Ultrasonic imaging elastic parameter display method and device, equipment and storage medium

Abstract

The invention relates to the field of ultrasonic diagnosis, and discloses an ultrasonic imaging elastic parameter display method, device and equipment and a storage medium, the method comprises the following steps: applying pressure to current tissue through a target probe on ultrasonic diagnosis equipment to obtain ultrasonic images of the current tissue under different pressures; determining a processing strategy of the ultrasonic image according to the tissue type of the current tissue; processing the ultrasonic images under different pressures based on the processing strategy to obtain a tissue boundary and an elastic parameter; and displaying the ultrasonic image, the tissue boundary and the elastic parameter to a feedback system. According to the invention, the problem of lack of tissue elasticity meticulous quantification in the existing ultrasonic elastography technology is solved.

Description

Technical Field

[0001] This invention relates to the field of ultrasound diagnostics, and more specifically to a method, apparatus, device, and storage medium for displaying elastic parameters of ultrasound imaging. Background Technology

[0002] Traditional ultrasound elastography relies primarily on color coding of images to qualitatively represent the elastic properties of tissues. While this method provides basic elasticity comparisons, it cannot achieve precise quantification of tissue elasticity parameters. In clinical practice, physicians typically infer tissue stiffness by visually assessing color changes, leading to diagnostic results that are highly dependent on subjective experience and lack objective, standardized quantification. Although existing technologies can provide some elasticity information, their limitations in imaging principles and processing methods make it difficult to capture subtle differences in tissue deformation, thus affecting the accuracy and reliability of lesion identification.

[0003] The main shortcoming of existing ultrasound elastography technology lies in the lack of detailed quantification of tissue elasticity. It cannot automatically generate accurate elasticity parameters through image acquisition under multiple pressure conditions and adaptive processing strategies. Traditional methods typically only provide static elasticity images and do not involve dynamically adjusting processing strategies according to different tissue types. This results in insufficiently comprehensive and accurate acquisition of elasticity parameters, affecting the objectivity and consistency of diagnosis. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device, and storage medium for displaying elastic parameters of ultrasound imaging, in order to solve the problem of lack of detailed quantification of tissue elasticity in existing ultrasound elastography technology.

[0005] In a first aspect, embodiments of the present invention provide a method for displaying elastic parameters in ultrasound imaging, the method comprising: Pressure is applied to the current tissue using a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures. The processing strategy for the ultrasound image is determined based on the current tissue type. Based on the aforementioned processing strategy, ultrasound images under different pressures are processed to obtain tissue boundaries and elastic parameters. The ultrasound image, the tissue boundary, and the elasticity parameter are displayed to the feedback system.

[0006] Furthermore, the step of applying pressure to the current tissue using a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures includes: Detect whether the target probe on the ultrasound diagnostic equipment is in a connected state; If in a connected state, an initial ultrasound image of the current tissue is acquired through the target probe; Analyze the initial ultrasound image to obtain the tissue type of the current tissue; Based on the tissue type, the target probe is controlled to apply pressure to the current tissue, thereby obtaining ultrasound images of the current tissue under different pressures.

[0007] Furthermore, the step of controlling the target probe to apply pressure to the current tissue according to the tissue type to obtain ultrasound images of the current tissue under different pressures includes: Query the pressure regulation parameters associated with the tissue type; The target probe is controlled to gradually apply pressure to the current tissue according to the pressure control parameters, and the current pressure value is monitored. When the current pressure value reaches the specified pressure value in the pressure control parameters, the ultrasound diagnostic device is controlled to acquire ultrasound images until the maximum pressure value in the pressure control parameters is reached, thereby obtaining ultrasound images under different pressures.

[0008] Furthermore, the processing of ultrasound images under different pressures based on the aforementioned processing strategy to obtain tissue boundaries and elastic parameters includes: For the tissue boundary, the network architecture in the processing strategy is used to extract morphological features at different levels in the ultrasound image; The pixels in the ultrasound image that meet the boundary conditions are determined based on the morphological characteristics. The tissue boundary is constructed using the pixels that meet the boundary conditions.

[0009] Furthermore, the processing of ultrasound images under different pressures based on the aforementioned processing strategy to obtain tissue boundaries and elastic parameters includes: For the elastic parameters, the elastic model in the processing strategy is used to extract the deformation information of the current tissue under different pressures from the ultrasound image; Establish the correlation between pressure and strain of the current tissue based on the deformation information; The resilience parameters of the current organization are calculated based on the aforementioned relationship.

[0010] Furthermore, after calculating the resilience parameters of the current organization based on the aforementioned correlation, the method further includes: Obtain simulation parameter data of the simulated tissue corresponding to the current tissue under different pressures; Based on the simulation parameter data, identify the target parameters in the elastic parameters where deviations exist; When the deviation of the target parameter reaches a preset standard, the elastic parameter is corrected to obtain the corrected elastic parameter.

[0011] Furthermore, displaying the ultrasound image, the tissue boundary, and the elastic parameters to the feedback system includes: The color mapping rules for the elasticity graph are determined based on the current organization type. Based on the color mapping rule, the elastic parameters and tissue boundaries of each pixel in the ultrasound image are labeled to obtain the target elasticity map; The target elasticity graph is displayed to the feedback system associated with the ultrasound diagnostic device.

[0012] Secondly, embodiments of the present invention provide a display device for ultrasonic imaging elastic parameters, the device comprising: An application module is used to apply pressure to the current tissue through a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures. A determination module is used to determine the processing strategy for the ultrasound image based on the tissue type of the current tissue; The processing module is used to process ultrasound images under different pressures based on the processing strategy to obtain tissue boundaries and elastic parameters. The display module is used to display the ultrasound image, the tissue boundary, and the elastic parameters to the feedback system.

[0013] Thirdly, embodiments of the present invention provide a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, the computer instructions being used to cause a computer to perform the method described in the first aspect or any corresponding embodiment thereof.

[0015] The method provided in this application has the following beneficial effects: The method provided in this application applies different pressures to the current tissue using a target probe and acquires corresponding ultrasound images, enabling the acquisition of more comprehensive tissue deformation data under dynamic pressure conditions, laying a data foundation for subsequent accurate quantification of elastic parameters. By adaptively determining the image processing strategy according to the tissue type, the algorithm's adaptability to different tissue characteristics is effectively improved, enhancing the adaptability and accuracy of elastic parameter calculation. By analyzing and processing multi-pressure images based on the processing strategy, accurate identification of tissue boundaries and reliable extraction of elastic parameters are achieved, significantly improving the objectivity and repeatability of parameter calculation. Finally, by integrating and displaying ultrasound images, tissue boundaries, and elastic parameters in the feedback system, intuitive and quantitative diagnostic evidence is provided, effectively reducing the reliance on subjective experience in the diagnostic process and improving the efficiency and reliability of clinical decision-making. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for displaying elastic parameters in ultrasound imaging according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating another method for displaying elastic parameters in ultrasound imaging according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a display device for displaying elastic parameters of ultrasound imaging according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] According to embodiments of the present invention, a method, apparatus, device, and storage medium for displaying elastic parameters of ultrasound imaging are provided. It should be noted that the steps shown in the flowcharts in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0020] This embodiment provides a method for displaying elastic parameters in ultrasound imaging. Figure 1 This is a flowchart of a method for displaying elastic parameters in ultrasound imaging according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Apply pressure to the current tissue using the target probe on the ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures.

[0021] In this embodiment, a target probe integrated with a pressure sensor on an ultrasound diagnostic device is programmed to automatically and progressively press on the current tissue according to preset pressure control parameters (such as initial pressure, maximum pressure, and incremental pressure). During the pressing process, the pressure sensor inside the probe monitors the current pressure value in real time, and when the pressure reaches each preset specified pressure value, it synchronously triggers the ultrasound transmitting and receiving circuits to acquire ultrasound images under that stable pressure state. This process continues from the initial pressure to the maximum pressure value, ultimately obtaining a sequence of ultrasound images acquired at different known pressure levels, providing multi-frame image data recording the dynamic deformation of the tissue for subsequent analysis.

[0022] As an example, in the examination of breast tissue, the probe pressure was controlled from 0.5 kPa, gradually increasing to 2.0 kPa in 0.2 kPa increments. When the pressure sensor feedback value stabilized at 0.5 kPa, 0.7 kPa, 0.9 kPa and up to 2.0 kPa, respectively, B-mode ultrasound images were acquired, ultimately obtaining an ultrasound image sequence containing 8 different pressure points.

[0023] Step S102: Determine the processing strategy for the ultrasound image based on the tissue type of the current tissue.

[0024] In this embodiment, based on the tissue type (such as thyroid or breast) identified after analyzing the initial ultrasound image, the processing strategy most suitable for that type is queried and invoked from a pre-set strategy library. This processing strategy is a configuration set that explicitly specifies the specific algorithms and parameters to be used in subsequent processing. For example, it includes a specific network architecture for boundary segmentation (such as DeepLabV3+ for complex breast structures), an elastic model for calculating deformation (such as a specific strain estimation algorithm for the liver), and the normal reference range of elastic parameters for that tissue type. This ensures that different tissues can obtain the optimal processing flow. For instance, when the current tissue is identified as thyroid, a thyroid-specific processing strategy is immediately invoked. This strategy specifies the use of a U-Net network trained on a large number of thyroid ultrasound images for nodule boundary segmentation, and selects a high-sensitivity elastic model suitable for superficial organs to calculate Young's modulus, while setting the modulus display range to 0-100 kPa to accommodate the stiffness characteristics of thyroid tissue.

[0025] Step S103: Based on the processing strategy, the ultrasound images under different pressures are processed to obtain the tissue boundary and elastic parameters.

[0026] In this embodiment, ultrasound image sequences acquired under different pressures are processed according to a determined processing strategy. The processing executes two core tasks in parallel or sequentially: first, morphological features are extracted using a network architecture specified by the strategy, and precise tissue boundaries are constructed by identifying pixels that meet boundary conditions; second, deformation information is extracted using an elastic model specified by the strategy, establishing the correlation between pressure and strain, and finally calculating quantitative elastic parameters (primarily Young's modulus). This step transforms the original image sequence into boundary contours and hardness values ​​with clear physical meaning.

[0027] Step S104: Display the ultrasound image, tissue boundaries, and elasticity parameters to the feedback system.

[0028] In this embodiment, an ultrasound image (typically a B-mode image used as a background), the calculated tissue boundary (represented by a highlighted outline), and the elastic parameters (represented by a pseudo-color map) are fused to generate a composite target elasticity map. This map is then rendered in real-time and displayed on the feedback system associated with the ultrasound diagnostic device (typically the device's main display). This integrated display provides the most intuitive diagnostic view, allowing simultaneous observation of the tissue's anatomical structure, the precise extent of the target area, and the quantitative distribution of stiffness within that area.

[0029] As an example, the fused image is generated as follows: using a grayscale B-mode image as a background, a bright white curve is used to outline the tumor tissue boundary. Simultaneously, based on the Young's modulus values ​​of various points within the tumor, pseudo-color filling is performed according to a "red-yellow-green-blue" color spectrum (red represents the softest, blue represents the hardest). This colored target elasticity map is displayed in real-time on the ultrasound device's screen, allowing the viewer to see the tumor's hardness distribution and read specific modulus values ​​to aid in diagnosis.

[0030] In this embodiment of the application, pressure is applied to the current tissue using a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures, including: Step A1: Check whether the target probe on the ultrasound diagnostic equipment is connected.

[0031] Specifically, after the system powers on or initiates elastography mode, the main control unit sends a hardware handshake signal or query command to the probe interface via the device's internal data bus (such as PCIe, USB, etc.). Upon receiving this signal, the microcontroller inside the target probe returns a confirmation data packet containing its unique identifier (such as probe model and serial number) and current status (such as sensor working normally and temperature being normal). By parsing this data packet, the system software not only confirms the physical connection is secure but also verifies whether the probe is a target probe that supports elastography (e.g., a dedicated probe integrating a pressure sensor). If the connection is successful, the driver and preset parameter values ​​matching the probe model are loaded; if no valid response is detected, the system will interrupt subsequent processes and display an error message "probe not connected" or "probe incompatible" on the user interface, ensuring that the hardware foundation for data acquisition is reliable and correct.

[0032] Step A2: If the connection is established, the initial ultrasound image of the current tissue is acquired through the target probe.

[0033] Specifically, after confirming probe connection is complete, a standard ultrasound scan is performed to obtain basic anatomical images. The ultrasound transmitting circuit drives the transducer array of the target probe to emit one or more ultrasound pulses into the human tissue and receives the returned echo signals. These radio frequency echo signals are amplified and filtered by the analog front end inside the probe, then focused and synthesized by the beamsynthesizer inside the ultrasound host. Finally, through digital signal processing (such as logarithmic compression, edge enhancement, etc.), a two-dimensional grayscale ultrasound image, i.e., the initial ultrasound image, is generated. This image is usually a conventional B-mode image, whose main purpose is to provide a spatial framework and initial tissue morphology information for subsequent analysis. At this time, the pressure applied to the probe is the initial stable pressure held by the operator, and active, programmed pressure control has not yet begun.

[0034] Step A3: Analyze the initial ultrasound image to obtain the tissue type of the current tissue.

[0035] Specifically, the initial ultrasound image is input into a pre-trained image classification model. This model can be a convolutional neural network, trained on a massive dataset of ultrasound images labeled with tissue types (such as "thyroid," "breast," and "liver"). The network automatically extracts deep features from the image, such as texture features (uniformity, roughness), morphological features (organ contours, anatomical structures), and echo characteristics (echo intensity, distribution), and classifies the type of the "current tissue" probabilistically accordingly. For example, if the image is identified as having typical thyroid gland features and adjacent carotid artery structures, it is classified as "thyroid tissue." The automatic identification result, as key contextual information, is directly used to trigger a pre-defined set of elastography parameters that match the tissue type.

[0036] Step A4: Control the target probe to apply pressure to the current tissue according to the tissue type to obtain ultrasound images of the current tissue under different pressures.

[0037] Specifically, based on the identified tissue type, the system queries and retrieves the associated pressure control parameters from an internally stored configuration database. These parameters are predefined using expert experience and experimental data, and typically include: the initial pressure application value, the termination value (maximum pressure value), the step increment, the time required to maintain stability at each pressure point, and the maximum pressure threshold set to ensure patient safety and data quality. Subsequently, the control unit drives the pressure application module integrated with or associated with the target probe (e.g., controlling the displacement of a miniature linear actuator within the probe, or adjusting the pressure on the probe contact surface via a pneumatic / hydraulic device) to apply programmed, progressive pressure to the current tissue according to the parameter settings. During the pressure application, the pressure sensor integrated into the probe monitors and provides feedback on the pressure value in real time. Whenever the pressure reaches a preset specified pressure value (i.e., a step point), the pressure is briefly stabilized, and the ultrasound diagnostic equipment is simultaneously triggered to acquire an ultrasound image at that stable pressure. This process is repeated from the initial pressure to the maximum pressure value, thereby acquiring a sequence of ultrasound images at different known pressure levels, providing standard multi-gradient input data for calculating the elastic deformation of the tissue.

[0038] In this embodiment of the application, the target probe is controlled to apply pressure to the current tissue according to the tissue type to obtain ultrasound images of the current tissue under different pressures, including: Step A401: Query the pressure regulation parameters associated with the tissue type.

[0039] Specifically, based on the identified tissue type (such as "thyroid" or "breast"), the system queries a pre-configured database of pressure control parameters. This database is essentially a lookup table, pre-setting optimized pressure control parameters for each known tissue type. These parameters include at least: the initial pressure application value, the final pressure value (i.e., the maximum pressure value), the increment (i.e., the difference between specified pressure values), the time required to maintain stability at each pressure point, and the maximum rate of pressure change set to ensure patient safety and data quality. For example, for breast tissue, the parameters can be set to start at 0.5 kPa, increasing in 0.3 kPa increments to 2.0 kPa; while for thyroid tissue, due to its more superficial and fragile nature, the parameters can be set to start at 0.2 kPa, increasing in 0.1 kPa increments to a maximum of 1.0 kPa. This approach ensures that subsequent compression procedures adapt to the physiological characteristics and mechanical responses of different tissues, obtaining the most effective elastic deformation data while ensuring safety.

[0040] Step A402: Control the target probe to gradually apply pressure to the current tissue according to the pressure control parameters, and monitor the current pressure value.

[0041] Specifically, based on the retrieved pressure control parameters, a closed-loop control circuit sends a control signal to the pressure application module (such as a micro motor, linear actuator, or piezoelectric ceramic actuator) integrated with or associated with the target probe. This signal drives the pressure application module to apply pressure smoothly and gradually to the current tissue according to the preset pressure change rate in the parameters, thereby forming a continuous pressure gradient from the initial pressure to the maximum pressure value. During this process, the pressure sensor integrated inside the target probe (such as a microelectromechanical system piezoresistive or capacitive sensor) collects the pressure signal of the contact surface in real time at a high frequency (e.g., thousands of times per second) and converts it into an electrical signal. After analog-to-digital conversion and calibration, this signal is read in real time by the system's main control unit, and this continuously updated reading is the current pressure value. This current pressure value is compared in real time with the expected value in the pressure control parameters, and the signal output to the pressure application module is dynamically adjusted through control algorithms such as PID (proportional-integral-derivative) to ensure the linearity and stability of pressure loading, prevent sudden pressure changes from causing discomfort or damage to the tissue, and provide accurate criteria for triggering image acquisition.

[0042] Step A403: When the current pressure value reaches the specified pressure value in the pressure control parameters, control the ultrasound diagnostic equipment to acquire ultrasound images until the maximum pressure value in the pressure control parameters is reached, and obtain ultrasound images under different pressures.

[0043] Specifically, during the gradual application of pressure according to the pressure control parameters, the pressure sensor integrated into the probe continuously feeds back the current pressure value to the main control system. The software compares this feedback value in real time with the specified pressure values ​​retrieved from the parameter table (i.e., a preset pressure step sequence, such as 0.2 kPa, 0.3 kPa, 0.4 kPa, etc.). Once the error between the current pressure value and a specified pressure value falls within the allowable range (e.g., ±0.02 kPa), a synchronization trigger signal is sent to the acquisition module of the ultrasound diagnostic device. This signal commands the device to acquire one frame of ultrasound image under the current stable pressure state. After acquisition, the pressure application module continues to operate until the pressure reaches the maximum pressure value set in the parameter table and the final image acquisition is completed, at which point it stops. Through this precise synchronization of pressure and acquisition, a sequence of ultrasound images acquired at different known, discrete, and stable pressure levels is ultimately obtained. This image sequence fully records the dynamic process of tissue deformation from slight to significant deformation, providing a standardized, high-quality data foundation for subsequent accurate calculation of strain and elastic parameters.

[0044] In this embodiment of the application, ultrasound images under different pressures are processed based on a processing strategy to obtain tissue boundaries and elastic parameters, including: Step B1: For tissue boundaries, the network architecture in the processing strategy is used to extract morphological features at different levels in the ultrasound image.

[0045] Specifically, based on the processing strategy selected for the current tissue type, a predefined network architecture (typically a deep convolutional neural network, such as U-Net or its variants) is invoked. This network takes the ultrasound image as input and propagates it forward through its multiple convolutional layers. Shallow layers primarily extract local, low-level morphological features, such as edges, gradients, and texture features; as the network deepens, deeper layers extract more global, high-level morphological features through increased receptive fields and feature combinations, such as the overall contour of organs, the shape of specific anatomical structures, and the overall morphology of lesion areas. This ability to extract features at different levels allows the network to simultaneously utilize local contextual information surrounding pixels and global semantic information of the entire image, laying a solid foundation for subsequent pixel classification.

[0046] Step B2: Determine the pixels in the ultrasound image that meet the boundary conditions based on their morphological characteristics.

[0047] Specifically, after extracting multi-level morphological features, the network uses a classifier (e.g., a 1x1 convolutional layer followed by a Softmax activation function) to determine the classification of each pixel in the ultrasound image. Boundary conditions are learned during the network's training phase; these are complex feature combination patterns used to define the typical characteristics of tissue boundaries (such as strong gradient changes in specific directions, texture contrast between different tissue types, and continuity and shape constraints consistent with anatomical knowledge). Based on the probability map of each pixel belonging to or not belonging to the boundary, by setting a probability threshold (e.g., 0.5) or using the argmax function, all pixels that meet the boundary conditions are finally identified and labeled—those most likely located at tissue boundaries.

[0048] Step B3: Construct the organization boundary using pixels that meet the boundary conditions.

[0049] Specifically, since the directly output pixels that meet the boundary conditions may be discrete, discontinuous, or even noisy, they need to be optimized and integrated. In the implementation, morphological operations (such as closing operations) are first used to connect adjacent boundary pixels, filling small gaps. Then, edge connection algorithms or contour finding algorithms (such as boundary tracking algorithms based on eight-neighborhood connections) are used to construct one or more continuous, closed or open curved contours, i.e., the final tissue boundary. This boundary accurately delineates the spatial extent of the target tissue (such as tumors or organs) in the ultrasound image, providing an accurate region of interest for subsequent quantitative analysis of elastic parameters, and providing direct graphical data for visualization annotation on the feedback system.

[0050] In this embodiment of the application, ultrasound images under different pressures are processed based on a processing strategy to obtain tissue boundaries and elastic parameters, including: Step C1: For the elastic parameters, the elastic model in the processing strategy is used to extract the deformation information of the current tissue under different pressures from the ultrasound image.

[0051] Specifically, based on the processing strategy selected for the current tissue type, the defined elasticity model is invoked (this model encapsulates specific deformation calculation algorithms, such as displacement estimation based on optical flow or cross-correlation algorithms based on block matching). This model uses the ultrasound image from the previous pressure level as a reference frame and performs frame-by-frame comparison and analysis with subsequent ultrasound images acquired under various pressures. By calculating the positional offset of each small region (pixel block) in the image before and after the pressure change, the elasticity model can accurately extract the field representing the tissue displacement vector; this displacement field is the deformation information. This process can capture the minute, continuous deformation patterns produced by tissue under pressure, transforming imperceptible grayscale changes into quantifiable physical displacement data, providing the most crucial input for subsequently establishing stress-strain relationships.

[0052] Step C2: Establish the correlation between the current organization's stress and strain based on the deformation information.

[0053] Specifically, using the calculated deformation information (i.e., displacement field), the strain tensor (e.g., longitudinal strain εz along the pressure direction) is first calculated through spatial differentiation. Then, the pressure values ​​(which can be converted into approximate stress, assuming the contact area is known or constant) fed back from the probe's pressure sensor and recorded synchronously with each frame of the image are used as input and correlated with the calculated average strain or strain values ​​at individual points. By analyzing discrete pressure-strain data pairs throughout the entire pressurization process (from the initial pressure to the maximum pressure value), linear or nonlinear fitting algorithms (such as the least squares method) are used to establish a correlation that describes the current macroscopic mechanical response of the tissue, typically expressed as a pressure-strain curve or constitutive equation. This relationship reflects the softness or hardness of the tissue, i.e., the magnitude of the pressure required to produce a unit strain.

[0054] Step C3: Calculate the resilience parameters of the current organization based on the correlation.

[0055] Specifically, based on the established correlation (i.e., the pressure-strain curve), quantitative elastic parameters are calculated using predefined physical formulas. The most important elastic parameter is Young's modulus (E), which, under the assumption of uniaxial stress, can be calculated using the formula E = Stress / Strain, where Stress is derived from the applied pressure, and Strain is the calculated strain. For more complex models, other parameters, such as shear modulus or strain ratio, also need to be calculated. Finally, specific numerically quantified elastic parameter values ​​(usually in kilopascals kPa) are output for each pixel or region of interest in the current tissue, thus achieving an objective and accurate quantification of tissue stiffness, replacing the traditional subjective judgment based on color depth.

[0056] In this embodiment of the application, displaying ultrasound images, tissue boundaries, and elastic parameters to a feedback system includes: Step D1: Determine the color mapping rules for the elasticity graph based on the current organization type.

[0057] Specifically, based on the identified tissue type (e.g., "breast" or "thyroid"), the corresponding color mapping rule is queried from a pre-configured library and loaded. This rule is a lookup table that maps the numerical range of elastic parameters (e.g., Young's modulus from 0 kPa to 100 kPa) to a specific color spectrum. Different tissues, due to their varying hardness ranges between normal and diseased tissues, will be fitted with different color mapping rules to optimize display contrast. For example, for breast tissue, a spectrum from "red (soft)" to "blue (hard)" is used to distinguish between fat (soft) and malignant tumors (hard); while for thyroid tissue, a spectrum from "green (soft)" to "red (hard)" might be used to highlight the hardness variations in nodular areas. This rule also defines specific colors (e.g., bright white or yellow) and line widths for highlighting tissue boundaries, ensuring that the boundaries are clearly distinguishable in the color elasticity map.

[0058] Step D2: Based on the color mapping rules, the elastic parameters and tissue boundaries of each pixel in the ultrasound image are labeled to obtain the target elasticity map.

[0059] Specifically, the system iterates through each pixel in the ultrasound image, reading the elasticity parameter values ​​(such as Young's modulus) calculated in step C3. Then, according to color mapping rules, a corresponding color is assigned to each pixel's elasticity parameter value. For example, a pixel with a Young's modulus of 20 kPa can be colored green according to the rules. Simultaneously, the constructed tissue boundary vector data, using the boundary colors and styles defined in the rules (such as a 2-pixel-wide bright white solid line), is overlaid and rendered onto this image, which has already been colored according to the elasticity parameters. Through this color annotation of pixel elasticity parameters and graphic annotation of contour lines, the system ultimately synthesizes a target elasticity map that integrates traditional anatomical morphology (grayscale background or semi-transparent overlay of B-mode image) with quantitative elasticity information (pseudo-color), and reflects the region of interest.

[0060] Step D3: Display the target elasticity map to the feedback system associated with the ultrasound diagnostic equipment.

[0061] Specifically, the device's internal graphics rendering engine generates a target elastogram along with its corresponding colorimetric legend, which is then output to the feedback system associated with the ultrasound diagnostic equipment hardware. This feedback system typically refers to the device's main display screen, but can also include auxiliary displays or remote diagnostic terminals. Images are refreshed at extremely high frame rates to achieve real-time feedback, allowing doctors to visually see the target elastogram and conventional B-mode images (usually updated synchronously in split-screen or image fusion mode) on the screen while operating the probe. Real-time quantitative display provides immediate diagnostic information, enabling rapid lesion identification, localization, and nature assessment based on color hardness distribution and clear tissue boundaries, thus improving diagnostic efficiency and accuracy.

[0062] In the embodiments of this application, such as Figure 2 As shown, after calculating the resilience parameters of the current organization based on the correlation, the method also includes: Step S201: Obtain simulation parameter data of the current tissue under different pressures.

[0063] In this embodiment, based on the identified tissue type (e.g., "breast") and its specific anatomical structure information, a digital 3D model that highly matches the tissue in terms of geometry, size, and material properties is retrieved from a pre-stored simulation tissue model library. Subsequently, a finite element analysis solver is driven to perform mechanical simulation calculations under different pressures (i.e., pressure control parameters) completely consistent with the actual testing process. Based on the tissue's constitutive model (e.g., linear elastic or hyperelastic models) and the set nonlinear and anisotropic characteristics, the solver calculates the stress and strain distribution of each element within the model under various pressure levels. These calculated stress and strain fields, covering the entire model space, constitute the simulation parameter data used for comparison. This data represents the mechanical response that the tissue should have under an ideal model.

[0064] Step S202: Identify the target parameter with deviation in the elastic parameters based on the simulation parameter data.

[0065] In this embodiment, the measured elastic parameters of the current tissue (such as Young's modulus distribution map) calculated from ultrasound images are compared point-by-point or region-by-region with the theoretical elastic parameters corresponding to the simulated parameters at the same spatial location and pressure level. The degree of difference between the two is calculated, for example, using relative error or root mean square error as a quantitative indicator. Subsequently, based on a preset deviation threshold (i.e., a component of the preset standard), the entire comparison result is automatically scanned to identify regions or parameter points where the difference between the measured and simulated values ​​exceeds the threshold. These marked parameters with questionable reliability are the target parameters that need to be processed. For example, areas at tissue boundaries or in regions where calculation distortion is caused by signal loss are often identified as having significant deviations.

[0066] Step S203: When the deviation of the target parameter reaches the preset standard, the elastic parameter is corrected to obtain the corrected elastic parameter.

[0067] In this embodiment, a correction algorithm is triggered when the deviation of the target parameter (such as the average relative error) reaches a predefined preset standard (e.g., more than 30% of pixels in a certain area have a deviation greater than 25%). The correction operation does not simply replace the measured values ​​with simulated values, but rather employs a data fusion strategy. For example, a local smoothing constraint can be established based on the distribution trend of simulated parameter data in the area. Then, a filtering algorithm (such as anisotropic diffusion filtering) is used to optimize the original measured elastic parameters, suppressing significant outliers while preserving their overall distribution characteristics. After this processing, a set of corrected elastic parameters that are physically more reasonable and numerically more reliable is output, effectively reducing uncertainties caused by signal noise, model mismatch, or calculation errors, ultimately improving the accuracy and robustness of quantitative analysis of elastic imaging.

[0068] This embodiment also provides a display device for ultrasound imaging elastic parameters, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0069] This embodiment provides a display device for ultrasonic imaging elastic parameters, such as... Figure 3 As shown, it includes: The application module 31 is used to apply pressure to the current tissue through the target probe of the ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures. The determination module 32 is used to determine the processing strategy of the ultrasound image based on the tissue type of the current tissue; Processing module 33 is used to process ultrasound images under different pressures based on processing strategies to obtain tissue boundaries and elastic parameters; Display module 34 is used to display ultrasound images, tissue boundaries, and elastic parameters to the feedback system.

[0070] In this embodiment of the application, the application module 31 includes: The detection submodule is used to detect whether the target probe on the ultrasound diagnostic equipment is in a connected state. The acquisition submodule is used to acquire the initial ultrasound image of the current tissue through the target probe if the connection is established. The analysis submodule is used to analyze the initial ultrasound image to obtain the tissue type of the current tissue. The control submodule is used to control the target probe to apply pressure to the current tissue according to the tissue type, so as to obtain ultrasound images of the current tissue under different pressures.

[0071] In this embodiment, the control submodule is specifically used to query the pressure regulation parameters associated with the tissue type; control the target probe to gradually apply pressure to the current tissue according to the pressure regulation parameters, and monitor the current pressure value; when the current pressure value reaches the specified pressure value in the pressure regulation parameters, control the ultrasound diagnostic device to acquire ultrasound images until the maximum pressure value in the pressure regulation parameters is reached, thereby obtaining ultrasound images under different pressures.

[0072] In this embodiment of the application, the processing module 33 is specifically used to extract morphological features at different levels in the ultrasound image using the network architecture in the processing strategy for the tissue boundary; determine the pixels in the ultrasound image that meet the boundary conditions based on the morphological features; and construct the tissue boundary using the pixels that meet the boundary conditions.

[0073] In this embodiment of the application, the processing module 33 is specifically used to extract the deformation information of the current tissue under different pressures from the ultrasound image using the elastic model in the processing strategy for the elastic parameters; establish the correlation between the pressure and strain of the current tissue based on the deformation information; and calculate the elastic parameters of the current tissue based on the correlation.

[0074] In this embodiment of the application, the device further includes: a correction module, used to acquire simulation parameter data of the simulated tissue corresponding to the current tissue under different pressures; identify target parameters with deviations in the elastic parameters based on the simulation parameter data; and correct the elastic parameters when the deviation of the target parameters reaches a preset standard to obtain the corrected elastic parameters.

[0075] In this embodiment, the display module 34 is specifically used to determine the color mapping rules of the elasticity map according to the tissue type of the current tissue; to annotate the elasticity parameters of each pixel in the ultrasound image and the tissue boundary based on the color mapping rules to obtain the target elasticity map; and to display the target elasticity map to the feedback system associated with the ultrasound diagnostic device.

[0076] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0077] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0078] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0079] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device as shown by a landing page for an app. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0080] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0081] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0082] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0083] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for displaying elastic parameters in ultrasound imaging, characterized in that, The method includes: Pressure is applied to the current tissue using a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures. The processing strategy for the ultrasound image is determined based on the current tissue type. Based on the aforementioned processing strategy, ultrasound images under different pressures are processed to obtain tissue boundaries and elastic parameters. The ultrasound image, the tissue boundary, and the elasticity parameter are displayed to the feedback system.

2. The method according to claim 1, characterized in that, The step of applying pressure to the current tissue using a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures includes: Detect whether the target probe on the ultrasound diagnostic equipment is in a connected state; If in a connected state, an initial ultrasound image of the current tissue is acquired through the target probe; Analyze the initial ultrasound image to obtain the tissue type of the current tissue; Based on the tissue type, the target probe is controlled to apply pressure to the current tissue, thereby obtaining ultrasound images of the current tissue under different pressures.

3. The method according to claim 2, characterized in that, The step of controlling the target probe to apply pressure to the current tissue according to the tissue type, and obtaining ultrasound images of the current tissue under different pressures, includes: Query the pressure regulation parameters associated with the tissue type; The target probe is controlled to gradually apply pressure to the current tissue according to the pressure control parameters, and the current pressure value is monitored. When the current pressure value reaches the specified pressure value in the pressure control parameters, the ultrasound diagnostic device is controlled to acquire ultrasound images until the maximum pressure value in the pressure control parameters is reached, thereby obtaining ultrasound images under different pressures.

4. The method according to claim 1, characterized in that, The process of processing ultrasound images under different pressures based on the aforementioned processing strategy to obtain tissue boundaries and elastic parameters includes: For the tissue boundary, the network architecture in the processing strategy is used to extract morphological features at different levels in the ultrasound image; The pixels in the ultrasound image that meet the boundary conditions are determined based on the morphological characteristics. The tissue boundary is constructed using the pixels that meet the boundary conditions.

5. The method according to claim 1, characterized in that, The process of processing ultrasound images under different pressures based on the aforementioned processing strategy to obtain tissue boundaries and elastic parameters includes: For the elastic parameters, the elastic model in the processing strategy is used to extract the deformation information of the current tissue under different pressures from the ultrasound image; Establish the correlation between pressure and strain of the current tissue based on the deformation information; The resilience parameters of the current organization are calculated based on the aforementioned relationship.

6. The method according to claim 5, characterized in that, After calculating the resilience parameters of the current organization based on the aforementioned correlation, the method further includes: Obtain simulation parameter data of the simulated tissue corresponding to the current tissue under different pressures; Based on the simulation parameter data, identify the target parameters in the elastic parameters where deviations exist; When the deviation of the target parameter reaches a preset standard, the elastic parameter is corrected to obtain the corrected elastic parameter.

7. The method according to claim 1, characterized in that, The step of displaying the ultrasound image, the tissue boundary, and the elastic parameters to the feedback system includes: The color mapping rules for the elasticity graph are determined based on the current organization's organization type. Based on the color mapping rule, the elastic parameters and tissue boundaries of each pixel in the ultrasound image are labeled to obtain the target elasticity map; The target elasticity graph is displayed to the feedback system associated with the ultrasound diagnostic device.

8. A display device for ultrasonic imaging elastic parameters, characterized in that, The device includes: An application module is used to apply pressure to the current tissue through a target probe on an ultrasound diagnostic device to obtain ultrasound images of the current tissue under different pressures. A determination module is used to determine the processing strategy for the ultrasound image based on the tissue type of the current tissue; The processing module is used to process ultrasound images under different pressures based on the processing strategy to obtain tissue boundaries and elastic parameters. The display module is used to display the ultrasound image, the tissue boundary, and the elastic parameters to the feedback system.

9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images