Quantitative analysis method of ultrasound contrast imaging and ultrasound equipment

Abstract

The present disclosure provides a quantitative analysis method and an ultrasonic device for ultrasound contrast images. The method is used to improve the accuracy of quantitative analysis of ultrasound contrast images. The method comprises: extracting feature points from any ultrasound contrast image in ultrasound contrast images of the same biological tissue to obtain each feature point; extracting features from each feature point to obtain a feature vector of each feature point; for any feature point in the ultrasound contrast image, using the feature vector of the feature point and the feature vector of each feature point of the target ultrasound contrast image, obtaining a target feature point in the target ultrasound contrast image that matches the feature point; obtaining a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point in the ultrasound contrast image and each target feature point; performing position transformation on the ROI area of ​​the target ultrasound contrast image through the transformation matrix to obtain the ROI area of ​​the ultrasound contrast image; obtaining a time intensity curve using the ROI area of ​​each ultrasound contrast image.

Description

Background Art

[0002] Quantitative analysis of ultrasound contrast-enhanced images is to obtain quantitative information of blood perfusion by analyzing the time-intensity curve of ultrasound contrast-enhanced images, so as to distinguish subtle differences. It can grasp the overall blood perfusion trend and obtain the analysis parameters of blood perfusion to quantify the perfusion process. Quantitative analysis of ultrasound contrast-enhanced images is usually performed by comparing suspicious tissue with normal tissue to obtain specific information of suspicious tissue.

[0003] However, since the background of ultrasound contrast imaging sequence images changes dynamically, during a long scanning process, changes in the patient's breathing and / or body position will cause the ROI (region of interest) to change in position on the ultrasound contrast imaging image. Therefore, problems such as deformation of biological tissue movement and disappearance of the ROI area will occur, which in turn leads to a low accuracy rate in quantitative analysis of ultrasound contrast imaging images. Summary of the invention

[0004] In an exemplary embodiment of the present disclosure, a quantitative analysis method of ultrasound contrast imaging and an ultrasound device are provided to improve the accuracy of quantitative analysis of ultrasound contrast imaging.

[0005] A first aspect of the present disclosure provides a method for quantitatively analyzing ultrasound contrast-enhanced images, the method comprising:

[0006] For any ultrasound contrast-enhanced image of the same biological tissue, feature points are extracted from the ultrasound contrast-enhanced image to obtain feature points; and,

[0007] Performing feature extraction on each of the feature points to obtain a feature vector of each of the feature points;

[0008] For any feature point in the ultrasound contrast-enhanced image, using a feature vector of the feature point and feature vectors of each feature point of a target ultrasound contrast-enhanced image in each ultrasound contrast-enhanced image, a target feature point in the target ultrasound contrast-enhanced image that matches the feature point is obtained;

[0009] Based on each feature point and each target feature point in the ultrasound contrast image, a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image is obtained;

[0010] Performing a position transformation on the ROI region of the target ultrasound contrast imaging image by using the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image;

[0011] The time intensity curve is obtained by using the ROI region of each ultrasound contrast image.

[0012] In this embodiment, by matching the feature points of each ultrasound contrast image with the target ultrasound contrast image, then obtaining the position transformation matrix between each ultrasound contrast image and the target ultrasound contrast image based on the matched target feature points and the feature points in each ultrasound contrast image, and then transforming the position of the ROI area in the target ultrasound image based on the position transformation matrix, the position of the ROI area in each ultrasound contrast image is obtained, and the time intensity curve is obtained based on each ROI position area. Therefore, in this embodiment, the ROI area in each ultrasound contrast image is determined by the position transformation matrix between each frame of the ultrasound contrast image and the target ultrasound contrast image, thereby realizing automatic tracking of the ROI area, thereby improving the accuracy of quantitative analysis of the ultrasound contrast image.

[0013] In one embodiment, extracting feature points from the ultrasound contrast imaging image to obtain each feature point includes:

[0014] For any pixel point in the ultrasound contrast imaging image, if there are target pixel points greater than a first specified number in a specified area of ​​the pixel point, the pixel point is determined to be the feature point, wherein the target pixel point is a pixel point whose absolute value of the difference between the pixel value and the pixel value of the pixel point is not greater than a first preset threshold; or,

[0015] For any pixel point in the ultrasound contrast imaging image, if the pixel point is a pixel point with the largest pixel value or the smallest pixel value among the pixel points in its neighborhood, the pixel point is determined to be the feature point.

[0016] In this embodiment, feature points are determined by pixel values ​​of each pixel point within a designated area of ​​the pixel point, so that the determined feature points are more accurate.

[0017] In one embodiment, the extracting features of each feature point to obtain a feature vector of each feature point includes:

[0018] For any feature point, based on the pixel values ​​of each pixel point in the specified area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixel points;

[0019] Using the gradient magnitude and gradient direction between the pixels in the specified area, the main gradient direction of the feature point is obtained;

[0020] Taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area;

[0021] Dividing the rotated designated area into a second designated number of sub-areas, and determining the gradient direction between each pixel point in each sub-area;

[0022] For any sub-region, determining the number of each pixel point in the sub-region in each target gradient direction;

[0023] The feature vector of the feature point is obtained by the number of each pixel point in each sub-region in each target gradient direction.

[0024] This embodiment determines the feature vector of the feature point through the gradient amplitude and gradient direction of the pixel point, so that the feature vector is determined more accurately.

[0025] In one embodiment, the step of determining the gradient magnitude and gradient direction between any two pixels based on the pixel values ​​of each pixel within the designated area of ​​the feature point includes:

[0026] For any two pixel points in the designated area, the direction from one pixel point to the other pixel point of the two pixel points is determined as the gradient direction, and the difference in pixel values ​​of the two pixel points is determined as the gradient amplitude corresponding to the gradient direction.

[0027] In one embodiment, obtaining the main gradient direction of the feature point by using the gradient magnitude and gradient direction between the pixels in the designated area includes:

[0028] For any gradient direction, counting the number of the gradient directions in the gradient directions between the pixels in the specified area; and

[0029] Multiplying the number of the gradient directions by the average value of each gradient amplitude corresponding to the gradient direction in the specified area to obtain the target number of the gradient directions;

[0030] The gradient direction with the largest target number among the gradient directions in the designated area is determined as the main gradient direction of the feature point.

[0031] In this embodiment, the main gradient direction of the feature point is determined by the gradient direction with the largest number of targets among the gradient directions in the designated area, thereby making the determined main gradient direction more accurate and further improving the accuracy of quantitative analysis of ultrasound contrast imaging.

[0032] In one embodiment, the step of using the feature vector of the feature point and the feature vector of each feature point of the target ultrasound contrast image in each ultrasound contrast image to obtain a target feature point in the target ultrasound contrast image that matches the feature point includes:

[0033] For any feature point in the ultrasound contrast-enhanced image, determining a matching degree between the two feature points based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image;

[0034] Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points;

[0035] A target feature point is obtained through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point.

[0036] In one embodiment, obtaining a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point in the ultrasound contrast image and each target feature point includes:

[0037] Randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point that matches the feature point;

[0038] Using the intermediate position transformation matrix to transform the position coordinates of each target feature point in the target ultrasound contrast imaging image, to obtain the transformed position coordinates of each target feature point;

[0039] For any feature point in the ultrasound contrast-enhanced image, a matching value is obtained according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast-enhanced image that matches the feature point;

[0040] If the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set;

[0041] Determining whether the number of the key feature point sets is greater than a fourth specified number;

[0042] If not, returning to the step of randomly extracting a third specified number of feature points from each feature point of the ultrasound contrast imaging image;

[0043] If so, the transformation matrix is ​​obtained based on the sets of key feature points.

[0044] In this embodiment, the position coordinates of each target feature point in the target ultrasound contrast image are transformed by an intermediate position transformation matrix to obtain the transformed position coordinates of each target feature point, and the transformed position coordinates are matched with the position coordinates of the feature point to obtain a matching value, a key feature point set is determined by the matching value, and the transformation matrix is ​​obtained based on the key feature point set. Thus, the transformation matrix is ​​determined by a key feature point set with a high matching degree, so that the transformation matrix is ​​determined more accurately, and the tracking accuracy of the ROI area is improved.

[0045] In one embodiment, the step of performing position transformation on the ROI region of the target ultrasound contrast imaging image by using the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image includes:

[0046] The transformation matrix is ​​multiplied by a position matrix corresponding to the ROI region of the target ultrasound contrast imaging image to obtain the ROI region of the ultrasound contrast imaging image.

[0047] In this embodiment, the ROI region of the ultrasound contrast image is obtained by multiplying the transformation matrix with the position matrix corresponding to the ROI region of the target ultrasound contrast image, thereby making the determined ROI region of the ultrasound contrast image more accurate.

[0048] In one embodiment, the step of obtaining a time intensity curve by using the ROI region of each ultrasound contrast imaging image includes:

[0049] For any ultrasound contrast-enhanced image, an average value of pixel values ​​of each target pixel point in the ROI region of the ultrasound contrast-enhanced image is determined as the contrast energy intensity of the ultrasound contrast-enhanced image;

[0050] Based on the contrast energy intensity of each ultrasound contrast image, a time intensity curve is obtained.

[0051] This embodiment obtains a time intensity curve through the contrast energy intensity of each ultrasound contrast image, so that the determined time intensity curve is more accurate, and further improves the accuracy of quantitative analysis of ultrasound contrast images.

[0052] In one embodiment, the target pixel is determined by:

[0053] Traversing each pixel point in the target ultrasound contrast imaging image, wherein the traversed pixel points are pixel points before digital scan conversion;

[0054] For any pixel point traversed, digital scanning transformation is performed on the pixel point to obtain the position coordinates of the pixel point;

[0055] Comparing the position coordinates of the pixel point with the position coordinates of the target ultrasound contrast imaging ROI region to determine whether the pixel point is within the ROI region;

[0056] If it is determined that the pixel point is within the ROI area, the pixel point is determined to be the target sampling point.

[0057] A second aspect of the present disclosure provides an ultrasound device, including a storage unit and a processor, wherein:

[0058] The storage unit is configured to store each ultrasound contrast image of the biological tissue;

[0059] The processor is configured to:

[0060] For any ultrasound contrast-enhanced image of the same biological tissue, feature points are extracted from the ultrasound contrast-enhanced image to obtain feature points; and,

[0061] Performing feature extraction on each of the feature points to obtain a feature vector of each of the feature points;

[0062] For any feature point in the ultrasound contrast-enhanced image, using a feature vector of the feature point and feature vectors of each feature point of a target ultrasound contrast-enhanced image in each ultrasound contrast-enhanced image, a target feature point in the target ultrasound contrast-enhanced image that matches the feature point is obtained;

[0063] Based on each feature point and each target feature point in the ultrasound contrast image, a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image is obtained;

[0064] Performing a position transformation on the ROI region of the target ultrasound contrast imaging image by using the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image;

[0065] The time intensity curve is obtained by using the ROI region of each ultrasound contrast image.

[0066] In one embodiment, the processor performs the feature point extraction on the ultrasound contrast imaging image to obtain each feature point, which is specifically configured as follows:

[0067] For any pixel point in the ultrasound contrast imaging image, if there are target pixel points greater than a first specified number in a specified area of ​​the pixel point, the pixel point is determined to be the feature point, wherein the target pixel point is a pixel point whose absolute value of the difference between the pixel value and the pixel value of the pixel point is not greater than a first preset threshold; or,

[0068] For any pixel point in the ultrasound contrast imaging image, if the pixel point is a pixel point with the largest pixel value or the smallest pixel value among the pixel points in its neighborhood, the pixel point is determined to be the feature point.

[0069] In one embodiment, the processor performs the feature extraction for each feature point to obtain the feature vector of each feature point, which is specifically configured as follows:

[0070] For any feature point, based on the pixel values ​​of each pixel point in the specified area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixel points;

[0071] Using the gradient magnitude and gradient direction between the pixels in the specified area, the main gradient direction of the feature point is obtained;

[0072] Taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area;

[0073] Dividing the rotated designated area into a second designated number of sub-areas, and determining the gradient direction between each pixel point in each sub-area;

[0074] For any sub-region, determining the number of each pixel point in the sub-region in each target gradient direction;

[0075] The feature vector of the feature point is obtained by the number of each pixel point in each sub-region in each target gradient direction.

[0076] In one embodiment, the processor performs the step of determining the gradient magnitude and gradient direction between any two pixels based on the pixel values ​​of each pixel within the specified area of ​​the feature point, and is specifically configured as follows:

[0077] For any two pixel points in the designated area, the direction from one pixel point to the other pixel point of the two pixel points is determined as the gradient direction, and the difference in pixel values ​​of the two pixel points is determined as the gradient amplitude corresponding to the gradient direction.

[0078] In one embodiment, the processor performs the step of using the gradient magnitude and gradient direction between the pixels in the designated area to obtain the main gradient direction of the feature point, and is specifically configured as follows:

[0079] For any gradient direction, counting the number of the gradient directions in the gradient directions between the pixels in the specified area; and

[0080] Multiplying the number of the gradient directions by the average value of each gradient amplitude corresponding to the gradient direction in the specified area to obtain the target number of the gradient directions;

[0081] The gradient direction with the largest target number among the gradient directions in the designated area is determined as the main gradient direction of the feature point.

[0082] In one embodiment, the processor performs the step of using the feature vector of the feature point and the feature vector of each feature point of the target ultrasound contrast image in each ultrasound contrast image to obtain the target feature point in the target ultrasound contrast image that matches the feature point, and is specifically configured as follows:

[0083] For any feature point in the ultrasound contrast-enhanced image, determining a matching degree between the two feature points based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image;

[0084] Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points;

[0085] A target feature point is obtained through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point.

[0086] In one embodiment, the processor performs the step of obtaining a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point in the ultrasound contrast image and each target feature point, and is specifically configured as follows:

[0087] Randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point that matches the feature point;

[0088] Using the intermediate position transformation matrix to transform the position coordinates of each target feature point in the target ultrasound contrast imaging image, to obtain the transformed position coordinates of each target feature point;

[0089] For any feature point in the ultrasound contrast-enhanced image, a matching value is obtained according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast-enhanced image that matches the feature point;

[0090] If the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set;

[0091] Determining whether the number of the key feature point sets is greater than a fourth specified number;

[0092] If not, returning to the step of randomly extracting a third specified number of feature points from each feature point of the ultrasound contrast imaging image;

[0093] If so, the transformation matrix is ​​obtained based on the sets of key feature points.

[0094] In one embodiment, the processor performs the position transformation of the ROI region of the target ultrasound contrast image by using the transformation matrix to obtain the ROI region of the ultrasound contrast image, which is specifically configured as follows:

[0095] The transformation matrix is ​​multiplied by a position matrix corresponding to the ROI region of the target ultrasound contrast imaging image to obtain the ROI region of the ultrasound contrast imaging image.

[0096] In one embodiment, the processor executes the step of using the ROI region of each ultrasound contrast imaging image to obtain a time intensity curve, and is specifically configured as follows:

[0097] For any ultrasound contrast-enhanced image, an average value of pixel values ​​of each target pixel point in the ROI region of the ultrasound contrast-enhanced image is determined as the contrast energy intensity of the ultrasound contrast-enhanced image;

[0098] Based on the contrast energy intensity of each ultrasound contrast image, a time intensity curve of the ultrasound contrast is obtained.

[0099] In one embodiment, the processor is further configured to:

[0100] The target pixel point is determined by:

[0101] Traversing each pixel point in the target ultrasound contrast imaging image, wherein the traversed pixel points are pixel points before digital scan conversion;

[0102] For any pixel point traversed, digital scanning transformation is performed on the pixel point to obtain the position coordinates of the pixel point;

[0103] Comparing the position coordinates of the pixel point with the position coordinates of the target ultrasound contrast imaging ROI region to determine whether the pixel point is within the ROI region;

[0104] If it is determined that the pixel point is within the ROI area, the pixel point is determined to be the target sampling point.

[0105] According to a third aspect provided by an embodiment of the present disclosure, a computer storage medium is provided, wherein the computer storage medium stores a computer program, and the computer program is used to execute the method as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0107] Figure 1 A schematic diagram of an applicable scenario in an embodiment of the present disclosure;

[0108] Figure 2This is a schematic diagram of a quantitative analysis method of ultrasound contrast imaging according to an embodiment of the present disclosure;

[0109] Figure 3 is a schematic diagram of an ultrasound contrast imaging image according to an embodiment of the present disclosure;

[0110] Figure 4 A schematic diagram of a designated area of ​​a pixel point according to an embodiment of the present disclosure;

[0111] Figure 5 A schematic diagram of a neighborhood pixel point of a pixel point according to an embodiment of the present disclosure;

[0112] Figure 6 A schematic diagram of a process for determining a feature vector of each feature point according to an embodiment of the present disclosure;

[0113] Figure 7 is a schematic diagram of the gradient direction between pixels according to an embodiment of the present disclosure;

[0114] Figure 8 A schematic diagram of a process for determining a main gradient direction according to an embodiment of the present disclosure;

[0115] Fig. 9 A schematic diagram of a designated area of ​​a rotating feature point according to an embodiment of the present disclosure;

[0116] Fig.10 is a schematic diagram of feature point matching according to an embodiment of the present disclosure;

[0117] Fig.11 A schematic diagram of a process for determining target feature points according to an embodiment of the present disclosure;

[0118] Fig.12 A schematic diagram of a process for determining a transformation matrix between an ultrasound contrast-enhanced image and a target ultrasound contrast-enhanced image according to an embodiment of the present disclosure;

[0119] Fig.13 A schematic diagram of a process for determining a time intensity curve according to an embodiment of the present disclosure;

[0120] Fig.14 The second flowchart of the method for quantitative analysis of ultrasound contrast imaging according to one embodiment of the present disclosure;

[0121] Fig.15 A quantitative analysis device for ultrasound contrast imaging according to an embodiment of the present disclosure;

[0122] Fig.16 It is a schematic structural diagram of an ultrasonic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0123] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0124] In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0125] The application scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems. In the description of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more.

[0126] In the prior art, since the background of ultrasound contrast imaging sequence images changes dynamically, during a long scanning process, changes in the patient's breathing and / or body position will cause changes in the position of the ROI (region of interest) on the ultrasound contrast imaging image. Therefore, problems such as deformation of biological tissue movement and disappearance of the ROI area will occur, which in turn leads to a low accuracy rate in quantitative analysis of ultrasound contrast imaging images.

[0127] Therefore, the present disclosure provides a quantitative analysis method for ultrasound contrast images, by matching the feature points of each ultrasound contrast image with the target ultrasound contrast image, and then obtaining the position transformation matrix between each ultrasound contrast image and the target ultrasound contrast image based on the matched target feature points and the feature points in each ultrasound contrast image, and then transforming the position of the ROI area in the target ultrasound image based on the position transformation matrix, thereby obtaining the position of the ROI area in each ultrasound contrast image, and obtaining the time intensity curve based on each ROI position area. Therefore, in the present disclosure, the ROI area in each ultrasound contrast image is determined by the position transformation matrix between each frame of the ultrasound contrast image and the target ultrasound contrast image, thereby realizing automatic tracking of the ROI area, thereby improving the accuracy of quantitative analysis of ultrasound images. Below, the scheme of the present disclosure is described in detail in conjunction with the accompanying drawings.

[0128] like Figure 1As shown, an application scenario of a quantitative analysis method of ultrasound contrast imaging includes: an ultrasound device 10 and a memory 20; wherein:

[0129] After the ultrasound device 10 acquires the ultrasound contrast images of the same biological tissue stored in the memory 20, for any ultrasound contrast images of the biological tissue, the ultrasound contrast image is subjected to feature point extraction to obtain each feature point, and each feature point is subjected to feature extraction to obtain a feature vector of each feature point; for any feature point in the ultrasound contrast image, the ultrasound device 10 uses the feature vector of the feature point and the feature vectors of each feature point of the target ultrasound contrast image in each ultrasound contrast image to obtain a target feature point in the target ultrasound contrast image that matches the feature point; then the ultrasound device 10 obtains a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point in the ultrasound contrast image and each target feature point, and performs position transformation on the ROI area of ​​the target ultrasound contrast image through the transformation matrix to obtain the ROI area of ​​the ultrasound contrast image; finally, the ultrasound device 10 uses the ROI area of ​​each ultrasound contrast image to obtain a time intensity curve.

[0130] Among them, the description in this application only details a single ultrasound device 10 and a memory 20, but those skilled in the art should understand that the ultrasound device 10 and the memory 20 shown are intended to represent the operation of the ultrasound device 10 and the memory 20 involved in the technical solution of this application. It does not imply any limitation on the number, type or location of the ultrasound device 10 and the memory 20. It should be noted that if additional modules are added to the illustrated environment or individual modules are removed from it, the underlying concept of the example embodiment of this application will not be changed. In addition, although for the convenience of explanation, Figure 1 A bidirectional arrow from the memory 20 to the ultrasound device 10 is shown in the figure, but those skilled in the art will appreciate that the sending and receiving of the above data also needs to be implemented through a network.

[0131] It should be noted that the memory 20 in the embodiment of the present application may be, for example, a cache system, a hard disk storage, a memory storage, etc. In addition, the quantitative analysis method of ultrasound contrast imaging proposed in the present application is not only applicable to Figure 1 The application scenario shown is also applicable to any device capable of quantitative analysis of ultrasound contrast-enhanced images.

[0132] like Figure 2 FIG. 1 is a flow chart of the quantitative analysis method of ultrasound contrast imaging disclosed in the present invention, comprising the following steps:

[0133] Step 201: extracting feature points from any ultrasound contrast-enhanced image of the same biological tissue to obtain feature points;

[0134] The data corresponding to the ultrasound contrast image stored in this embodiment is the data before digital scan conversion. Since the number of ultrasound contrast images before digital scan conversion is much smaller than the amount of data after digital scan conversion, for example, Figure 3 As shown, Figure 3 The image on the left is the image before the ultrasound contrast image is digitally scanned and converted, and the image on the right is the image after the ultrasound contrast image is digitally scanned and converted. It can be seen that the size of the image on the left is smaller than that of the image on the right, and the corresponding data volume is also much smaller than the data volume after digital scan conversion. Therefore, storage space can be saved and computing efficiency can be improved.

[0135] Furthermore, the ultrasound contrast images used in step 201, step 202 and step 203 in this embodiment are all ultrasound contrast images before digital scan conversion. However, before executing step 204, the data corresponding to the ultrasound contrast image needs to be digitally scan converted, that is, the data after digital scan conversion needs to be used to determine the transformation matrix.

[0136] It should be noted that digital scan conversion must be used in the quantitative analysis process of ultrasound contrast imaging, so it will not be described in detail in this embodiment.

[0137] In one embodiment, feature points may be extracted from the ultrasound contrast imaging image in step 201 to obtain the feature points in the following two ways:

[0138] Method 1: For any pixel point in the ultrasound contrast image, if there are target pixel points greater than a first specified number in the specified area of ​​the pixel point, the pixel point is determined to be the feature point, wherein the target pixel point is a pixel point whose absolute value of the difference between the pixel value and the pixel value of the pixel point is not greater than a first preset threshold.

[0139] In this embodiment, the designated area of ​​the pixel point is a circle with the pixel point as the center and a preset value as the radius.

[0140] For example, Figure 4 As shown, the circle in the figure is a designated area of ​​pixel point A. If there are target pixel points greater than a first designated number in the designated area, pixel point A is determined as a feature point.

[0141] It should be noted that the first preset threshold and the specified number in this embodiment can be limited according to actual conditions, and this embodiment does not limit the values ​​of the first preset threshold and the specified number.

[0142] Method 2: For any pixel point in the ultrasound contrast imaging image, if the pixel point is a pixel point with the largest pixel value or the smallest pixel value among all pixel points in its neighborhood, the pixel point is determined to be the feature point.

[0143] For example, Figure 5 As shown, the pixels in the neighborhood of pixel point E are pixel point A, pixel point B, pixel point C, pixel point D, pixel point F, pixel point G, pixel point H and pixel point I. If pixel point E is the pixel point with the largest pixel value or the smallest pixel value among pixel point A, pixel point B, pixel point C, pixel point D, pixel point F, pixel point G, pixel point H and pixel point I, then pixel point E is determined to be a feature point.

[0144] Step 202: extracting features from each feature point to obtain a feature vector of each feature point;

[0145] In one embodiment, Figure 6 As shown, it is a schematic diagram of the process of determining the feature vector of each feature point, including the following steps:

[0146] Step 601: for any feature point, based on the pixel values ​​of each pixel in a designated area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixels;

[0147] In one embodiment, the gradient magnitude and gradient direction between any two pixels are determined in the following manner:

[0148] For any two pixel points in the designated area, the direction from one pixel point to the other pixel point of the two pixel points is determined as the gradient direction, and the difference in pixel values ​​of the two pixel points is determined as the gradient amplitude corresponding to the gradient direction.

[0149] For example, Figure 7 As shown in the figure, the direction from pixel point M to pixel point N is the gradient direction of pixel point M→N, and the gradient amplitude corresponding to the gradient direction of pixel point M→N is the difference obtained by subtracting the pixel value of pixel point N from the pixel value of pixel point M. In addition, the direction from pixel point N to pixel point M is the gradient direction of pixel point N→M, and the gradient amplitude corresponding to the gradient direction of pixel point N→M is the difference obtained by subtracting the pixel value of pixel point M from the pixel value of pixel point N.

[0150] Step 602: Obtain the main gradient direction of the feature point by using the gradient magnitude and gradient direction between the pixels in the designated area;

[0151] In one embodiment, Figure 8 As shown, it is a schematic diagram of the process of determining the main direction of the gradient, which includes the following steps:

[0152] Step 801: for any gradient direction, counting the number of the gradient directions in the gradient directions between the pixels in the specified area;

[0153] Step 802: multiplying the number of the gradient directions by the average value of each gradient amplitude corresponding to the gradient direction in the designated area to obtain the target number of the gradient directions;

[0154] For example, the gradient directions between the pixels in the specified area include the upper direction, the lower direction, the upper left direction, the lower left direction and the upper right direction. If the number of upper directions in the specified area is 10, the number of lower directions is 11, the number corresponding to the upper left direction is 20, the number corresponding to the lower left direction is 25, and the number corresponding to the upper right direction is 10. And the gradient amplitude corresponding to the upper direction is 3, the gradient amplitude corresponding to the lower direction is 5, the gradient amplitude corresponding to the upper left direction is 2, the gradient amplitude corresponding to the lower left direction is 4, and the gradient amplitude corresponding to the upper right direction is 4. Then it is determined that the target number corresponding to the upper direction is 30, the target number corresponding to the lower direction is 55, the target number corresponding to the upper left direction is 40, the target number corresponding to the lower left direction is 100, and the target number corresponding to the upper right direction is 40.

[0155] Step 803: Determine the main gradient direction of the feature point by taking the gradient direction with the largest target number among the gradient directions in the designated area.

[0156] Based on the aforementioned gradient directions and the target numbers corresponding to the gradient directions, the gradient direction with the largest target number is the downward direction, and the downward direction is determined as the main direction.

[0157] Step 603: taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area;

[0158] For example, Fig. 9 As shown, the circle in the figure is the designated area of ​​the feature point A. If it is determined that the main gradient direction of the feature point A is the downward direction, the designated area of ​​the feature point A is rotated 180° clockwise to the downward direction to obtain the rotated designated area.

[0159] Step 604: Divide the rotated designated area into a second designated number of sub-areas, and determine the gradient direction between each pixel point in each sub-area;

[0160] It should be noted that each sub-region after division is a sub-region of the same size and shape. In addition, the second specified number in this embodiment can be set according to actual conditions, and this embodiment does not limit this. And determining the gradient direction between each pixel point in each sub-region is the same as the direction of determining the gradient direction between the pixel points described above, and this embodiment will not be repeated here.

[0161] Step 605: for any sub-region, determining the number of each pixel point in the sub-region in each target gradient direction;

[0162] Wherein, the target gradient direction is a pre-set gradient. The target gradient direction in this embodiment includes an upper direction, a lower direction, a left direction, a right direction, an upper left direction, a lower left direction, an upper right direction, and a lower right direction. However, the target gradient direction is not limited in this embodiment, and the target gradient direction can be set according to actual conditions.

[0163] Step 606: Obtain a feature vector of the feature point through the number of each pixel point in each sub-region in each target gradient direction.

[0164] In one embodiment, the number of each pixel point in each target gradient direction is arranged according to a preset order of the target gradient direction to obtain a feature vector of the feature point.

[0165] For example, the target gradient directions include upward, downward, left, right, upper left, lower left, upper right and lower right, and the corresponding numbers of each target gradient direction are 4, 6, 2, 5, 9, 3, 2, 5. And the preset order of each target gradient direction is: upward, downward, left, right, upper left, lower left, upper right and lower right, then the feature vector is [4, 6, 2, 5, 9, 3, 2, 5].

[0166] Step 203: for any feature point in the ultrasound contrast-enhanced image, using a feature vector of the feature point and feature vectors of each feature point of a target ultrasound contrast-enhanced image in each ultrasound contrast-enhanced image, obtain a target feature point in the target ultrasound contrast-enhanced image that matches the feature point;

[0167] The target ultrasound contrast imaging image is selected and set by the doctor.

[0168] For example, Fig.10 As shown, each matched feature point is obtained after each feature point in a frame of ultrasound contrast imaging is matched with each feature point in a target ultrasound contrast imaging image.

[0169] In one embodiment, Fig.11 As shown, it is a schematic diagram of the process of determining the target feature points, including the following steps:

[0170] Step 1101: for any feature point in the ultrasound contrast-enhanced image, based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image, determining a matching degree between the two feature points;

[0171] In one embodiment, the matching degree of two feature points is determined in the following manner:

[0172] For any data in the feature vector of the feature point, determine the target data with the same target gradient direction as the data in the feature vector of any feature point in the target ultrasound contrast image, subtract the data from the target data to obtain a data difference, square the data difference to obtain the first intermediate data, add the intermediate data corresponding to each data in the feature vector of each feature point and perform square root calculation to obtain the matching degree between the feature point and any feature point in the target ultrasound contrast image. The matching degree of any two feature points can be determined by formula (1):

[0173]

[0174] Among them, P is the matching degree of any two feature points, a1~a n is the data in the feature vector of the feature point, b1~b n is the data in the feature vector of any feature point in the target ultrasound contrast imaging image.

[0175] Step 1102: Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points;

[0176] The first feature point is the feature point in the target ultrasound contrast image with the highest matching degree with the feature point, and the second feature point is the feature point in the target ultrasound contrast image with the second highest matching degree with the feature point.

[0177] For example, the target ultrasound contrast image includes feature point 1, feature point 2, feature point 3, and feature point 4. If feature point 1 has the highest matching degree with feature point A in the ultrasound contrast image, feature point 1 is determined as the first feature point of feature point A. If feature point 4 is determined to have the second highest matching degree with feature point A in the ultrasound contrast image, feature point A is determined as the second feature point of feature point A.

[0178] Step 1103: Obtain a target feature point through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point.

[0179] In one embodiment, the target feature points are determined by:

[0180] Divide the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point to obtain a matching degree ratio, and compare the matching degree ratio with a preset matching degree ratio. If the matching degree ratio is less than the preset matching degree ratio, determine that the first feature point is the target feature point of the feature point.

[0181] Step 204: obtaining a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point and each target feature point in the ultrasound contrast image;

[0182] In one embodiment, Fig.12 As shown, it is a schematic diagram of a process for determining a transformation matrix between an ultrasound contrast-enhanced image and a target ultrasound contrast-enhanced image, comprising the following steps:

[0183] Step 1201: randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point matching the feature point;

[0184] In one embodiment, the intermediate position transformation matrix is ​​obtained by dividing the matrix composed of the position coordinates of each feature point by the matrix composed of the position coordinates of each target feature point.

[0185] The matrix composed of the position coordinates of the feature points has the same form as the matrix composed of the position coordinates of each target feature point, for example, the first row corresponds to the horizontal coordinate of each feature point, and the second row corresponds to the vertical coordinate of each feature point.

[0186] Step 1202: transforming the position coordinates of each target feature point in the target ultrasound contrast image using the intermediate position transformation matrix to obtain the transformed position coordinates of each target feature point;

[0187] In one embodiment, step 1202 may be implemented as follows: multiplying the intermediate position transformation matrix by a matrix composed of position coordinates of each target feature point in the target ultrasound contrast imaging image to obtain the transformed position coordinates of each target feature point.

[0188] Step 1203: For any feature point in the ultrasound contrast image, a matching value is obtained according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast image that matches the feature point. The matching value can be obtained by formula (2):

[0189]

[0190] Among them, d is the matching value, x1 is the horizontal coordinate of the feature point, x2 is the converted horizontal coordinate of the target feature point matching the feature point in the target ultrasound contrast image, y1 is the vertical coordinate of the feature point, and y2 is the converted vertical coordinate of the target feature point matching the feature point in the target ultrasound contrast image.

[0191] Step 1204: if the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set;

[0192] It should be noted that the second preset threshold can be set according to actual conditions, and this embodiment does not limit it here.

[0193] Step 1205: determine whether the number of the key feature point set is greater than a fourth specified number, if so, execute step 1206, if not, return to step 1201;

[0194] It should be noted that the fourth designated number can be set according to actual conditions and is not limited in this embodiment.

[0195] Step 1206: Obtain the transformation matrix based on the key feature point sets.

[0196] The key feature point set includes a plurality of feature points and a plurality of target feature points matching the plurality of feature points.

[0197] In one embodiment, the transformation matrix is ​​determined by:

[0198] The transformation matrix is ​​obtained by dividing the matrix composed of the position coordinates of the plurality of feature points by the matrix composed of the plurality of target feature points.

[0199] Step 205: performing position transformation on the ROI region of the target ultrasound contrast-enhanced image by using the transformation matrix to obtain the ROI region of the ultrasound contrast-enhanced image;

[0200] In one embodiment, step 205 may be implemented as: multiplying the transformation matrix by the position matrix corresponding to the ROI region of the target ultrasound contrast image to obtain the ROI region of the ultrasound contrast image.

[0201] Step 206: Obtain a time intensity curve using the ROI region of each ultrasound contrast imaging image.

[0202] In one embodiment, Fig.13 As shown, it is a schematic diagram of the process of determining the time intensity curve, which includes the following steps:

[0203] Step 1301: for any ultrasound contrast-enhanced image, determining the average value of the pixel values ​​of each target pixel point in the ROI region of the ultrasound contrast-enhanced image as the contrast energy intensity of the ultrasound contrast-enhanced image;

[0204] In one embodiment, the target pixel is determined by:

[0205] Each pixel point in the target ultrasound contrast image is traversed, wherein the traversed pixel points are pixel points before digital scan conversion; for any traversed pixel point, the pixel point is digitally scanned and converted to obtain the position coordinates of the pixel point; the position coordinates of the pixel point are compared with the position coordinates of the ROI area of ​​the target ultrasound contrast image to determine whether the pixel point is within the ROI area; if it is determined that the pixel point is within the ROI area, the pixel point is determined to be the target sampling point.

[0206] It should be noted that: in order to solve the problem of too much ultrasound contrast imaging data, the data stored in this embodiment is the data before the ultrasound contrast imaging image is digitally scanned and transformed, so before using the position coordinates of the pixel point to compare with the position coordinates of the target ultrasound contrast imaging ROI area, it is necessary to first perform digital scanning and transformation on the pixel point. The horizontal coordinate of the pixel point after digital scanning and transformation can be determined by formula (3):

[0207] P x =(R+(N-1)*S)*sinθ......(3);

[0208] Among them, P x is the horizontal coordinate of the pixel after digital scanning transformation, R is the radius of the ultrasonic device probe, N is the index of the pixel, S is the distance between each pixel, and θ is the preset digital scanning transformation angle.

[0209] The vertical coordinate of the pixel after digital scanning transformation can be determined by formula (4):

[0210] P y =(R+(N-1)*S)*cosθ-R*sinα......(4);

[0211] Among them, P y is the vertical coordinate of the pixel after digital scanning transformation, R is the radius of the ultrasonic equipment probe, N is the index of the pixel, S is the distance between each pixel, and θ is the preset digital scanning transformation angle.

[0212] Step 1302: Based on the contrast energy intensity of each ultrasound contrast image, a time intensity curve of the ultrasound contrast is obtained.

[0213] In one embodiment, the time corresponding to each ultrasound contrast image is used as the horizontal coordinate, and the contrast energy intensity of each ultrasound contrast image is used as the vertical coordinate to obtain the time intensity coordinate corresponding to each ultrasound contrast image, and the time intensity curve is obtained using the time intensity coordinate corresponding to each ultrasound contrast image.

[0214] It should be noted that the method for analyzing the time intensity curve is not limited in this embodiment and can be selected and set according to actual conditions.

[0215] In order to further understand the technical solution of the present disclosure, Fig.14 A detailed description may include the following steps:

[0216] Step 1401: extracting feature points from any ultrasound contrast-enhanced image of the same biological tissue to obtain feature points;

[0217] Step 1402: for any feature point, based on the pixel values ​​of each pixel in a designated area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixels;

[0218] Step 1403: using the gradient magnitude and gradient direction between the pixels in the designated area, obtaining the main gradient direction of the feature point;

[0219] Step 1404: taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area;

[0220] Step 1405: Divide the rotated designated area into a second designated number of sub-areas, and determine the gradient direction between each pixel point in each sub-area;

[0221] Step 1406: for any sub-region, determine the number of each pixel point in the sub-region in each target gradient direction;

[0222] Step 1407: Obtain a feature vector of the feature point by counting the number of pixels in each sub-region in each target gradient direction;

[0223] Step 1408: for any feature point in the ultrasound contrast-enhanced image, based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image, determining a matching degree between the two feature points;

[0224] Step 1409: Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points;

[0225] Step 1410: Obtaining a target feature point through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point;

[0226] Step 1411: randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point matching the feature point;

[0227] Step 1412: transforming the position coordinates of each target feature point in the target ultrasound contrast image using the intermediate position transformation matrix to obtain the transformed position coordinates of each target feature point;

[0228] Step 1413: for any feature point in the ultrasound contrast-enhanced image, obtain a matching value according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast-enhanced image that matches the feature point;

[0229] Step 1414: if the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set;

[0230] Step 1415: determine whether the number of the key feature point set is greater than the fourth specified number, if so, execute step 1416, if not, return to step 1411;

[0231] Step 1416: Obtain the transformation matrix based on the key feature point sets;

[0232] Step 1417: performing position transformation on the ROI region of the target ultrasound contrast-enhanced image by using the transformation matrix to obtain the ROI region of the ultrasound contrast-enhanced image;

[0233] Step 1418: Obtain a time intensity curve using the ROI region of each ultrasound contrast imaging image.

[0234] Based on the same disclosed concept, the quantitative analysis method of ultrasound contrast images disclosed above can also be implemented by a quantitative analysis device for ultrasound contrast images. The effect of the quantitative analysis device for ultrasound contrast images is similar to that of the aforementioned method, and will not be described in detail here.

[0235] Fig.15 The figure is a schematic diagram of the structure of a quantitative analysis device for ultrasound contrast imaging according to an embodiment of the present disclosure.

[0236] like Fig.15As shown, the quantitative analysis device 1500 of ultrasound contrast imaging of the present disclosure may include a feature extraction module 1510 , a feature vector determination module 1520 , a matching module 1530 , a transformation matrix determination module 1540 , a ROI region conversion module 1550 and a time intensity curve determination module 1560 .

[0237] The feature extraction module 1510 is used to extract feature points from any one of the ultrasound contrast images of the same biological tissue to obtain each feature point; and

[0238] A feature vector determination module 1520 is used to extract features from each feature point to obtain a feature vector of each feature point;

[0239] A matching module 1530 is used to obtain, for any feature point in the ultrasound contrast image, a target feature point in the target ultrasound contrast image that matches the feature point by using a feature vector of the feature point and a feature vector of each feature point of a target ultrasound contrast image in each ultrasound contrast image;

[0240] A transformation matrix determination module 1540 is used to obtain a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point and each target feature point in the ultrasound contrast image;

[0241] The ROI region conversion module 1550 is used to perform position transformation on the ROI region of the target ultrasound contrast imaging image through the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image;

[0242] The time intensity curve determination module 1560 is used to obtain a time intensity curve using the ROI region of each ultrasound contrast imaging image.

[0243] In one embodiment, the feature extraction module 1510 is specifically used to:

[0244] For any pixel point in the ultrasound contrast imaging image, if there are target pixel points greater than a first specified number in a specified area of ​​the pixel point, the pixel point is determined to be the feature point, wherein the target pixel point is a pixel point whose absolute value of the difference between the pixel value and the pixel value of the pixel point is not greater than a first preset threshold; or,

[0245] For any pixel point in the ultrasound contrast imaging image, if the pixel point is a pixel point with the largest pixel value or the smallest pixel value among the pixel points in its neighborhood, the pixel point is determined to be the feature point.

[0246] In one embodiment, the feature vector determination module 1520 performs the feature extraction on each feature point to obtain the feature vector of each feature point, which is specifically used for:

[0247] For any feature point, based on the pixel values ​​of each pixel point in the specified area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixel points;

[0248] Using the gradient magnitude and gradient direction between the pixels in the specified area, the main gradient direction of the feature point is obtained;

[0249] Taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area;

[0250] Dividing the rotated designated area into a second designated number of sub-areas, and determining the gradient direction between each pixel point in each sub-area;

[0251] For any sub-region, determining the number of each pixel point in the sub-region in each target gradient direction;

[0252] The feature vector of the feature point is obtained by the number of each pixel point in each sub-region in each target gradient direction.

[0253] In one embodiment, the feature vector determination module 1520 performs the step of determining the gradient magnitude and gradient direction between any two pixels based on the pixel values ​​of each pixel within the specified area of ​​the feature point, specifically for:

[0254] For any two pixel points in the designated area, the direction from one pixel point to the other pixel point of the two pixel points is determined as the gradient direction, and the difference in pixel values ​​of the two pixel points is determined as the gradient amplitude corresponding to the gradient direction.

[0255] In one embodiment, the feature vector determination module 1520 performs the step of using the gradient magnitude and gradient direction between the pixels in the specified area to obtain the main gradient direction of the feature point, specifically for:

[0256] For any gradient direction, counting the number of the gradient directions in the gradient directions between the pixels in the specified area; and

[0257] Multiplying the number of the gradient directions by the average value of each gradient amplitude corresponding to the gradient direction in the specified area to obtain the target number of the gradient directions;

[0258] The gradient direction with the largest target number among the gradient directions in the designated area is determined as the main gradient direction of the feature point.

[0259] In one embodiment, the matching module 1530 is specifically configured to:

[0260] For any feature point in the ultrasound contrast-enhanced image, determining a matching degree between the two feature points based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image;

[0261] Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points;

[0262] A target feature point is obtained through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point.

[0263] In one embodiment, the transformation matrix determination module 1540 is specifically configured to:

[0264] Randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point that matches the feature point;

[0265] Using the intermediate position transformation matrix to transform the position coordinates of each target feature point in the target ultrasound contrast imaging image, to obtain the transformed position coordinates of each target feature point;

[0266] For any feature point in the ultrasound contrast-enhanced image, a matching value is obtained according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast-enhanced image that matches the feature point;

[0267] If the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set;

[0268] Determining whether the number of the key feature point sets is greater than a fourth specified number;

[0269] If not, returning to the step of randomly extracting a third specified number of feature points from each feature point of the ultrasound contrast imaging image;

[0270] If so, the transformation matrix is ​​obtained based on the sets of key feature points.

[0271] In one embodiment, the ROI region conversion module 1550 is specifically used to:

[0272] The transformation matrix is ​​multiplied by a position matrix corresponding to the ROI region of the target ultrasound contrast imaging image to obtain the ROI region of the ultrasound contrast imaging image.

[0273] In one embodiment, the time intensity curve determination module 1560 is specifically configured to:

[0274] For any ultrasound contrast-enhanced image, an average value of pixel values ​​of each target pixel point in the ROI region of the ultrasound contrast-enhanced image is determined as the contrast energy intensity of the ultrasound contrast-enhanced image;

[0275] Based on the contrast energy intensity of each ultrasound contrast image, a time intensity curve of the ultrasound contrast is obtained.

[0276] In one embodiment, the apparatus further comprises:

[0277] The target pixel point determination module 1570 is used to determine the target pixel point by:

[0278] Traversing each pixel point in the target ultrasound contrast imaging image, wherein the traversed pixel points are pixel points before digital scan conversion;

[0279] For any pixel point traversed, digital scanning transformation is performed on the pixel point to obtain the position coordinates of the pixel point;

[0280] Comparing the position coordinates of the pixel point with the position coordinates of the target ultrasound contrast imaging ROI region to determine whether the pixel point is within the ROI region;

[0281] If it is determined that the pixel point is within the ROI area, the pixel point is determined to be the target sampling point.

[0282] After introducing a method and apparatus for quantitatively analyzing ultrasound contrast images according to an exemplary embodiment of the present disclosure, next, an ultrasound device according to another exemplary embodiment of the present disclosure is introduced.

[0283] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0284] In some possible embodiments, the ultrasound device according to the present disclosure may include at least one processor and at least one computer storage medium. The computer storage medium stores program code, and when the program code is executed by the processor, the processor executes the steps of the quantitative analysis method of ultrasound contrast images according to various exemplary embodiments of the present disclosure described above in this specification. For example, the processor may execute the following steps: Figure 2 Steps 201-206 shown in .

[0285] Refer to the following Fig.16 16 to describe the ultrasound device 1600 according to this embodiment of the present disclosure. Fig.16 The displayed ultrasound device 1600 is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0286] like Fig.16 As shown, the ultrasound device 1600 is presented in the form of a general ultrasound device. The components of the ultrasound device 1600 may include, but are not limited to: the at least one processor 1601, the at least one computer storage medium 1602, and a bus 1603 connecting different system components (including the computer storage medium 1602 and the processor 1601).

[0287] Bus 1603 represents one or more of several types of bus structures, including a computer storage media bus or computer storage media controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0288] Computer storage media 1602 may include readable media in the form of volatile computer storage media, such as random access computer storage media (RAM) 1621 and / or cache storage media 1622 , and may further include read-only computer storage media (ROM) 1623 .

[0289] The computer storage medium 1602 may also include a program / utility 1625 having a set (at least one) of program modules 1624, such program modules 1624 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0290] The ultrasound device 1600 may also communicate with one or more external devices 1604 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the ultrasound device 1600, and / or communicate with any device that enables the ultrasound device 1600 to communicate with one or more other ultrasound devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1605. In addition, the ultrasound device 1600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1606. As shown, the network adapter 1606 communicates with other modules for the ultrasound device 1600 via a bus 1603. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the ultrasound device 600, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0291] In some possible embodiments, various aspects of the method for quantitative analysis of ultrasound contrast images provided by the present disclosure may also be implemented in the form of a program product, which includes program code. When the program product is run on a computer device, the program code is used to enable the computer device to execute the steps of the method for quantitative analysis of ultrasound contrast images according to various exemplary embodiments of the present disclosure described above in this specification.

[0292] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access computer storage medium (RAM), a read-only computer storage medium (ROM), an erasable programmable read-only computer storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only computer storage medium (CD-ROM), an optical computer storage medium, a magnetic computer storage medium, or any suitable combination of the above.

[0293] The program product for quantitative analysis of ultrasound contrast imaging of the embodiment of the present disclosure may adopt a portable compact disk read-only computer storage medium (CD-ROM) and include program code, and may be run on an ultrasound device. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0294] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0295] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0296] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user ultrasound device, partially on the user device, as a separate software package, partially on the user ultrasound device and partially on a remote ultrasound device, or entirely on a remote ultrasound device or server. In the case of a remote ultrasound device, the remote ultrasound device may be connected to the user ultrasound device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external ultrasound device (e.g., via the Internet using an Internet service provider).

[0297] It should be noted that although several modules of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be embodied.

[0298] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0299] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk computer storage media, CD-ROM, optical computer storage media, etc.) containing computer-usable program codes.

[0300] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0301] These computer program instructions may also be stored in a computer-readable computer storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable computer storage medium produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0302] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0303] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. An ultrasonic device, characterized in that: The device comprises a storage unit and a processor, wherein: The storage unit is configured to store each ultrasound contrast image of the biological tissue; The processor is configured to: For any ultrasound contrast-enhanced image of the same biological tissue, feature points are extracted from the ultrasound contrast-enhanced image to obtain feature points; and, Performing feature extraction on each of the feature points to obtain a feature vector of each of the feature points; For any feature point in the ultrasound contrast-enhanced image, using a feature vector of the feature point and feature vectors of each feature point of a target ultrasound contrast-enhanced image in each ultrasound contrast-enhanced image, a target feature point in the target ultrasound contrast-enhanced image that matches the feature point is obtained; Based on each feature point and each target feature point in the ultrasound contrast image, a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image is obtained; Performing a position transformation on the ROI region of the target ultrasound contrast imaging image by using the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image; The time intensity curve is obtained by using the ROI region of each ultrasound contrast image.

2. The ultrasonic device according to claim 1, characterized in that The processor performs the feature point extraction on the ultrasound contrast imaging image to obtain each feature point, and is specifically configured as follows: For any pixel point in the ultrasound contrast imaging image, if there are target pixel points greater than a first specified number in a specified area of ​​the pixel point, the pixel point is determined to be the feature point, wherein the target pixel point is a pixel point whose absolute value of the difference between the pixel value and the pixel value of the pixel point is not greater than a first preset threshold; or, For any pixel point in the ultrasound contrast imaging image, if the pixel point is a pixel point with the largest pixel value or the smallest pixel value among the pixel points in its neighborhood, the pixel point is determined to be the feature point.

3. The ultrasonic device according to claim 1, characterized in that The processor performs the feature extraction on each feature point to obtain the feature vector of each feature point, and is specifically configured as follows: For any feature point, based on the pixel values ​​of each pixel point in the specified area of ​​the feature point, determine the gradient magnitude and gradient direction between any two pixel points; Using the gradient magnitude and gradient direction between the pixels in the specified area, the main gradient direction of the feature point is obtained; Taking the feature point as the center, rotating the designated area of ​​the feature point according to the main direction of the gradient to obtain a rotated designated area; Dividing the rotated designated area into a second designated number of sub-areas, and determining the gradient direction between each pixel point in each sub-area; For any sub-region, determining the number of each pixel point in the sub-region in each target gradient direction; The feature vector of the feature point is obtained by the number of each pixel point in each sub-region in each target gradient direction.

4. The ultrasonic device according to claim 3, characterized in that The processor executes the step of determining the gradient magnitude and gradient direction between any two pixels based on the pixel values ​​of each pixel in the designated area of ​​the feature point, and is specifically configured as follows: For any two pixels in the designated area, the direction from one pixel to the other pixel is determined as the gradient direction, and the difference in pixel values ​​of the two pixels is determined as the gradient amplitude corresponding to the gradient direction.

5. The ultrasonic device according to claim 3, characterized in that The processor executes the step of using the gradient magnitude and gradient direction between the pixels in the designated area to obtain the main gradient direction of the feature point, and is specifically configured as follows: For any gradient direction, counting the number of the gradient directions in the gradient directions between the pixels in the specified area; and Multiplying the number of the gradient directions by the average value of each gradient amplitude corresponding to the gradient direction in the specified area to obtain the target number of the gradient directions; The gradient direction with the largest target number among the gradient directions in the designated area is determined as the main gradient direction of the feature point.

6. The ultrasonic device according to claim 1, characterized in that The processor executes the step of using the feature vector of the feature point and the feature vector of each feature point of the target ultrasound contrast image in each ultrasound contrast image to obtain the target feature point in the target ultrasound contrast image that matches the feature point, and is specifically configured as follows: For any feature point in the ultrasound contrast-enhanced image, determining a matching degree between the two feature points based on a feature vector of the feature point and a feature vector of any feature point in the target ultrasound contrast-enhanced image; Determine a first feature point and a second feature point in the target ultrasound contrast imaging image by using the matching degree between the feature points; A target feature point is obtained through the matching degree between the first feature point and the feature point and the matching degree between the second feature point and the feature point.

7. The ultrasonic device according to claim 1, characterized in that The processor executes the step of obtaining a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image based on each feature point in the ultrasound contrast image and each target feature point, and is specifically configured as follows: Randomly extracting a third specified number of feature points from the feature points of the ultrasound contrast imaging image, and obtaining an intermediate position transformation matrix using the position coordinates of each feature point and the position coordinates of each target feature point that matches the feature point; Using the intermediate position transformation matrix to transform the position coordinates of each target feature point in the target ultrasound contrast imaging image, to obtain the transformed position coordinates of each target feature point; For any feature point in the ultrasound contrast-enhanced image, a matching value is obtained according to the position coordinates of the feature point and the converted position coordinates of a target feature point in the target ultrasound contrast-enhanced image that matches the feature point; If the matching value is less than a second preset threshold, determining the feature point and the target feature point as a key feature point set; Determining whether the number of the key feature point sets is greater than a fourth specified number; If not, returning to the step of randomly extracting a third specified number of feature points from each feature point of the ultrasound contrast imaging image; If so, the transformation matrix is ​​obtained based on the sets of key feature points.

8. The ultrasonic device according to claim 1, characterized in that The processor executes the step of using the ROI area of ​​each ultrasound contrast imaging image to obtain a time intensity curve, and is specifically configured as follows: For any ultrasound contrast-enhanced image, an average value of pixel values ​​of each target pixel point in the ROI region of the ultrasound contrast-enhanced image is determined as the contrast energy intensity of the ultrasound contrast-enhanced image; Based on the contrast energy intensity of each ultrasound contrast image, a time intensity curve of the ultrasound contrast is obtained.

9. The ultrasonic device according to claim 1, characterized in that The processor is further configured to: The target pixel point is determined by: Traversing each pixel point in the target ultrasound contrast imaging image, wherein the traversed pixel points are pixel points before digital scan conversion; For any pixel point traversed, digital scanning transformation is performed on the pixel point to obtain the position coordinates of the pixel point; Comparing the position coordinates of the pixel point with the position coordinates of the target ultrasound contrast imaging ROI region to determine whether the pixel point is within the ROI region; If it is determined that the pixel point is within the ROI area, the pixel point is determined to be the target sampling point.

10. A quantitative analysis method for ultrasound contrast imaging, characterized in that: The method comprises: For any ultrasound contrast-enhanced image of the same biological tissue, feature points are extracted from the ultrasound contrast-enhanced image to obtain feature points; and, Performing feature extraction on each of the feature points to obtain a feature vector of each of the feature points; For any feature point in the ultrasound contrast-enhanced image, using a feature vector of the feature point and feature vectors of each feature point of a target ultrasound contrast-enhanced image in each ultrasound contrast-enhanced image, a target feature point in the target ultrasound contrast-enhanced image that matches the feature point is obtained; Based on each feature point and each target feature point in the ultrasound contrast image, a transformation matrix between the ultrasound contrast image and the target ultrasound contrast image is obtained; Performing a position transformation on the ROI region of the target ultrasound contrast imaging image by using the transformation matrix to obtain the ROI region of the ultrasound contrast imaging image; The time intensity curve is obtained by using the ROI region of each ultrasound contrast image.

Images