrix and the third beam matrix corresponding to multiple sample objects to obtain the target beam interpolation model.

[0083] Based on the above scheme, optionally, during the training process of the target beam interpolation model, the target beam interpolation model is parameter adjusted based on the following loss function: ; in, Represents the loss function; These represent the model parameters of the target beam interpolation model; Represents the loss kernel function; Represents the difference measure operator; The model parameters are: The target beam interpolation model; Indicates the first The fourth beam matrix of each sample object; Indicates the first The third beam matrix of each sample object; Indicates the first Weight matrix of each sample object; Represents the regularization coefficient; The model parameters are: The regularization term; Indicates the number of sample objects.

[0084] Based on the above scheme, optionally, the ultrasonic probe 310 includes an echo signal acquisition submodule. The echo signal acquisition submodule is used to emit a first ultrasonic wave toward the target object based on a first scanning density, and to receive the first ultrasonic echo signal of the first ultrasonic wave based on a first sampling frequency.

[0085] Based on the above scheme, optionally, the ultrasound image processing module 330 includes an ultrasound image construction submodule. The ultrasound image construction submodule is used to perform post-processing operations based on the second beam matrix to construct an ultrasound image; wherein the post-processing operations include at least one of the following: signal envelope calculation, pixel map conversion, velocity map conversion, and time-domain filtering.

[0086] Based on the above scheme, optionally, the ultrasonic circuit board 320 includes a first beam matrix construction submodule and a second beam matrix construction submodule. The first beam matrix construction submodule is used to perform beamforming processing on the first ultrasonic echo signal to obtain a first initial beam matrix; the second beam matrix construction submodule is used to perform preprocessing operations on the first initial beam matrix to obtain a first beam matrix; wherein the preprocessing operations include at least one of the following: bandpass filtering, sampling, interpolation, modulation, and demodulation.

[0087] The ultrasound image processing system provided in this embodiment of the invention can execute the ultrasound image processing method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0088] Example 4 Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0089] like Figure 7As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0090] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0091] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as ultrasound image processing methods.

[0092] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0093] In some embodiments, the ultrasound image processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the ultrasound image processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the ultrasound image processing method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0099] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0100] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0101] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An ultrasound image processing method, characterized in that, include: The first ultrasonic echo signal corresponding to the target object is acquired based on the ultrasonic probe; The first ultrasonic echo signal is subjected to beamforming processing to obtain a first beam matrix; The first beam matrix is ​​interpolated based on the target beam interpolation model to obtain the second beam matrix; An ultrasound image corresponding to the target object is constructed based on the second beam matrix.

2. The ultrasound image processing method according to claim 1, characterized in that, Before interpolating the first beam matrix based on the target beam interpolation model to obtain the second beam matrix, the method further includes: Obtain the first scan density and the first sampling frequency used when acquiring the first ultrasonic echo signal; The target beam interpolation model is selected from multiple beam interpolation models based on the first scanning density and the first sampling frequency. The first scanning density or the first sampling frequency is different for different beam interpolation models.

3. The ultrasound image processing method according to claim 2, characterized in that, The training method for the target beam interpolation model includes: The second ultrasound echo signals corresponding to multiple sample objects are acquired based on the second scanning density and the second sampling frequency, wherein the second scanning density is greater than the first scanning density and the second sampling frequency is greater than the first sampling frequency; The second ultrasonic echo signal is subjected to beamforming processing to obtain a third beam matrix, and a first sampling dimension is determined based on the first scanning density and the first sampling frequency. Based on the first sampling dimension, multiple third beam matrices are sampled respectively to obtain a fourth beam matrix corresponding to the third beam matrix; The machine learning model is trained based on the fourth beam matrix and the third beam matrix corresponding to multiple sample objects to obtain the target beam interpolation model.

4. The ultrasound image processing method according to claim 1, characterized in that, During the training process of the target beam interpolation model, the target beam interpolation model is parameter-adjusted based on the following loss function: ； in, Represents the loss function; These represent the model parameters of the target beam interpolation model; Represents the loss kernel function; Represents the difference measure operator; The model parameters are: The target beam interpolation model; Indicates the first The fourth beam matrix of each sample object; Indicates the first The third beam matrix of each sample object; Indicates the first Weight matrix of each sample object; Represents the regularization coefficient; The model parameters are: The regularization term; Indicates the number of sample objects.

5. The ultrasound image processing method according to claim 1, characterized in that, The first ultrasonic echo signal corresponding to the target object acquired based on the ultrasonic probe includes: A first ultrasonic wave is emitted toward the target object based on a first scanning density, and a first ultrasonic echo signal is received based on a first sampling frequency.

6. The ultrasound image processing method according to claim 1, characterized in that, The step of constructing the ultrasound image corresponding to the target object based on the second beam matrix includes: Post-processing operations are performed based on the second beam matrix to construct an ultrasound image; wherein the post-processing operations include at least one of the following: signal envelope processing, pixel map conversion processing, velocity map conversion processing, and time-domain filtering processing.

7. The ultrasound image processing method according to claim 1, characterized in that, The beamforming process of the first ultrasonic echo signal to obtain a first beam matrix includes: The first ultrasonic echo signal is subjected to beamforming processing to obtain a first initial beam matrix; The first initial beam matrix is ​​preprocessed to obtain a first beam matrix; wherein the preprocessing operation includes at least one of the following: bandpass filtering, sampling, interpolation, modulation, and demodulation.

8. An ultrasound image processing system, characterized in that, include: An ultrasonic probe is used to acquire the first ultrasonic echo signal corresponding to the target object. An ultrasonic circuit board is used to perform beamforming processing on the first ultrasonic echo signal to obtain a first beam matrix. An ultrasound image processing module is used to interpolate the first beam matrix based on a target beam interpolation model to obtain a second beam matrix; and to construct an ultrasound image corresponding to the target object based on the second beam matrix.

9. An ultrasonic imaging device, characterized in that, The ultrasound imaging device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the ultrasound image processing method according to any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the ultrasound image processing method as described in any one of claims 1-7.

Images