A multi-zone time-temperature curve comparison system and method

Abstract

The application provides a multi-region time-hardness curve contrast system and method. The method is intended to set multiple target regions in advance in a three-dimensional ultrasound image, calculate the average hardness in each frame of the region by using a shear wave elasticity technique, lock the target region by using a tissue following method, draw a hardness change curve of each region with time, and reflect the elasticity difference between lesion muscle tissue and normal muscle tissue by using the peak time, maximum hardness and minimum hardness of the curve, so as to evaluate the recovery degree of the muscle.

Description

Technical Field

[0001] This invention relates to the field of ultrasound medical imaging, and in particular to a system and method for comparing time-stiffness curves in multiple regions. Background Technology

[0002] Based on the technical solution in patent application CN111388012B, "This invention provides a method, device, and system for detecting tissue hardness, comprising: acquiring motion parameters of shear waves propagating along the depth direction at multiple test locations over time; and calculating hardness information at each depth of the multiple test locations based on the motion parameters. This solution uses a tissue section at each depth of the test tissue as a unit, and calculates the hardness information at each depth of the multiple test locations based on the motion parameters of the shear waves propagating along the depth direction at multiple test locations over time, thereby obtaining tissue hardness. It involves minimal computation, provides accurate results with excellent real-time performance, and can accurately and efficiently obtain tissue hardness."

[0003] Problems: In some clinical applications, such as musculoskeletal ultrasound, it is necessary to assess the changes in stiffness of injured muscles during the transition from relaxation to tension and compare them with normal muscles. While the aforementioned patent can record changes in stiffness values ​​over time, it cannot perform comparative analysis of stiffness across multiple target areas. Furthermore, the transition from muscle relaxation to tension is often accompanied by displacement changes, which may even extend beyond the two-dimensional cross-section, necessitating consideration of muscle tissue tracking. Summary of the Invention

[0004] This invention provides a system and method for comparing time-hardness curves in multiple regions, in order to solve the problems mentioned in the background art.

[0005] A system for comparing time-hardness curves across multiple regions, comprising:

[0006] The region setting module is used to pre-define multiple target regions in a 3D ultrasound image using different colors;

[0007] The hardness testing module is used to obtain the average hardness of each target area based on shear wave elasticity technology.

[0008] The feature matching module is used to acquire multiple frames of three-dimensional ultrasound images of muscles during the process of muscle relaxation to tension, perform feature extraction and feature matching on multiple three-dimensional ultrasound images, and obtain the positional movement information of the target area based on the feature matching results;

[0009] The curve plotting module is used to determine the average hardness of the new location of the target area based on the location movement information of the target area, and to plot the time-hardness curves of multiple target areas.

[0010] Preferably, it also includes: an image acquisition module for acquiring three-dimensional ultrasound images;

[0011] The image acquisition module includes:

[0012] The image acquisition unit is used to acquire three-dimensional ultrasound images of muscles during the tension-to-relaxation process using a volume probe;

[0013] The display unit is used to display three-dimensional ultrasound images in real time using orthogonal three planes, namely the transverse, sagittal and coronal planes.

[0014] Preferably, the region setting module includes:

[0015] The manual setting unit is used to set a healthy reference group and one or more diseased tissue groups in a three-dimensional ultrasound image based on historical experience.

[0016] An automatic setting unit is used to identify abnormal and reference regions in three-dimensional ultrasound images based on deep learning.

[0017] The selection unit is used to set multiple target areas from the 3D ultrasound image with different colors according to the user's selection.

[0018] Preferably, the hardness testing module includes:

[0019] Excitation unit, used to excite shear waves to the target region;

[0020] The ultrasonic detection unit is used to emit high-speed ultrasonic waves to detect the propagation of shear waves and to receive the reflected echo information.

[0021] The velocity calculation unit is used to obtain the shear wave velocity of the high-speed ultrasonic wave at the sampling point of the shear wave based on the reflected echo information.

[0022] The hardness calculation unit is used to determine the average hardness of each target area based on the shear wave velocity.

[0023] Preferably, the speed calculation unit includes:

[0024] The signal acquisition unit is used to acquire long pulse echo signals and short pulse echo signals based on reflected echo information.

[0025] The signal analysis unit is used to acquire the local vibration characteristics of the target area based on the long pulse echo signal, determine the sampling points in the target area based on the local vibration characteristics of the tissue, and determine the displacement of each sampling point in the real-time tracking lateral direction based on the short pulse echo signal.

[0026] The velocity determination unit is used to determine the time when the shear wave reaches its peak value based on the displacement of the sampling point in the real-time tracking lateral direction, and to determine the shear wave velocity of the sampling point based on the time when the shear wave reaches its peak value.

[0027] Preferably, the hardness calculation unit includes:

[0028] The first calculation unit is used to calculate the hardness index of the sampling point based on the shear wave velocity and according to the following formula;

[0029] E i,j,k =3*ρ 组织 *c i,j,k 2

[0030] Where i,j,k represent the coordinates of the sampling point in the three-dimensional ultrasound image as (i, j, k), E i,j,k The Young's modulus of the sampling point (i, j, k) is the hardness index, ρ. 组织 c represents the tissue density of the target region. i,j,k This represents the shear wave velocity at the sampling point (i, j, k);

[0031] The second calculation unit is used to calculate the average hardness index of the target area based on the hardness index of all sampling points and according to the following formula.

[0032]

[0033] Among them, E mean,t The average Young's modulus of the target area is represented by N, which is the average hardness index. N represents the total number of sampling points in the target area.

[0034] Preferably, the feature matching module includes:

[0035] The matrix construction unit is used to obtain the grayscale image features of each frame of three-dimensional ultrasound image and to establish the grayscale co-occurrence matrix of the three-dimensional ultrasound image based on the grayscale image features.

[0036] The eigenvalue calculation unit is used to calculate the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix based on the following formula;

[0037] Engergy=∑ a ∑ b C ab 2

[0038] Entropy=-∑ a ∑ b C ab logC ab

[0039] Contrast=∑ a ∑ b (ab) 2 C ab

[0040]

[0041]

[0042] μ x =∑ a ∑ b a*C ab

[0043] μ y =∑ a ∑ b b*C ab

[0044] σ x 2 =∑ a ∑ b C ab (a-μ x ) 2

[0045] σ y 2 =∑ a ∑ b C ab (a-μ y ) 2

[0046] Where Energy represents the energy of the gray-level co-occurrence matrix, Entropy represents the entropy of the gray-level co-occurrence matrix, Contrast represents the contrast of the gray-level co-occurrence matrix, Correlation represents the correlation of the gray-level co-occurrence matrix, IDM represents the inverse difference of the gray-level co-occurrence matrix, and C ab Let represent the gray-level feature value of the a-th row and b-th column of the gray-level co-occurrence matrix, where the value of a is in the range [1, x] and a is an integer, and the value of b is in the range [1, y] and b is an integer;

[0047] The feature matching unit is used to perform feature matching on three-dimensional ultrasound images at different stages based on the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix to obtain the feature matching results.

[0048] The position determination unit is used to determine the movement features of the target area as the muscle moves from relaxation to tension based on the feature matching results, and to determine the position movement information of the target area based on the movement features.

[0049] Preferably, the feature matching unit includes:

[0050] The scheme determination unit is used to call the corresponding feature attribute weight allocation scheme based on the detected muscle position features in the human body;

[0051] The weighted calculation unit is used to assign weights to the energy, entropy, contrast, correlation and inverse difference of the gray-level co-occurrence matrix based on the feature attribute weight allocation scheme, and to calculate the weighted feature value at the sampling point according to the weight allocation result.

[0052] The weighted matching unit is used to perform weighted feature value matching on three-dimensional ultrasound images at different stages based on the weighted feature values ​​of sampling points, and to determine the feature matching results between three-dimensional ultrasound images at different stages.

[0053] Preferably, the curve plotting module includes:

[0054] The coordinate determination unit is used to establish positional correlations between three-dimensional ultrasound images at different stages based on the positional movement information of the target area, and to establish hardness-time coordinate points of the target area as a function of time based on the positional correlations.

[0055] The fitting unit is used to perform curve fitting on the hardness-time coordinate points to obtain the time-hardness curve.

[0056] A method for comparing time-hardness curves across multiple regions includes:

[0057] S1: Multiple target regions are pre-defined using different colors in a three-dimensional ultrasound image;

[0058] S2: Based on shear wave elasticity technology, the average hardness of each target area is obtained;

[0059] S3: Acquire multiple frames of three-dimensional ultrasound images of the muscle from relaxation to tension, perform feature extraction and feature matching on multiple three-dimensional ultrasound images, and obtain the positional movement information of the target area based on the feature matching results;

[0060] S4: Based on the location movement information of the target area, determine the average hardness of the new location of the target area, and plot the time-hardness curve of the multi-target area.

[0061] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0062] This method aims to pre-set multiple target regions in three-dimensional ultrasound images, use shear wave elasticity technology to calculate the average hardness of the region in each frame, and use a tissue following method to lock the target region and plot the hardness change curve of each region over time. The peak time, maximum hardness, and minimum hardness of the curve can reflect the elasticity difference between lesion muscle tissue and normal muscle tissue, thereby assessing the degree of muscle recovery.

[0063] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0064] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0065] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0066] Figure 1 This is a structural diagram of a multi-region time hardness curve comparison system according to an embodiment of the present invention;

[0067] Figure 2 This is a structural diagram of the hardness detection module in an embodiment of the present invention;

[0068] Figure 3 This is a flowchart of a method for comparing time-hardness curves in multiple regions according to an embodiment of the present invention. Detailed Implementation

[0069] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0070] Example 1:

[0071] This invention provides a system for comparing time-hardness curves across multiple regions, such as... Figure 1 As shown, it includes:

[0072] The region setting module is used to pre-define multiple target regions in a 3D ultrasound image using different colors;

[0073] The hardness testing module is used to obtain the average hardness of each target area based on shear wave elasticity technology.

[0074] The feature matching module is used to acquire multiple frames of three-dimensional ultrasound images of muscles during the process of muscle relaxation to tension, perform feature extraction and feature matching on multiple three-dimensional ultrasound images, and obtain the positional movement information of the target area based on the feature matching results;

[0075] The curve plotting module is used to determine the average hardness of the new location of the target area based on the location movement information of the target area, and to plot the time-hardness curves of multiple target areas.

[0076] In this embodiment, shear wave elastography is a novel elastic imaging modality that measures the absolute value of Young's modulus, a numerical value reflecting tissue elasticity. The higher the value, the harder the tissue, thereby distinguishing between normal and abnormal tissues.

[0077] In this embodiment, feature extraction includes the extraction of energy, entropy, contrast, correlation, and inverse difference.

[0078] The beneficial effects of the above design scheme are as follows: This method aims to pre-set multiple target areas in three-dimensional ultrasound images, use shear wave elasticity technology to calculate the average hardness of the area in each frame, and lock the target area through the tissue following method to draw the hardness change curve of each area over time. The peak time, maximum hardness and minimum hardness of the curve can reflect the elastic difference between lesion muscle tissue and normal muscle tissue, thereby assessing the degree of muscle recovery.

[0079] Example 2:

[0080] Based on Embodiment 1, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, and further includes: an image acquisition module for acquiring three-dimensional ultrasound images;

[0081] The image acquisition module includes:

[0082] The image acquisition unit is used to acquire three-dimensional ultrasound images of muscles during the tension-to-relaxation process using a volume probe;

[0083] The display unit is used to display three-dimensional ultrasound images in real time using orthogonal three planes, namely the transverse, sagittal and coronal planes.

[0084] In this embodiment, in order to solve the problem of muscle displacement changes during tension and relaxation, the limitation of two-dimensional plane is first broken, so it is necessary to obtain three-dimensional ultrasound images; the probe for obtaining three-dimensional ultrasound images can be a volume probe or a two-dimensional array probe; for the obtained three-dimensional ultrasound images, orthogonal three planes (transverse plane, sagittal plane and coronal plane) are used to display the reconstructed three-dimensional images in real time.

[0085] The beneficial effects of the above design scheme are: by acquiring three-dimensional ultrasound images, the limitations of two-dimensional planes can be overcome, and the problem of displacement changes in muscles during tension and relaxation can be solved.

[0086] Example 3:

[0087] Based on Embodiment 1, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a region setting module:

[0088] The manual setting unit is used to set a healthy reference group and one or more diseased tissue groups in a three-dimensional ultrasound image based on historical experience.

[0089] An automatic setting unit is used to identify abnormal and reference regions in three-dimensional ultrasound images based on deep learning.

[0090] The selection unit is used to set multiple target areas from the 3D ultrasound image with different colors according to the user's selection.

[0091] The beneficial effects of the above design scheme are: by providing both manual and automatic target area setting methods, it offers diverse and accurate setting methods for determining the target area, and provides an accurate regional basis for subsequent hardness testing of the target area.

[0092] Example 4:

[0093] Based on Example 1, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, such as... Figure 2 As shown, the hardness testing module includes:

[0094] Excitation unit, used to excite shear waves to the target region;

[0095] The ultrasonic detection unit is used to emit high-speed ultrasonic waves to detect the propagation of shear waves and to receive the reflected echo information.

[0096] The velocity calculation unit is used to obtain the shear wave velocity of the high-speed ultrasonic wave at the sampling point of the shear wave based on the reflected echo information.

[0097] The hardness calculation unit is used to determine the average hardness of each target area based on the shear wave velocity.

[0098] In this embodiment, the emitted detection ultrasound can be either a focused wave or a plane wave, but both require very high frame rates. If it is a focused wave, multi-beam focusing technology needs to be applied when receiving the echo to achieve rapid detection of shear waves in the coverage area; if it is a plane wave, multiple composite angles can be designed for transmitting and receiving echoes to achieve accurate detection of shear waves in the coverage area.

[0099] The beneficial effects of the above design scheme are: providing excitation shear waves to the target area and receiving reflected echo information; obtaining the shear wave velocity of the high-speed ultrasonic wave at the sampling point of the shear wave based on the reflected echo information; and determining the average hardness of each target area based on the shear wave velocity to ensure the accuracy of the obtained hardness.

[0100] Example 5:

[0101] Based on Embodiment 4, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a speed calculation unit comprising:

[0102] The signal acquisition unit is used to acquire long pulse echo signals and short pulse echo signals based on reflected echo information.

[0103] The signal analysis unit is used to acquire the local vibration characteristics of the target area based on the long pulse echo signal, determine the sampling points in the target area based on the local vibration characteristics of the tissue, and determine the displacement of each sampling point in the real-time tracking lateral direction based on the short pulse echo signal.

[0104] The velocity determination unit is used to determine the time when the shear wave reaches its peak value based on the displacement of the sampling point in the real-time tracking lateral direction, and to determine the shear wave velocity of the sampling point based on the time when the shear wave reaches its peak value.

[0105] In this embodiment, the long pulse echo signal is obtained based on the transmitted long pulse signal, and the short pulse echo signal is obtained based on the transmitted short pulse signal. The transmission of the long pulse signal is used to induce vibration in the tissue of the target area, and the generation of the short pulse signal is used for vibration detection.

[0106] In this embodiment, the shear wave velocity is calculated using the time-peak method.

[0107] The beneficial effects of the above design scheme are: by analyzing the reflected echo information and combining it with the time peak method, the shear wave velocity at the sampling point of the shear wave can be calculated, providing a parameter basis for the detection of hardness in the target area.

[0108] Example 6:

[0109] Based on Embodiment 4, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a hardness calculation unit comprising:

[0110] The first calculation unit is used to calculate the hardness index of the sampling point based on the shear wave velocity and according to the following formula;

[0111] E i,j,k =3*ρ 组织 *c i,j,k 2

[0112] Where i,j,k represent the coordinates of the sampling point in the three-dimensional ultrasound image as (i, j, k), E i,j,k The Young's modulus of the sampling point (i, j, k) is the hardness index, ρ. 组织 c represents the tissue density of the target region. i,j,k This represents the shear wave velocity at the sampling point (i, j, k);

[0113] The second calculation unit is used to calculate the average hardness index of the target area based on the hardness index of all sampling points and according to the following formula.

[0114]

[0115] Among them, E mean,t The average Young's modulus of the target area is represented by N, which is the average hardness index. N represents the total number of sampling points in the target area.

[0116] The beneficial effect of the above design scheme is that by using Young's modulus as a hardness index, the average hardness of the target area can be calculated, ensuring the accuracy of the obtained average hardness.

[0117] Example 7:

[0118] Based on Embodiment 1, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a feature matching module:

[0119] The matrix construction unit is used to obtain the grayscale image features of each frame of three-dimensional ultrasound image and to establish the grayscale co-occurrence matrix of the three-dimensional ultrasound image based on the grayscale image features.

[0120] The eigenvalue calculation unit is used to calculate the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix based on the following formula;

[0121] Engergy=∑ a ∑ b C ab 2

[0122] Entropy=-∑ a ∑ b C ab logC ab

[0123] Contrast=∑ a ∑ b (ab) 2 C ab

[0124]

[0125]

[0126] μ x =∑ a ∑ b a*C ab

[0127] μ y=∑ a ∑ b b*C ab

[0128] σ x 2 =∑ a ∑ b C ab (a-μ x ) 2

[0129] σ y 2 =∑ a ∑ b C ab (a-μ y ) 2

[0130] Where Energy represents the energy of the gray-level co-occurrence matrix, Entropy represents the entropy of the gray-level co-occurrence matrix, Contrast represents the contrast of the gray-level co-occurrence matrix, Correlation represents the correlation of the gray-level co-occurrence matrix, IDM represents the inverse difference of the gray-level co-occurrence matrix, and C ab Let represent the gray-level feature value of the a-th row and b-th column of the gray-level co-occurrence matrix, where the value of a is in the range [1, x] and a is an integer, and the value of b is in the range [1, y] and b is an integer;

[0131] The feature matching unit is used to perform feature matching on three-dimensional ultrasound images at different stages based on the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix to obtain the feature matching results.

[0132] The position determination unit is used to determine the movement features of the target area as the muscle moves from relaxation to tension based on the feature matching results, and to determine the position movement information of the target area based on the movement features.

[0133] The beneficial effects of the above design scheme are: by calculating the eigenvalues ​​of energy, entropy, contrast, correlation and inverse difference of the gray-level co-occurrence matrix, feature matching between different three-dimensional ultrasound images can be performed, realizing the detection of displacement changes during the process of muscle relaxation to tension, and realizing the tracking of the target area, thus providing a basis for the accurate detection of hardness during the process of muscle relaxation to tension.

[0134] Example 8:

[0135] Based on Embodiment 7, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a feature matching unit comprising:

[0136] The scheme determination unit is used to call the corresponding feature attribute weight allocation scheme based on the detected muscle position features in the human body;

[0137] The weighted calculation unit is used to assign weights to the energy, entropy, contrast, correlation and inverse difference of the gray-level co-occurrence matrix based on the feature attribute weight allocation scheme, and to calculate the weighted feature value at the sampling point according to the weight allocation result.

[0138] The weighted matching unit is used to perform weighted feature value matching on three-dimensional ultrasound images at different stages based on the weighted feature values ​​of sampling points, and to determine the feature matching results between three-dimensional ultrasound images at different stages.

[0139] In this embodiment, the feature attributes are the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix.

[0140] In this embodiment, the location characteristics of muscles in the human body are different, and the feature attribute weight allocation scheme is different, which is specifically obtained based on historical experience.

[0141] The beneficial effects of the above design scheme are as follows: By using a feature attribute weighting scheme to assign weights to the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix, and calculating the weighted feature values ​​at the sampling points based on the weighted feature values ​​at the sampling points, weighted feature value matching is performed on the three-dimensional ultrasound images at different stages based on the weighted feature values ​​at the sampling points, and the feature matching results between the three-dimensional ultrasound images at different stages are determined. By setting the weights of feature attributes, the different degrees of role of feature attributes in feature matching are highlighted, ensuring the accuracy of feature matching, thereby ensuring the accuracy of tissue tracking, and ultimately ensuring the accuracy of hardness detection.

[0142] Example 9:

[0143] Based on Embodiment 1, this embodiment of the invention provides a system for comparing time-hardness curves in multiple regions, including a curve plotting module comprising:

[0144] The coordinate determination unit is used to establish positional correlations between three-dimensional ultrasound images at different stages based on the positional movement information of the target area, and to establish hardness-time coordinate points of the target area as a function of time based on the positional correlations.

[0145] The fitting unit is used to perform curve fitting on the hardness-time coordinate points to obtain the time-hardness curve.

[0146] In this embodiment, the trend of each curve can be used to visually observe the changes in hardness of different target areas within a tension-relaxation cycle, and the health status of the target areas can be obtained by comparison.

[0147] In this embodiment, the difference between the maximum hardness and the minimum hardness can also be automatically calculated and displayed on the screen, thereby quantifying the hardness variation level of different target areas and forming an objective evaluation basis.

[0148] The beneficial effects of the above design scheme are: by obtaining time-hardness curves of multiple target areas and comparing the maximum hardness and minimum hardness in multiple dimensions, the hardness change level of different target areas can be quantified, forming an objective evaluation basis and providing an accurate data foundation for doctors' evaluation.

[0149] Example 10:

[0150] This invention provides a method for comparing time-hardness curves across multiple regions, such as... Figure 3 As shown, it includes:

[0151] S1: Multiple target regions are pre-defined using different colors in a three-dimensional ultrasound image;

[0152] S2: Based on shear wave elasticity technology, the average hardness of each target area is obtained;

[0153] S3: Acquire multiple frames of three-dimensional ultrasound images of the muscle from relaxation to tension, perform feature extraction and feature matching on multiple three-dimensional ultrasound images, and obtain the positional movement information of the target area based on the feature matching results;

[0154] S4: Based on the location movement information of the target area, determine the average hardness of the new location of the target area, and plot the time-hardness curve of the multi-target area.

[0155] In this embodiment, shear wave elastography is a novel elastic imaging modality that measures the absolute value of Young's modulus, a numerical value reflecting tissue elasticity. The higher the value, the harder the tissue, thereby distinguishing between normal and abnormal tissues.

[0156] In this embodiment, feature extraction includes the extraction of energy, entropy, contrast, correlation, and inverse difference.

[0157] The beneficial effects of the above design scheme are as follows: This method aims to pre-set multiple target areas in three-dimensional ultrasound images, use shear wave elasticity technology to calculate the average hardness of the area in each frame, and lock the target area through the tissue following method to draw the hardness change curve of each area over time. The peak time, maximum hardness and minimum hardness of the curve can reflect the elastic difference between lesion muscle tissue and normal muscle tissue, thereby assessing the degree of muscle recovery.

[0158] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A system for comparing time-hardness curves across multiple regions, characterized in that, include: The region setting module is used to pre-define multiple target regions in a 3D ultrasound image using different colors; The hardness testing module is used to obtain the average hardness of each target area based on shear wave elasticity technology. The feature matching module acquires multiple frames of 3D ultrasound images of muscles transitioning from relaxation to tension. It performs feature extraction and matching on these multiple images, and based on the matching results, obtains the positional movement information of the target region, including: The matrix construction unit is used to obtain the grayscale image features of each frame of three-dimensional ultrasound image and to establish the grayscale co-occurrence matrix of the three-dimensional ultrasound image based on the grayscale image features. The eigenvalue calculation unit is used to calculate the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix based on the following formula; ； ； ； ； ； ； ； ； ； in, This represents the energy of the gray-level co-occurrence matrix. The entropy of the gray-level co-occurrence matrix is ​​represented by... The contrast of the gray-level co-occurrence matrix is ​​represented by... This represents the correlation of the gray-level co-occurrence matrix. Represents the inverse difference of the gray-level co-occurrence matrix. Let represent the gray-level feature value in the a-th row and b-th column of the gray-level co-occurrence matrix, where the value of a is in the range [1, x] and a is an integer, and the value of b is in the range [1, y] and b is an integer; The feature matching unit is used to perform feature matching on three-dimensional ultrasound images at different stages based on the energy, entropy, contrast, correlation, and inverse difference of the gray-level co-occurrence matrix to obtain the feature matching results. The position determination unit is used to determine the movement features of the target area as the muscle moves from relaxation to tension based on the feature matching results, and to determine the position movement information of the target area based on the movement features. The curve plotting module is used to determine the average hardness of the new location of the target area based on the location movement information of the target area, and to plot the time-hardness curves of multiple target areas.

2. The system for comparing time-hardness curves in multiple regions according to claim 1, characterized in that, Also includes: The image acquisition module is used to acquire three-dimensional ultrasound images; The image acquisition module includes: The image acquisition unit is used to acquire three-dimensional ultrasound images of muscles during the tension-to-relaxation process using a volume probe; The display unit is used to display three-dimensional ultrasound images in real time using orthogonal three planes, namely the transverse, sagittal and coronal planes.

3. The system for comparing time-hardness curves in multiple regions according to claim 1, characterized in that, The regional settings module includes: The manual setting unit is used to set a healthy reference group and one or more diseased tissue groups in a three-dimensional ultrasound image based on historical experience. An automatic setting unit is used to identify abnormal and reference regions in three-dimensional ultrasound images based on deep learning. The selection unit is used to set multiple target areas from the 3D ultrasound image with different colors according to the user's selection.

4. The system for comparing time-hardness curves in multiple regions according to claim 1, characterized in that, The hardness testing module includes: Excitation unit, used to excite shear waves to the target region; The ultrasonic detection unit is used to emit high-speed ultrasonic waves to detect the propagation of shear waves and to receive the reflected echo information. The velocity calculation unit is used to obtain the shear wave velocity of the high-speed ultrasonic wave at the sampling point of the shear wave based on the reflected echo information. The hardness calculation unit is used to determine the average hardness of each target area based on the shear wave velocity.

5. A system for comparing time-hardness curves in multiple regions according to claim 4, characterized in that, The speed calculation unit includes: The signal acquisition unit is used to acquire long pulse echo signals and short pulse echo signals based on reflected echo information. The signal analysis unit is used to acquire the local vibration characteristics of the target area based on the long pulse echo signal, determine the sampling points in the target area based on the local vibration characteristics of the tissue, and determine the displacement of each sampling point in the real-time tracking lateral direction based on the short pulse echo signal. The velocity determination unit is used to determine the time when the shear wave reaches its peak value based on the displacement of the sampling point in the real-time tracking lateral direction, and to determine the shear wave velocity of the sampling point based on the time when the shear wave reaches its peak value.

6. A system for comparing time-hardness curves in multiple regions according to claim 4, characterized in that, The hardness calculation unit includes: The first calculation unit is used to calculate the hardness index of the sampling point based on the shear wave velocity and according to the following formula; ； in, Let (i, j, k) represent the coordinates of the sampling point in the three-dimensional ultrasound image. The Young's modulus at sampling point (i, j, k) is the hardness index. Indicates the tissue density of the target region. This represents the shear wave velocity at the sampling point (i, j, k); The second calculation unit is used to calculate the average hardness index of the target area based on the hardness index of all sampling points and according to the following formula. ； in, This represents the average Young's modulus of the target region, i.e., the average hardness index. This indicates the total number of sampling points in the target area.

7. The system for comparing time-hardness curves in multiple regions according to claim 1, characterized in that, Feature matching unit, including: The scheme determination unit is used to call the corresponding feature attribute weight allocation scheme based on the detected muscle position features in the human body; The weighted calculation unit is used to assign weights to the energy, entropy, contrast, correlation and inverse difference of the gray-level co-occurrence matrix based on the feature attribute weight allocation scheme, and to calculate the weighted feature value at the sampling point according to the weight allocation result. The weighted matching unit is used to perform weighted feature value matching on three-dimensional ultrasound images at different stages based on the weighted feature values ​​of sampling points, and to determine the feature matching results between three-dimensional ultrasound images at different stages.

8. A system for comparing time-hardness curves in multiple regions according to claim 1, characterized in that, The curve drawing module includes: The coordinate determination unit is used to establish positional correlations between three-dimensional ultrasound images at different stages based on the positional movement information of the target area, and to establish hardness-time coordinate points of the target area as a function of time based on the positional correlations. The fitting unit is used to perform curve fitting on the hardness-time coordinate points to obtain the time-hardness curve.

9. A method for comparing time-hardness curves in multiple regions, specifically used in the system for comparing time-hardness curves in multiple regions as described in claim 1, characterized in that, include: S1: Multiple target regions are pre-defined using different colors in the three-dimensional ultrasound image; S2: Based on shear wave elasticity technology, obtain the average hardness of each target area; S3: Acquire multiple frames of three-dimensional ultrasound images of the muscle from relaxation to tension, perform feature extraction and feature matching on multiple three-dimensional ultrasound images, and obtain the positional movement information of the target area based on the feature matching results; S4: Based on the location movement information of the target area, determine the average hardness of the new location of the target area, and plot the time-hardness curve of the multi-target area.

Images