Tissue evaluation method and apparatus, electronic device, and storage medium
By acquiring and processing ultrasound data, generating target tissue parameters, and utilizing data processing models, the problem of inaccurate tissue assessment results caused by the subjective experience of medical staff is solved, achieving more accurate and consistent tissue assessment.
Patent Information
- Application Number
- PCT/CN2024/096068
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-30
- Filing Date
- 2024-05-29
- Publication Date
- 2024-12-05
AI Technical Summary
In existing technologies, the accuracy of medical staff's assessment of tissues based on subjective experience is low, leading to differences in assessment results among different doctors for the same patient.
By acquiring ultrasound data, including ultrasound images, color Doppler ultrasound images, and elastography images, data recognition and processing are performed to generate target tissue parameters, such as ultrasound parameters, vascular parameters, and elasticity parameters. Feature extraction is then performed using an ultrasound data processing model to output evaluation results.
This approach ensures the accuracy and comprehensiveness of organizational assessment results, reduces reliance on the subjective experience of medical staff, and improves the uniformity and accuracy of assessment results.
Smart Images

Figure CN2024096068_05122024_PF_FP_ABST
Abstract
Description
Organization assessment method, device, electronic device and storage medium
[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on May 30, 2023, with application number 202310632782.X and application name “Tissue Assessment Method, Device, Electronic Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field
[0002] The present application relates to the field of tissue assessment, and in particular to a tissue assessment method, device, electronic device, and storage medium. Background Art
[0003] In the existing technology, medical staff usually use medical equipment (such as ultrasound equipment) to examine tissues such as the liver and breast, and based on the examination results and experience, conduct subjective analysis of the examined tissues to determine the evaluation results of the tissues, such as whether a lesion has occurred and the extent of the lesion.
[0004] However, this existing evaluation method is closely related to the subjectivity of medical staff. Different doctors may reach different conclusions on the same patient. Therefore, the tissue evaluation results determined by medical staff based solely on their own subjective experience are highly subjective and inaccurate.
[0005] Summary of the Invention
[0006] In view of this, the embodiments of the present application provide a tissue assessment method, device, electronic device and storage medium, which aim to solve the problem in the prior art that the tissue assessment results determined by medical staff based solely on their own subjective experience are highly subjective and inaccurate.
[0007] According to a first aspect, an embodiment of the present application provides a tissue assessment method, comprising:
[0008] Acquiring unprocessed ultrasound data corresponding to the target tissue, the unprocessed ultrasound data including at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastography image, and radiofrequency data corresponding to the elastography;
[0009] Performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue, the target tissue parameters including at least one of ultrasound parameters, blood vessel parameters, and elasticity parameters; the ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; the blood vessel parameters are used to characterize the state of blood vessels in at least one target tissue; and the elasticity parameters are used to characterize the elastic state of the target tissue;
[0010] Analyze the target tissue parameters and determine the evaluation results corresponding to the target tissue.
[0011] The tissue assessment method provided in the embodiment of the present application obtains the ultrasonic data to be processed corresponding to the target tissue, and the ultrasonic data to be processed includes at least one of an ultrasonic B-ultrasound image, a color ultrasound image, an elastic imaging image, and radiofrequency data corresponding to the elastic imaging. Then, data recognition processing is performed on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue, thereby ensuring the accuracy of the target tissue parameters generated, and ensuring the comprehensiveness and diversity of the target tissue parameters. Then, the target tissue parameters are analyzed to determine the assessment results corresponding to the target tissue, thereby ensuring the accuracy of the assessment results corresponding to the determined target tissue. The above method does not rely on the subjective experience of medical staff to determine the assessment results corresponding to the target tissue, but instead obtains the ultrasonic data to be processed corresponding to the target tissue, performs data recognition processing on the ultrasonic data to be processed, generates target tissue parameters corresponding to the target tissue, analyzes the target tissue parameters, and determines the assessment results corresponding to the target tissue. Not only does it achieve multi-faceted analysis of the target tissue, but it also ensures the accuracy of the assessment results corresponding to the determined target tissue.
[0012] In conjunction with the first aspect, in a first implementation of the first aspect, analyzing target tissue parameters to determine an evaluation result corresponding to the target tissue includes:
[0013] obtaining an ultrasound data processing model;
[0014] The target tissue parameters corresponding to the target tissue are input into the ultrasonic data processing model, features of the target tissue parameters are extracted, and based on the extracted features, an evaluation result corresponding to the target tissue is output.
[0015] The tissue assessment method provided in the embodiment of the present application obtains an ultrasonic data processing model, inputs target tissue parameters corresponding to the target tissue into the ultrasonic data processing model, performs feature extraction on the target tissue parameters, and outputs an assessment result corresponding to the target tissue based on the extracted features, thereby ensuring the accuracy of the assessment result corresponding to the output target tissue corresponding to the to-be-processed ultrasonic data, and does not rely on the subjective experience of medical staff to determine the assessment result corresponding to the target tissue.
[0016] In combination with the first aspect, in a second embodiment of the first aspect, performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue includes:
[0017] Perform image recognition processing on the color ultrasound image in the ultrasound data to be processed, and determine the region of interest corresponding to the target tissue in the color ultrasound image;
[0018] Perform image recognition on the region of interest and determine the vascular parameters corresponding to the region of interest.
[0019] The tissue assessment method provided in the embodiments of the present application performs image recognition processing on the color ultrasound image in the processed ultrasound data to determine the region of interest corresponding to the target tissue in the color ultrasound image, thereby ensuring the accuracy of the determined region of interest corresponding to the target tissue in the color ultrasound image. Image recognition is then performed on the region of interest to determine the vascular parameters corresponding to the region of interest, thereby ensuring the accuracy of the determined vascular parameters corresponding to the region of interest.
[0020] In combination with the first aspect, in a third embodiment of the first aspect, the elastic imaging image includes a quasi-static elastic imaging image and / or a shear wave elastic imaging image, and performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue includes:
[0021] Performing data recognition on the quasi-static elastography image and / or the shear wave elastography image in the to-be-processed ultrasound data corresponding to the target tissue, and extracting the elastic modulus distribution corresponding to the quasi-static elastography image and / or the shear wave elastography image;
[0022] Data recognition is performed on the elastic modulus distribution to determine the elastic parameters corresponding to the target tissue.
[0023] The tissue assessment method provided in the embodiments of the present application performs data recognition on the quasi-static elastography image and / or shear wave elastography image in the processed ultrasound data corresponding to the target tissue, extracts the elastic modulus distribution corresponding to the quasi-static elastography image and / or shear wave elastography image, and ensures the accuracy of the extracted elastic modulus distribution. The elastic modulus distribution is then subjected to data recognition to determine the elastic parameters corresponding to the target tissue, ensuring the accuracy of the determined elastic parameters corresponding to the target tissue.
[0024] In combination with the first aspect, in a fourth embodiment of the first aspect, the ultrasound parameters include a scale parameter and a shape factor parameter; and performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue includes:
[0025] Obtaining a probability density function of an ultrasonic backscatter signal envelope corresponding to an ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed;
[0026] The scale parameter and the shape factor parameter are calculated based on the relationship between the probability density function and the scale parameter function and the shape factor parameter function corresponding to the ultrasonic B-type image and / or radio frequency data.
[0027] The tissue assessment method provided in the embodiments of the present application obtains a probability density function of the ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radiofrequency data, thereby ensuring the accuracy of the probability density function of the ultrasonic backscatter signal envelope corresponding to the obtained ultrasonic B-ultrasound image and / or radiofrequency data. Then, based on the relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasonic B-ultrasound image and / or radiofrequency data, the scale parameter and shape factor parameter are calculated, thereby ensuring the accuracy of the calculated scale parameter and shape factor parameter, thereby enabling the characterization of scattering, attenuation, and scatterer distribution characteristics based on the scale parameter and shape factor parameter.
[0028] In combination with the first aspect, in a fifth embodiment of the first aspect, the ultrasound parameters include nonlinear acoustic parameters, and data recognition processing is performed on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue, including:
[0029] Identifying the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed, obtaining the second harmonic generated when the ultrasonic signal propagates in the target tissue, and obtaining a first relationship between the second harmonic and the nonlinear coefficient of the target tissue;
[0030] Calculate the nonlinear coefficient based on the second harmonic and the first relationship;
[0031] obtaining a second relationship between the nonlinear coefficient and the nonlinear acoustic parameter;
[0032] The nonlinear acoustic parameter is calculated according to the second relationship and the nonlinear coefficient.
[0033] The tissue assessment method provided in the embodiment of the present application obtains the second harmonic generated by the ultrasonic signal when it propagates in the target tissue based on ultrasonic B-ultrasound images and / or radio frequency data, and obtains a first relationship between the second harmonic and the nonlinear coefficient of the target tissue, thereby ensuring the accuracy of the obtained second harmonic and the accuracy of the first relationship between the obtained second harmonic and the nonlinear coefficient of the target tissue. A second relationship between the nonlinear coefficient and a nonlinear acoustic parameter is obtained; the accuracy of the second relationship between the obtained nonlinear coefficient and the nonlinear acoustic parameter is ensured. Then, based on the second relationship and the nonlinear coefficient, the nonlinear acoustic parameter is calculated, thereby ensuring the accuracy of the calculated nonlinear acoustic parameter.
[0034] In combination with the first aspect, in a sixth embodiment of the first aspect, the ultrasound parameters include attenuation information, and data recognition processing is performed on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue, including:
[0035] Identify the ultrasound B-ultrasound image and / or radio frequency data in the ultrasound data to be processed, and obtain the ultrasound signal propagating in the target tissue;
[0036] Performing a signal recovery operation on the ultrasonic signal to obtain the ultrasonic signal to be calculated;
[0037] The type of the ultrasonic signal to be calculated is determined, and the attenuation information of the ultrasonic signal to be calculated is calculated according to the type of the ultrasonic signal to be calculated using a calculation method corresponding to the type.
[0038] The tissue assessment method provided in the embodiments of the present application acquires an ultrasonic signal propagating in the target tissue based on an ultrasonic B-ultrasound image and / or radiofrequency data. It then performs a signal recovery operation on the ultrasonic signal to obtain the ultrasonic signal to be calculated, thereby ensuring the accuracy of the obtained ultrasonic signal to be calculated. The method also determines the type of the ultrasonic signal to be calculated and calculates the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type of the ultrasonic signal to be calculated, thereby ensuring the accuracy of the calculated attenuation information of the ultrasonic signal.
[0039] In combination with the sixth embodiment of the first aspect, in the seventh embodiment of the first aspect, determining the type of the ultrasonic signal to be calculated, and calculating the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type according to the type of the ultrasonic signal to be calculated, includes:
[0040] When the ultrasound signal to be calculated is a time domain signal, obtaining data of interest corresponding to the target tissue in the ultrasound signal to be calculated;
[0041] Calculate the signal energy of the data in one or more time windows of the data of interest;
[0042] The signal energy of the data in one or more time windows is fitted to obtain the attenuation information of the ultrasonic signal to be calculated.
[0043] The tissue assessment method provided in an embodiment of the present application obtains data of interest corresponding to the target tissue in the ultrasound signal to be calculated, when the ultrasound signal to be calculated is a time-domain signal, thereby ensuring the accuracy of the obtained data of interest corresponding to the target tissue. The signal energy of the data within one or more time windows in the data of interest is calculated, thereby ensuring the accuracy of the calculated signal energy of the data within the one or more time windows. A fitting operation is performed on the signal energy of the data within the one or more time windows to obtain attenuation information of the ultrasound signal to be calculated, thereby ensuring the accuracy of the obtained attenuation information of the ultrasound signal to be calculated.
[0044] In combination with the sixth embodiment of the first aspect, in the eighth embodiment of the first aspect, determining the type of the ultrasonic signal to be calculated, and calculating the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type according to the type of the ultrasonic signal to be calculated, includes:
[0045] When the ultrasound signal to be calculated is a frequency domain signal, obtaining data of interest corresponding to the target tissue in the ultrasound signal to be calculated;
[0046] Calculate the signal energy of the data corresponding to one or more time windows in the data of interest by short-time Fourier transform;
[0047] A fitting operation is performed on the signal energy of the data corresponding to one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated.
[0048] The tissue assessment method provided in an embodiment of the present application obtains data of interest corresponding to the target tissue in the ultrasound signal to be calculated, when the ultrasound signal to be calculated is a frequency domain signal, thereby ensuring the accuracy of the acquired data of interest corresponding to the target tissue in the ultrasound signal to be calculated. Then, the signal energy of the data corresponding to one or more time windows in the data of interest is calculated using a short-time Fourier transform, thereby ensuring the accuracy of the calculated signal energy of the data corresponding to one or more time windows in the data of interest. A fitting operation is performed on the signal energy of the data corresponding to the one or more time windows to obtain attenuation information of the ultrasound signal to be calculated, thereby ensuring the accuracy of the acquired attenuation information of the ultrasound signal to be calculated.
[0049] According to a second aspect, an embodiment of the present application further provides a tissue assessment device, comprising:
[0050] an acquisition module, configured to acquire unprocessed ultrasound data corresponding to the target tissue, the unprocessed ultrasound data including at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging;
[0051] an identification module, configured to perform data identification processing on the processed ultrasound data and generate target tissue parameters corresponding to the target tissue, wherein the target tissue parameters include at least one of ultrasound parameters, blood vessel parameters, and elasticity parameters; the ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; the blood vessel parameters are used to characterize the state of blood vessels in at least one target tissue; and the elasticity parameters are used to characterize the elastic state of the target tissue;
[0052] The determination module is used to analyze the target tissue parameters and determine the evaluation results corresponding to the target tissue.
[0053] The tissue assessment device provided in the embodiment of the present application obtains the ultrasonic data to be processed corresponding to the target tissue, and the ultrasonic data to be processed includes at least one of an ultrasonic B-ultrasound image, a color ultrasound image, an elastic imaging image, and radiofrequency data corresponding to the elastic imaging. Then, data recognition processing is performed on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue, thereby ensuring the accuracy of the target tissue parameters generated, and ensuring the comprehensiveness and diversity of the target tissue parameters. Then, the target tissue parameters are analyzed to determine the assessment results corresponding to the target tissue, thereby ensuring the accuracy of the assessment results determined for the target tissue. The above-mentioned device does not rely on the subjective experience of medical staff to determine the assessment results corresponding to the target tissue. Instead, it obtains the ultrasonic data to be processed corresponding to the target tissue, performs data recognition processing on the ultrasonic data to be processed, generates target tissue parameters corresponding to the target tissue, analyzes the target tissue parameters, and determines the assessment results corresponding to the target tissue. Not only does it achieve multi-faceted analysis of the target tissue, but it also ensures the accuracy of the assessment results determined for the target tissue.
[0054] According to the third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the tissue assessment method in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.
[0055] According to a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the tissue assessment method in the first aspect or any one embodiment of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0057] FIG1 is a flow chart of a tissue assessment method provided by an embodiment of the present application;
[0058] FIG2 is a flow chart of a tissue assessment method provided by another embodiment of the present application;
[0059] FIG3 is a flow chart of a tissue assessment method provided by another embodiment of the present application;
[0060] FIG4 is a flow chart of a tissue assessment method provided by another embodiment of the present application;
[0061] FIG5 is a flow chart of a tissue assessment method provided by another embodiment of the present application;
[0062] FIG6 is a flow chart of a tissue assessment method provided by another embodiment of the present application;
[0063] FIG7 is a schematic diagram of an ultrasonic signal to be calculated in a tissue assessment method provided by another embodiment of the present application;
[0064] FIG8 is a schematic diagram of a region of interest in a tissue assessment method provided by another embodiment of the present application;
[0065] FIG9 is a schematic diagram of data in different time windows in a tissue assessment method provided by another embodiment of the present application;
[0066] FIG10 is a functional module diagram of a tissue assessment device provided by an embodiment of the present application;
[0067] FIG11 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION
[0068] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.
[0069] It should be noted that the organizational assessment method provided in the embodiments of the present application may be executed by an organizational assessment device, which may be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware. The electronic device may be a server or a terminal. The server in the embodiments of the present application may be a single server or a server cluster composed of multiple servers. The terminal in the embodiments of the present application may be a smart phone, a personal computer, a tablet computer, a wearable device, an intelligent robot, or other intelligent hardware devices. In the following method embodiments, the execution subject is an electronic device as an example for explanation.
[0070] In one embodiment of the present application, as shown in FIG1 , a tissue assessment method is provided, which is described by taking the application of the method to an electronic device as an example, including the following steps:
[0071] S11. Obtaining the ultrasonic data to be processed corresponding to the target tissue.
[0072] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging.
[0073] Optionally, the electronic device may use an ultrasonic device to perform ultrasonic detection on the target tissue to obtain ultrasonic data to be processed corresponding to the target tissue.
[0074] Optionally, the electronic device may also receive ultrasonic data to be processed corresponding to the target tissue sent by other devices.
[0075] Optionally, the electronic device may also receive ultrasound data to be processed corresponding to the target tissue input by the user.
[0076] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the ultrasonic data to be processed corresponding to the target tissue.
[0077] The evaluation method of the present application is mainly used to evaluate the soft tissue of an organism, so the target tissue can be the liver, the breast, the kidney, etc. The embodiments of the present application do not limit the target tissue.
[0078] S12. Perform data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue.
[0079] Among them, the target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elasticity parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elasticity parameters are used to characterize the elastic state of the target tissue.
[0080] Optionally, the electronic device may process the ultrasound B-ultrasound image and / or radio frequency data to generate ultrasound parameters corresponding to the target tissue.
[0081] Optionally, the electronic device may identify the elastic imaging image and extract elastic parameters.
[0082] Optionally, the electronic device can identify the color ultrasound image and extract blood vessel parameters.
[0083] This step will be described in detail below.
[0084] S13. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0085] In an optional embodiment of the present application, the electronic device can obtain a weight coefficient corresponding to at least one of the ultrasound parameters, vascular parameters, and elasticity parameters included in the target tissue parameters. The electronic device can analyze at least one of the ultrasound parameters, vascular parameters, and elasticity parameters corresponding to the target tissue. The electronic device can determine the level of at least one of the ultrasound parameters, vascular parameters, and elasticity parameters, respectively, and multiply the levels of the ultrasound parameters, vascular parameters, and elasticity parameters by the weight coefficients corresponding to the corresponding ultrasound parameters and / or vascular parameters and / or elasticity parameters, respectively, to calculate a final result. Then, based on the range of the final result, the evaluation result corresponding to the target tissue is determined.
[0086] The evaluation results may be health evaluation results, lesion severity evaluation results, etc., and may be reflected in the form of grades, scores, etc.
[0087] In an embodiment of the present application, at least two of the ultrasound parameters, vascular parameters and elasticity parameters can be analyzed to determine the evaluation results corresponding to the target tissue, that is, the target tissue is evaluated by multiple parameters together, so that a more accurate evaluation result can be obtained.
[0088] The tissue assessment method provided in an embodiment of the present application obtains unprocessed ultrasound data corresponding to the target tissue. The unprocessed ultrasound data includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastography image, and radiofrequency data corresponding to the elastography. Then, data recognition processing is performed on the unprocessed ultrasound data to generate target tissue parameters corresponding to the target tissue, ensuring the accuracy of the generated target tissue parameters and ensuring the comprehensiveness and diversity of the target tissue parameters. The target tissue parameters are then analyzed to determine an assessment result corresponding to the target tissue, ensuring the accuracy of the determined assessment result corresponding to the target tissue. The above method does not rely on the subjective experience of medical personnel to determine the assessment result corresponding to the target tissue. Instead, it obtains unprocessed ultrasound data corresponding to the target tissue, performs data recognition processing on the unprocessed ultrasound data, generates target tissue parameters corresponding to the target tissue, analyzes the target tissue parameters, and determines the assessment result corresponding to the target tissue. As can be seen from the above, the tissue assessment method provided in the present application can use multiple parameters to comprehensively assess the tissue, that is, conduct a comprehensive analysis of the tissue from multiple aspects, thereby ensuring the accuracy of the assessment result determined for the target tissue.
[0089] Taking the target tissue parameters including ultrasound parameters, vascular parameters and elasticity parameters in the application scenario of liver tissue as an example: the size, edge characteristics, scattering coefficient, attenuation, scatterer distribution characteristic parameters, etc. of the region of interest can be obtained through B-ultrasound images; the vascular density, blood flow velocity, blood flow velocity gradient, vascular tortuosity and other parameters can be obtained through color ultrasound images; the elastic modulus, elastic distribution parameters, viscoelastic parameters, dispersion curve, etc. can be obtained through elastic imaging images; the scattering coefficient, attenuation, scatterer distribution characteristic parameters, etc. can be obtained through radio frequency data. Then, through the comprehensive evaluation of the above multiple parameters, the evaluation results of the pathological changes of liver tissue in terms of fibrosis, inflammation, fatty degeneration, vesicular degeneration, etc. can be obtained.
[0090] In an optional embodiment of the present application, the above-mentioned S13 “analyzing the target tissue parameters and determining the evaluation result corresponding to the target tissue” may include the following steps:
[0091] S131. Acquire an ultrasound data processing model.
[0092] Optionally, the electronic device may further obtain a training data set, which may include training tissue parameters corresponding to the target tissue and training evaluation results corresponding to the training tissue parameters.
[0093] Among them, the training evaluation result can be the score corresponding to the target organization, or it can be the grade score corresponding to the target organization. This embodiment of the application does not specifically limit the training evaluation result.
[0094] The electronic device can input training tissue parameters corresponding to the target tissue in the training data set into the initial ultrasound data processing network and then output a virtual assessment result corresponding to the target tissue. The electronic device then calculates the difference between the virtual assessment result and the training assessment result corresponding to the training tissue parameters and updates the initial ultrasound data processing network based on the difference between the virtual assessment result and the training assessment result to obtain an ultrasound data processing model.
[0095] Among them, the ultrasound data processing model can be a machine learning network model, of course, it can also be other network models. The machine learning network model can be DNN (Deep Neural Networks, Deep Neural Networks), CNN (Convolutional Neural Networks, Convolutional Neural Networks), RNN (Recurrent Neural Network, Recurrent Neural Networks), etc. When the ultrasound data processing model is CNN, it can be a V-Net model, U-Net model, Generative Adversarial Nets model, etc. The embodiment of the present application does not specifically limit the type of ultrasound data processing model.
[0096] In an optional embodiment of the present application, the electronic device can also receive an ultrasonic data processing model input by a user, and can also receive an ultrasonic data processing model sent by other devices. The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the ultrasonic data processing model.
[0097] S132. Input the target tissue parameters corresponding to the target tissue into the ultrasonic data processing model, perform feature extraction on the target tissue parameters, and output the evaluation results corresponding to the target tissue based on the extracted features.
[0098] Specifically, after the electronic device obtains the ultrasound data processing model, it can input the target tissue parameters corresponding to the target tissue into the ultrasound data processing model. The ultrasound data processing model performs feature recognition on the target tissue parameters corresponding to the target tissue, and outputs the evaluation results corresponding to the target tissue based on the recognized features.
[0099] In addition, the tissue assessment method provided in the embodiment of the present application obtains an ultrasonic data processing model, inputs the target tissue parameters corresponding to the target tissue into the ultrasonic data processing model, performs feature extraction on the target tissue parameters, and outputs the assessment results corresponding to the target tissue based on the extracted features, thereby ensuring the accuracy of the output assessment results corresponding to the target tissue and not relying on the subjective experience of medical staff to determine the assessment results corresponding to the target tissue.
[0100] In one embodiment of the present application, as shown in FIG2 , a tissue assessment method is provided, which is described by taking the application of the method to an electronic device as an example, including the following steps:
[0101] S21. Obtaining the ultrasonic data to be processed corresponding to the target tissue.
[0102] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging.
[0103] For details about this step, please refer to the introduction of S11 in FIG1 , which will not be described in detail here.
[0104] S22 , performing data recognition processing on the ultrasonic data to be processed, and generating target tissue parameters corresponding to the target tissue.
[0105] The target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elastic parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elastic parameters are used to characterize the elastic state of the target tissue.
[0106] In an optional embodiment of the present application, the above-mentioned S22 “performing data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue” may include the following steps:
[0107] S221 , performing image recognition processing on the color ultrasound image in the ultrasound data to be processed, and determining a region of interest corresponding to the target tissue in the color ultrasound image.
[0108] Specifically, the electronic device may utilize the tissue recognition model to perform image recognition processing on the color ultrasound image in the ultrasound data to be processed, and determine the region of interest corresponding to the target tissue in the color ultrasound image.
[0109] Among them, the tissue recognition model can be a model based on manual features, such as DPM (Deformable Parts Model), and the tissue recognition model can also be a model based on convolutional neural networks, such as YOLO (You Only Look Once) detector, R-CNN (Region-based Convolutional Neural Networks, region-based convolutional neural networks) model, SSD (Single Shot MultiBox, single shot multi-box) detector and Mask R-CNN (Mask Region-based Convolutional Neural Networks, masked region-based convolutional neural networks) model, etc. The embodiments of the present application do not specifically limit the tissue recognition model.
[0110] The tissue recognition model is trained based on a first training sample set, and the first training sample set includes a first training medical image corresponding to a first label, wherein the first label is a target tissue.
[0111] S222: Perform image recognition on the region of interest to determine blood vessel parameters corresponding to the region of interest.
[0112] In an optional embodiment of the present application, the vascular parameter may be used to characterize at least one of the vascular morphology such as vascular density, blood flow velocity, blood flow velocity gradient, and vascular tortuosity.
[0113] Specifically, the electronic device can use a vascular recognition model to perform vascular image recognition on a region of interest (ROI), identify the blood vessels within the ROI, and determine the vascular density within the ROI based on the number of identified blood vessels and the size of the ROI. Furthermore, the electronic device can determine the blood flow velocity within each vessel in the ROI based on the brightness and darkness corresponding to each vessel. Then, based on the blood flow velocity corresponding to each ROI, the electronic device determines the blood flow velocity gradient corresponding to the color ultrasound image. Finally, the morphology of the blood vessels within each ROI is identified, and the degree of vascular tortuosity is determined based on the morphological recognition results.
[0114] The blood vessel recognition model can be a model based on handcrafted features, such as the Deformable Parts Model (DPM). It can also be a model based on a convolutional neural network, such as the YOLO (You Only Look Once) detector, the R-CNN (Region-based Convolutional Neural Networks) model, the SSD (Single Shot MultiBox) detector, and the Mask R-CNN (Mask Region-based Convolutional Neural Networks) model. The embodiments of this application do not specifically limit the blood vessel recognition model.
[0115] The blood vessel recognition model is trained based on a second training sample set, and the second training sample set includes a second training medical image correspondingly labeled with a second label, wherein the second label is a blood vessel in the second training medical image.
[0116] S23. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0117] The tissue assessment method provided in the embodiments of the present application performs image recognition processing on the color ultrasound image in the processed ultrasound data to determine the region of interest corresponding to the target tissue in the color ultrasound image, thereby ensuring the accuracy of the determined region of interest corresponding to the target tissue in the color ultrasound image. Image recognition is then performed on the region of interest to determine the vascular parameters corresponding to the region of interest, thereby ensuring the accuracy of the determined vascular parameters corresponding to the region of interest.
[0118] In one embodiment of the present application, as shown in FIG3 , a tissue assessment method is provided. The method is described by taking an electronic device as an example, and includes the following steps:
[0119] S31. Obtaining the ultrasonic data to be processed corresponding to the target tissue.
[0120] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging.
[0121] For details about this step, please refer to the introduction of S21 in FIG2 , which will not be described in detail here.
[0122] S32 , performing data recognition processing on the ultrasonic data to be processed, and generating target tissue parameters corresponding to the target tissue.
[0123] The target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elastic parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elastic parameters are used to characterize the elastic state of the target tissue.
[0124] In an optional embodiment of the present application, the elastic imaging image includes a quasi-static elastic imaging image and / or a shear wave elastic imaging image. The above S32 "performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue" may include the following steps:
[0125] S321 , performing data recognition on the quasi-static elastography image and / or the shear wave elastography image in the ultrasound data to be processed, and extracting the elastic modulus distribution corresponding to the quasi-static elastography image and / or the shear wave elastography image.
[0126] The elastic parameter is at least one of elastic indices such as elastic modulus, elastic distribution parameter, viscoelastic parameter, and dispersion curve.
[0127] Specifically, the electronic device can perform data recognition on the elastic imaging image to determine the elastic modulus distribution corresponding to the target tissue.
[0128] Among them, the elastic imaging image includes a quasi-static elastic imaging image and / or a shear wave elastic imaging image. Preferably, the shear wave elastic imaging image can be obtained by performing shear wave elastic imaging under pressure quality control, and the quasi-static elastic imaging image can be obtained by performing quasi-static elastic imaging during the pressure quality control process. Among them, pressure quality control refers to the process of controlling the pressure applied to the target tissue to meet a certain pressure range during the elastic imaging of the target tissue. The pressure quality control process refers to the process of adjusting the pressure applied to the target tissue. This process involves the operation of lifting or pressing the detection probe up or down, and the magnitude of the applied pressure is adjusted by lifting or pressing the detection probe up or down; pressure quality control means that the pressure applied to the target tissue is controlled within a certain pressure range.
[0129] S322: Perform data recognition on the elastic modulus distribution to determine the elastic parameters corresponding to the target tissue.
[0130] Taking shear wave elastography as an example, the electronic device can determine the elastic distribution parameters corresponding to the target tissue based on the determined elastic modulus distribution. The electronic device can then track the shear waves during the shear wave elastography process, determine their morphology, and generate a corresponding dispersion curve. The dispersion curve can then be used to determine the viscoelastic parameters corresponding to the target tissue.
[0131] S33. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0132] For details about this step, please refer to the introduction of S23 in FIG2 , which will not be described in detail here.
[0133] The tissue assessment method provided in an embodiment of the present application performs data recognition on the quasi-static elastography image and / or shear wave elastography image in the processed ultrasound data corresponding to the target tissue, extracts the elastic modulus distribution corresponding to the quasi-static elastography image and / or shear wave elastography image, and ensures the accuracy of the extracted elastic modulus distribution. Data recognition is then performed on the elastic modulus distribution to determine the elastic parameters corresponding to the target tissue, ensuring the accuracy of the determined elastic parameters corresponding to the target tissue.
[0134] In one embodiment of the present application, as shown in FIG4 , a tissue assessment method is provided, which is described by taking the application of the method to an electronic device as an example, including the following steps:
[0135] S41. Obtaining the ultrasonic data to be processed corresponding to the target tissue.
[0136] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging.
[0137] For details about this step, please refer to the introduction of S31 in FIG3 , which will not be described in detail here.
[0138] S42 , performing data recognition processing on the ultrasonic data to be processed, and generating target tissue parameters corresponding to the target tissue.
[0139] Among them, the target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elasticity parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elasticity parameters are used to characterize the elastic state of the target tissue.
[0140] In an optional embodiment of the present application, the ultrasound parameters include scale parameters and shape factor parameters; the above S42 "performing data recognition processing on the processed ultrasound data to generate target tissue parameters corresponding to the target tissue" may include the following steps:
[0141] S421: Obtain a probability density function of an ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed.
[0142] In an optional embodiment of the present application, the electronic device can receive the probability density function of the ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radio frequency data sent by other devices; it can also receive the probability density function of the ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radio frequency data input by the user.
[0143] In an optional embodiment of the present application, an electronic device can generate a Nakagami image based on radio frequency data and Nakagami imaging technology. The Nakagami image is a mapping of the model's m parameter, a shape parameter used to describe the statistical distribution of the backscattered signal envelope. A change in m from 0 to 1 indicates a shift in the signal envelope's statistical distribution from a "pre-Rayleigh distribution" (typically a K distribution) to a Rayleigh distribution. A value greater than 1 indicates a "post-Rayleigh distribution" (typically a Rician distribution).
[0144] The probability density function of the ultrasonic backscatter signal envelope R in the Nakagami statistical model can be expressed as:
[0145] where Γ(·) and U(·) are the gamma function and unit step function, respectively; Ω is the scale parameter, which characterizes the energy variation of the scattering point; m is the shape factor, which characterizes the shape variation of the signal amplitude probability distribution curve; and r is the ultrasonic backscatter signal envelope.
[0146] S422 , calculating and obtaining scale parameters and shape factor parameters according to the relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasound B-type image and / or radio frequency data.
[0147] Specifically, the electronic device may obtain a relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasound B-type ultrasound image and / or radio frequency data. The electronic device then calculates the scale parameter and shape factor parameter based on the relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasound B-type ultrasound image and / or radio frequency data.
[0148] For example, the scale parameter Ω and the Nakagami parameter m associated with the Nakagami distribution can be calculated according to the following formula: Ω = E(R 2 ) (2)
[0149] It should be noted that the scale parameter Ω is correlated with the scattering coefficient; and the scale parameter Ω at different positions is correlated with the attenuation.
[0150] S43. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0151] For details about this step, please refer to the introduction of S33 in FIG3 , which will not be described in detail here.
[0152] The tissue assessment method provided in the embodiments of the present application obtains the probability density function of the ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radiofrequency data in the ultrasonic data to be processed, thereby ensuring the accuracy of the probability density function of the ultrasonic backscatter signal envelope corresponding to the obtained ultrasonic B-ultrasound image and / or radiofrequency data. Then, based on the relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasonic B-ultrasound image and / or radiofrequency data, the scale parameter and shape factor parameter are calculated, thereby ensuring the accuracy of the calculated scale parameter and shape factor parameter, thereby enabling the scattering, attenuation, and scatterer distribution characteristics to be characterized based on the scale parameter and shape factor parameter.
[0153] In one embodiment of the present application, as shown in FIG5 , a tissue assessment method is provided. The method is described by taking an electronic device as an example, and includes the following steps:
[0154] S51 : Acquire the ultrasonic data to be processed corresponding to the target tissue.
[0155] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging.
[0156] For details about this step, please refer to the introduction to S41 in FIG4 , which will not be described in detail here.
[0157] S52 : Perform data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue.
[0158] Among them, the target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elasticity parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elasticity parameters are used to characterize the elastic state of the target tissue.
[0159] In an optional embodiment of the present application, the ultrasound parameters include nonlinear acoustic parameters; the above S52 “performing data recognition processing on the ultrasound data to be processed to generate target tissue parameters corresponding to the target tissue” may include the following steps:
[0160] S521. Identify the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed, obtain the second harmonic generated when the ultrasonic signal propagates in the target tissue, and obtain a first relationship between the second harmonic and the nonlinear coefficient of the target tissue.
[0161] Specifically, the electronic device can analyze and study the ultrasonic B-ultrasound image and / or radio frequency data to obtain the second harmonic generated when the ultrasonic signal propagates in the target tissue.
[0162] The electronic device can then receive the first relationship between the second harmonic and the nonlinear coefficient of the target tissue from another device, or receive the first relationship between the second harmonic and the nonlinear coefficient of the target tissue input by a user, or search the electronic device's storage space for the first relationship between the second harmonic and the nonlinear coefficient of the target tissue. The embodiments of the present application do not specifically limit the manner in which the electronic device obtains the first relationship between the second harmonic and the nonlinear coefficient of the target tissue.
[0163] Exemplarily, the first relationship between the second harmonic P2 and the nonlinear coefficient β of the target tissue can be expressed as follows:
[0164] Where ρ0 and c0 represent the density and sound velocity of the target tissue, respectively, x is the distance the sound wave propagates, f is the frequency of the emission source, p is the amplitude of the emission source, and β is the nonlinear coefficient.
[0165] S522: Calculate the nonlinear coefficient according to the second harmonic and the first relationship.
[0166] Specifically, after obtaining the second harmonic and the first relationship between the second harmonic and the nonlinear coefficient of the target tissue, the electronic device may substitute the second harmonic into the first relationship to calculate the nonlinear coefficient.
[0167] S523: Obtain a second relationship between the nonlinear coefficient and the nonlinear acoustic parameter.
[0168] Specifically, the electronic device may receive the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter from another device, may receive the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter from a user, and may search for the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter in a storage space of the electronic device. The embodiments of the present application do not specifically limit the manner in which the electronic device obtains the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter.
[0169] For example, the second relationship between the nonlinear coefficient β and the nonlinear acoustic parameter can be expressed as: β = 1 + B / 2A (5)
[0170] Here, B / A is the nonlinear acoustic parameter. The nonlinear acoustic parameter is a fundamental parameter in nonlinear acoustics. It not only indicates the magnitude of the nonlinear effect produced when ultrasound waves pass through a medium, but also describes and explains nonlinear phenomena such as waveform distortion, harmonic generation, and acoustic streaming produced when ultrasound waves propagate through biological tissues.
[0171] S524: Calculate nonlinear acoustic parameters according to the second relationship and the nonlinear coefficient.
[0172] Specifically, after obtaining the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter and the nonlinear coefficient, the electronic device may substitute the nonlinear coefficient into the second relationship between the nonlinear coefficient and the nonlinear acoustic parameter to calculate the nonlinear acoustic parameter.
[0173] S53. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0174] For details about this step, please refer to the introduction to S43 in FIG4 , which will not be described in detail here.
[0175] The tissue assessment method provided in the embodiment of the present application identifies the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed, obtains the second harmonic generated when the ultrasonic signal propagates in the target tissue, and obtains the first relationship between the second harmonic and the nonlinear coefficient of the target tissue, thereby ensuring the accuracy of the obtained second harmonic and the accuracy of the first relationship between the obtained second harmonic and the nonlinear coefficient of the target tissue. The second relationship between the nonlinear coefficient and the nonlinear acoustic parameter is obtained; the accuracy of the second relationship between the obtained nonlinear coefficient and the nonlinear acoustic parameter is ensured, and then the nonlinear acoustic parameter is calculated based on the second relationship and the nonlinear coefficient, thereby ensuring the accuracy of the calculated nonlinear acoustic parameter.
[0176] In one embodiment of the present application, as shown in FIG6 , a tissue assessment method is provided, which is described by taking the application of the method to an electronic device as an example, including the following steps:
[0177] S61. Obtaining the ultrasonic data to be processed corresponding to the target tissue.
[0178] The ultrasound data to be processed includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image corresponding to the target tissue, and radio frequency data corresponding to the elastic imaging.
[0179] For details about this step, please refer to the introduction of S51 in FIG5 , which will not be described in detail here.
[0180] S62 , performing data recognition processing on the ultrasonic data to be processed, and generating target tissue parameters corresponding to the target tissue.
[0181] Among them, the target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elasticity parameters; ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; vascular parameters are used to characterize the state of blood vessels in at least one target tissue; and elasticity parameters are used to characterize the elastic state of the target tissue.
[0182] In an optional embodiment of the present application, the ultrasound parameters include attenuation information. The above S62 “performing data recognition processing on the ultrasound data to be processed to generate target tissue parameters corresponding to the target tissue” may include the following steps:
[0183] S621 : Identify the ultrasound B-ultrasound image and / or radio frequency data in the ultrasound data to be processed, and obtain the ultrasound signal propagating in the target tissue.
[0184] Optionally, the electronic device may identify and analyze the ultrasonic B-ultrasound image and / or radio frequency data to obtain the ultrasonic signal propagating in the target tissue.
[0185] Optionally, the electronic device may also acquire the ultrasonic signal propagating in the target tissue during the process of generating the ultrasonic B-ultrasound image and / or radio frequency data.
[0186] The embodiments of the present application do not specifically limit the manner in which the electronic device acquires the ultrasonic signal propagating in the target tissue.
[0187] S622: Perform a signal recovery operation on the ultrasonic signal to obtain the ultrasonic signal to be calculated.
[0188] Specifically, the electronic device may obtain a method for processing the ultrasonic signal during the generation of the ultrasonic signal, and then perform a signal recovery operation on the ultrasonic signal according to the method for processing the ultrasonic signal during the generation of the ultrasonic signal to obtain the ultrasonic signal to be calculated.
[0189] For example, it is assumed that the ultrasonic signal is A(t) (t is the time, A is the corresponding signal amplitude), and the signal recovery coefficient is W(t), wherein the signal recovery coefficient is obtained by calculation or experimental testing;
[0190] The signal recovery process is A'(t)=A(t)×W(t); wherein A'(t) is the recovered signal, that is, the ultrasonic signal to be calculated.
[0191] S623: Determine the type of the ultrasonic signal to be calculated, and calculate the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type of the ultrasonic signal to be calculated.
[0192] In an optional embodiment of the present application, the above-mentioned S623 "determining the type of the ultrasonic signal to be calculated, and calculating the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type according to the type of the ultrasonic signal to be calculated" may include the following content:
[0193] In one case, when the ultrasound signal to be calculated is a time domain signal, obtaining data of interest corresponding to the target tissue in the ultrasound signal to be calculated;
[0194] Calculate the signal energy of the data in one or more time windows of the data of interest;
[0195] The signal energy of the data in one or more time windows is fitted to obtain the attenuation information of the ultrasonic signal to be calculated.
[0196] Specifically, when the ultrasound signal to be calculated is a time domain signal, the electronic device can identify the ultrasound signal and obtain the data of interest corresponding to the target tissue in the ultrasound signal to be calculated.
[0197] For example, FIG7 shows a schematic diagram of an ultrasound signal to be calculated. The ultrasound signal to be calculated can be a signal directly acquired by a hardware analog-to-digital converter (ADC), such as an RF signal. FIG8 shows a schematic diagram of obtaining data of interest corresponding to a target tissue in the ultrasound signal to be calculated. The region of interest is represented by the data in the box in FIG8 .
[0198] Then, the electronic device can obtain the depth center corresponding to the data in each time window, and determine a section of data of interest corresponding to the depth center, and then calculate the sum of the squares of the amplitudes of the signals at each depth in the section of data of interest, which is the signal energy of the section of data of interest.
[0199] For example, for a signal segment centered at depth d1 (that is, signals at a series of depths centered at depth d1), the sum of the squares of the amplitudes of the signals at each depth in the signal segment is calculated, which is the energy Id1 of the signal segment; similarly, the energies of the signal segments centered at depths d2, d3, ..., dn are calculated to be Id2, Id3, ..., Idn, respectively.
[0200] As shown in FIG9 , different time windows are represented by boxes in FIG9 , where the position corresponding to the center of the box is equal to the corresponding depth, the width of the box is equal to the size of the time window, and the signal in the box is equal to the above-mentioned signal segment, and the sum of the squares of the signals is the energy of the signal segment.
[0201] Then, the electronic device performs a fitting operation on the signal energy of the data in one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated.
[0202] For example, a simplified formula for calculating the signal energy attenuation A between two depths d1 and d2 is: Energy attenuation A = (Id1 - Id2) / (d1 - d2). For energy fitting at multiple depths, linear fitting can be used, for example.
[0203] In another case, when the ultrasonic signal to be calculated is a frequency domain signal, data of interest corresponding to the target tissue in the ultrasonic signal to be calculated is obtained.
[0204] The signal energy of the data corresponding to one or more time windows in the data of interest is calculated by short-time Fourier transform.
[0205] A fitting operation is performed on the signal energy of the data corresponding to one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated.
[0206] Specifically, when the ultrasound signal to be calculated is a frequency domain signal, the electronic device can identify the ultrasound signal and obtain the data of interest corresponding to the target tissue in the ultrasound signal to be calculated.
[0207] For example, the electronic device may obtain the data of interest, namely the liver region data, by using, for example, a liver tissue positioning algorithm.
[0208] Then, the electronic device calculates the signal energy of the data corresponding to one or more time windows in the data of interest through short-time Fourier transform.
[0209] For example, for a signal segment centered at depth d1 (that is, signals at a series of depths centered at depth d1), the energy of the signal at each depth in the signal segment is calculated, which is the energy of the signal segment Id1; similarly, the energies of each signal segment centered at depths d2, d3, ..., dn are calculated to be Id2, Id3, ..., Idn respectively.
[0210] Then, the electronic device performs a fitting operation on the signal energy of the data corresponding to one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated.
[0211] For example, a simplified formula for calculating the signal energy attenuation A between two depths d1 and d2 is: Energy attenuation A = (Id1 - Id2) / (d1 - d2). For energy fitting at multiple depths, linear fitting can be used, for example.
[0212] S63. Analyze the target tissue parameters to determine the evaluation results corresponding to the target tissue.
[0213] For details about this step, please refer to the introduction of S53 in FIG5 , which will not be described in detail here.
[0214] The tissue assessment method provided in the embodiments of the present application identifies ultrasound B-ultrasound images and / or radiofrequency data in the processed ultrasound data, obtains the ultrasound signal propagating in the target tissue, then performs a signal recovery operation on the ultrasound signal to obtain the ultrasound signal to be calculated, thereby ensuring the accuracy of the obtained ultrasound signal to be calculated. When the ultrasound signal to be calculated is a time domain signal, data of interest corresponding to the target tissue in the ultrasound signal to be calculated is obtained, thereby ensuring the accuracy of the obtained data of interest corresponding to the target tissue. The signal energy of the data within one or more time windows in the data of interest is calculated, thereby ensuring the accuracy of the calculated signal energy of the data within the one or more time windows. The signal energy of the data within the one or more time windows is fitted to obtain attenuation information of the ultrasound signal to be calculated, thereby ensuring the accuracy of the obtained attenuation information of the ultrasound signal to be calculated. When the ultrasound signal to be calculated is a frequency domain signal, data of interest corresponding to the target tissue in the ultrasound signal to be calculated is obtained, thereby ensuring the accuracy of the obtained data of interest corresponding to the target tissue in the ultrasound signal to be calculated. Then, the signal energy of the data corresponding to the one or more time windows in the data of interest is calculated using a short-time Fourier transform, thereby ensuring the accuracy of the calculated signal energy of the data corresponding to the one or more time windows in the data of interest. A fitting operation is performed on the signal energy of the data corresponding to one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated, thereby ensuring the accuracy of the acquired attenuation information of the ultrasonic signal to be calculated.
[0215] It should be understood that, although the various steps in the flowcharts of Figures 1-6 are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in Figures 1-6 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.
[0216] The evaluation method provided in this embodiment can use multiple parameters to comprehensively evaluate the organization, that is, to evaluate the organization from multiple dimensions, so that the obtained evaluation results are more accurate.
[0217] As shown in FIG10 , this embodiment provides a tissue assessment device, including:
[0218] An acquisition module 71 is configured to acquire ultrasound data to be processed corresponding to the target tissue, the ultrasound data to be processed including at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radiofrequency data corresponding to the elastic imaging;
[0219] The identification module 72 is configured to perform data identification processing on the processed ultrasound data and generate target tissue parameters corresponding to the target tissue. The target tissue parameters include at least one of ultrasound parameters, vascular parameters, and elasticity parameters. The ultrasound parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics. The vascular parameters are used to characterize the state of blood vessels in at least one target tissue. The elasticity parameters are used to characterize the elastic state of the target tissue.
[0220] The determination module 73 is used to analyze the target tissue parameters and determine the evaluation result corresponding to the target tissue.
[0221] In one embodiment of the present application, the above-mentioned determination module 73 is specifically used to obtain an ultrasonic data processing model; input the target tissue parameters corresponding to the target tissue into the ultrasonic data processing model, perform feature extraction on the target tissue parameters, and output the evaluation results corresponding to the target tissue based on the extracted features.
[0222] In one embodiment of the present application, the above-mentioned recognition module 72 is specifically used to perform image recognition processing on the color ultrasound image in the processed ultrasound data to determine the region of interest corresponding to the target tissue in the color ultrasound image; perform image recognition on the region of interest to determine the vascular parameters corresponding to the region of interest.
[0223] In one embodiment of the present application, the above-mentioned identification module 72 is specifically used to perform data recognition on the quasi-static elastic imaging image and / or shear wave elastic imaging image in the ultrasound data to be processed corresponding to the target tissue, extract the elastic modulus distribution corresponding to the quasi-static elastic imaging image and / or shear wave elastic imaging image; perform data recognition on the elastic modulus distribution, and determine the elastic parameters corresponding to the target tissue.
[0224] In one embodiment of the present application, the ultrasonic parameters include scale parameters and shape factor parameters. The above-mentioned identification module 72 is specifically used to obtain the probability density function of the ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed; based on the relationship between the probability density function and the scale parameter function and shape factor parameter function corresponding to the ultrasonic B-ultrasound image and / or radio frequency data, the scale parameter and shape factor parameter are calculated.
[0225] In one embodiment of the present application, the ultrasonic parameters include nonlinear acoustic parameters. The above-mentioned identification module 72 is specifically used to identify the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed, obtain the second harmonic generated when the ultrasonic signal propagates in the target tissue, and obtain a first relationship between the second harmonic and the nonlinear coefficient of the target tissue; calculate the nonlinear coefficient based on the second harmonic and the first relationship; obtain a second relationship between the nonlinear coefficient and the nonlinear acoustic parameter; and calculate the nonlinear acoustic parameter based on the second relationship and the nonlinear coefficient.
[0226] In one embodiment of the present application, the ultrasonic parameters include attenuation information. The above-mentioned identification module 72 is specifically used to identify the ultrasonic B-ultrasound image and / or radio frequency data in the ultrasonic data to be processed to obtain the ultrasonic signal propagating in the target tissue; perform signal recovery operations on the ultrasonic signal to obtain the ultrasonic signal to be calculated; determine the type of the ultrasonic signal to be calculated, and calculate the attenuation information of the ultrasonic signal to be calculated using a calculation method corresponding to the type of the ultrasonic signal to be calculated.
[0227] In one embodiment of the present application, the above-mentioned identification module 72 is specifically used to obtain the data of interest corresponding to the target tissue in the ultrasound signal to be calculated when the ultrasound signal to be calculated is a time domain signal; calculate the signal energy of the data in one or more time windows in the data of interest; and perform a fitting operation on the signal energy of the data in one or more time windows to obtain the attenuation information of the ultrasound signal to be calculated.
[0228] In one embodiment of the present application, the above-mentioned identification module 72 is specifically used to obtain the data of interest corresponding to the target tissue in the ultrasound signal to be calculated when the ultrasound signal to be calculated is a frequency domain signal; calculate the signal energy of the data corresponding to one or more time windows in the data of interest through short-time Fourier transform; and perform a fitting operation on the signal energy of the data corresponding to the one or more time windows to obtain the attenuation information of the ultrasound signal to be calculated.
[0229] The specific limitations and beneficial effects of the tissue assessment device can be found in the limitations of the tissue assessment method above and will not be repeated here. The various modules in the tissue assessment device can be implemented in whole or in part through software, hardware, or a combination thereof. The modules can be embedded in or independent of the processor in the electronic device in hardware form, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to the modules.
[0230] An embodiment of the present application further provides an electronic device having the tissue assessment device shown in FIG. 10 .
[0231] As shown in Figure 11, Figure 11 is a structural diagram of an electronic device provided by an optional embodiment of the present application. As shown in Figure 11, the electronic device may include: at least one processor 81, such as a CPU (Central Processing Unit), at least one communication interface 83, a memory 84, and at least one communication bus 82. Among them, the communication bus 82 is used to realize the connection and communication between these components. Among them, the communication interface 83 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 83 may also include a standard wired interface and a wireless interface. The memory 84 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 84 may optionally be at least one storage device located away from the aforementioned processor 81. Among them, the processor 81 can be combined with the device described in Figure 10, the memory 84 stores the application program, and the processor 81 calls the program code stored in the memory 84 to execute any of the above method steps.
[0232] The communication bus 82 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 82 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, FIG11 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.
[0233] The memory 84 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the memory 84 may also include a combination of the above types of memory.
[0234] The processor 81 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.
[0235] The processor 81 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 PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.
[0236] Optionally, the memory 64 is further configured to store program instructions. The processor 61 may call the program instructions to implement the tissue assessment method as shown in the embodiments of FIG. 1 to FIG. 6 of the present application.
[0237] The present application also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the tissue assessment method in any of the above method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the storage medium can also include a combination of the above types of memory.
[0238] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.
Claims
1. A method for organizational assessment, characterized in that: include: Acquire the to-be-processed ultrasound data corresponding to the target tissue, wherein the to-be-processed ultrasound data includes at least one of an ultrasound B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging; Performing data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue, wherein the target tissue parameters include at least one of ultrasonic parameters, vascular parameters, and elastic parameters; the ultrasonic parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; The vascular parameter is used to characterize the state of at least one blood vessel in the target tissue; the elastic parameter is used to characterize the elastic state of the target tissue; The target tissue parameters are analyzed to determine the evaluation results corresponding to the target tissue.
2. The method according to claim 1, characterized in that The analyzing the target tissue parameter to determine the evaluation result corresponding to the target tissue includes: obtaining an ultrasound data processing model; The target tissue parameters are input into the ultrasound data processing model, features of the target tissue parameters are extracted, and based on the extracted features, an evaluation result corresponding to the target tissue is output.
3. The method according to claim 1 or 2, characterized in that: The performing data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue includes: Performing image recognition processing on the color ultrasound image in the ultrasound data to be processed to determine a region of interest corresponding to the target tissue in the color ultrasound image; Image recognition is performed on the region of interest to determine blood vessel parameters corresponding to the region of interest.
4. The method according to any one of claims 1 to 3, characterized in that The elastic imaging image includes a quasi-static elastic imaging image and / or a shear wave elastic imaging image, and the data recognition processing is performed on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue, including: Performing data recognition on the quasi-static elastic imaging image and / or the shear wave elastic imaging image in the ultrasonic data to be processed, and extracting elastic modulus distribution corresponding to the quasi-static elastic imaging image and / or the shear wave elastic imaging image; Data recognition is performed on the elastic modulus distribution to determine the elastic parameters corresponding to the target tissue.
5. The method according to any one of claims 1 to 3, characterized in that The ultrasonic parameters include scale parameters and shape factor parameters; the step of performing data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue includes: Acquire a probability density function of an ultrasonic backscatter signal envelope corresponding to the ultrasonic B-ultrasound image and / or the radio frequency data in the ultrasonic data to be processed; The scale parameter and the shape factor parameter are calculated based on the relationship between the probability density function and the scale parameter function and the shape factor parameter function corresponding to the ultrasonic B-mode ultrasound image and / or the radio frequency data.
6. The method according to any one of claims 1 to 3, characterized in that The ultrasonic parameters include nonlinear acoustic parameters, and the data recognition processing is performed on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue, including: Identify the ultrasonic B-ultrasound image and / or the radio frequency data in the ultrasonic data to be processed, obtain the second harmonic generated when the ultrasonic signal propagates in the target tissue, and obtain a first relationship between the second harmonic and the nonlinear coefficient of the target tissue; Calculating the nonlinear coefficient according to the second harmonic and the first relationship; Acquiring a second relationship between the nonlinear coefficient and the nonlinear acoustic parameter; The nonlinear acoustic parameter is calculated according to the second relationship and the nonlinear coefficient.
7. The method according to any one of claims 1 to 3, characterized in that The ultrasonic parameters include attenuation information, and the step of performing data recognition processing on the ultrasonic data to be processed to generate target tissue parameters corresponding to the target tissue includes: Identify the ultrasonic B-ultrasound image and / or the radio frequency data in the ultrasonic data to be processed, and acquire the ultrasonic signal propagated in the target tissue; Performing a signal recovery operation on the ultrasonic signal to obtain an ultrasonic signal to be calculated; The type of the ultrasonic signal to be calculated is determined, and according to the type of the ultrasonic signal to be calculated, the attenuation information of the ultrasonic signal to be calculated is calculated by adopting a calculation method corresponding to the type.
8. The method according to claim 7, characterized in that The determining the type of the ultrasonic signal to be calculated, and calculating the attenuation information of the ultrasonic signal to be calculated by using a calculation method corresponding to the type according to the type of the ultrasonic signal to be calculated, includes: When the ultrasound signal to be calculated is a time domain signal, acquiring the data of interest corresponding to the target tissue in the ultrasound signal to be calculated; Calculating signal energy of data in one or more time windows of the data of interest; Perform a fitting operation on the signal energy of the data in the one or more time windows to obtain the The attenuation information of the ultrasonic signal is to be calculated.
9. The method according to claim 7, characterized in that: The determining the type of the ultrasonic signal to be calculated, and calculating the attenuation information of the ultrasonic signal to be calculated by using a calculation method corresponding to the type according to the type of the ultrasonic signal to be calculated, includes: When the ultrasound signal to be calculated is a frequency domain signal, acquiring the data of interest corresponding to the target tissue in the ultrasound signal to be calculated; Calculate the signal energy of data corresponding to one or more time windows in the data of interest by short-time Fourier transform; A fitting operation is performed on the signal energy of the data corresponding to the one or more time windows to obtain the attenuation information of the ultrasonic signal to be calculated.
10. A tissue assessment device, characterized in that: include: An acquisition module, used for acquiring the to-be-processed ultrasonic data corresponding to the target tissue, wherein the to-be-processed ultrasonic data includes at least one of an ultrasonic B-ultrasound image, a color ultrasound image, an elastic imaging image, and radio frequency data corresponding to the elastic imaging; an identification module, used for performing data identification processing on the ultrasonic data to be processed, and generating target tissue parameters corresponding to the target tissue, wherein the target tissue parameters include at least one of ultrasonic parameters, vascular parameters, and elastic parameters; the ultrasonic parameters are used to characterize scattering, attenuation, and scatterer distribution characteristics; The vascular parameter is used to characterize the state of at least one blood vessel in the target tissue; the elastic parameter is used to characterize the elastic state of the target tissue; The determination module is used to analyze the target tissue parameters and determine the evaluation result corresponding to the target tissue.
11. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores computer instructions, and the processor executes the tissue assessment method according to any one of claims 1 to 9 by executing the computer instructions.
12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the tissue assessment method according to any one of claims 1 to 9.
Citation Information
Patent Citations
Lesion tissue growth monitoring method and system
CN103720489A
Tumor ultrasonic imaging feature extraction method and system
CN103948402A
Parameter for reflecting biological tissue abnormity and measuring method thereof
CN106983524A
Intelligent decision-making assisting system based on multi-modal ultrasomics
CN107582097A
Ultrasonic signal processing method and device, equipment and storage medium
CN110313936A
