CN104680481A - Ultrasonic auxiliary scanning method and ultrasonic auxiliary scanning system - Google Patents

Abstract

The invention discloses an ultrasonic-assisted scanning method and system. On the basis of generating real-time ultrasound images, the method performs a matching operation on the acquired real-time images and the library images in the image library, so as to instantly feed back the correctness of the current scanning operation to the user. The method can further output graphic and textual help information according to the matching result. If the current real-time image is a standard section image of a certain tissue or organ, the relevant graphic information of the standard section will be automatically called up to improve the convenience of operation. If the standard section image cannot be obtained, the user will be prompted how to adjust the position of the probe so as to obtain the desired image quickly and accurately. The method and system of the invention improve user interaction and user guidance, and can significantly improve the effect of auxiliary scanning.

Description

Ultrasound-assisted scanning method and system

technical field

The invention belongs to the technical field of ultrasonic imaging, and relates to an ultrasonic-assisted scanning method and system.

Background technique

Ultrasound instruments are generally used by doctors to observe the internal tissue structure of the human body. The doctor places the operating probe on the skin surface corresponding to the part of the human body to obtain an ultrasonic image of the part. Due to its safety, convenience, non-destructive, and cheap features, ultrasound has become the main auxiliary means for doctors to diagnose. Due to the complexity of the operation of ultrasound equipment, it is necessary for the operating doctor to have a very clear understanding of the spatial structure of each organ and tissue of the human body in order to make a standard section of each organ and tissue. Newly hired ultrasound doctors, clinicians in emerging fields, and private clinics Many groups of people, such as doctors and some nursing staff, have the need to improve ultrasound knowledge and technology, and all face the practical problem of lack of training resources.

The advantage of integrating teaching software on the ultrasound system is that users can learn and operate while learning, rather than simply learning theoretical knowledge through books, which greatly improves the training efficiency. However, although the current ultrasound-assisted teaching system can realize both pictures and texts and step-by-step teaching, it is only when the user selects a standard section that the system displays the standard image of the section and related graphic explanations. It is necessary to hold the probe with one hand, and it is inconvenient to select the desired section. In addition, the existing ultrasonic teaching system has poor operation interaction, and the system cannot give feedback according to the real-time operation of the user. Therefore, the user cannot judge the correctness of his own operation well, and cannot obtain information based on his own situation in the actual operation link. effective guidance. Therefore, it is necessary to help users complete the learning and improvement of ultrasonic scanning technology faster and better.

Contents of the invention

Aiming at the above-mentioned technical problems existing in the teaching system integrated with ultrasonic instruments, the present invention provides a real-time feedback on whether the user's operation is correct, and automatically calls out the detailed explanation of the pictures and texts under the standard section according to the operation result or guides how to adjust the operation. An ultrasound-assisted scanning system and method for obtaining a standard section.

According to a first aspect of the present invention, an ultrasound-assisted scanning method is provided. The method includes transmitting ultrasonic waves to a body under test at a probe position, receiving echo signals reflected by the body under test and generating a current real-time image;

The method also includes:

calling a plurality of library images from a pre-established image library, the plurality of library images including standard images reflecting clinical standard slices of the body under test;

performing similarity matching on the generated real-time image to the plurality of library images; and

Outputting the matching result of the real-time image and the plurality of library images, and calling the standard image according to the matching result or assisting in explaining how to adjust the position of the probe to obtain a real-time image matching the standard image.

According to a field aspect of the present invention, an ultrasound-assisted scanning system is provided. The system includes:

The probe is used to transmit ultrasonic waves to the body under test at a probe position and receive echo signals reflected by the body under test;

a signal processor, configured to process the echo signal and generate a current real-time image accordingly;

a display for displaying said real-time image generated by the output;

The ultrasound-assisted scanning system also includes:

The image library is used to store a plurality of library images established in advance, and the plurality of library images include standard images reflecting clinical standard sections of the body under test;

an image matching module, configured to perform similarity matching between the generated real-time image and the plurality of library images; and

The output configuration module is used to enable the display to output the matching result of the real-time image and the plurality of library images, and call the standard image according to the matching result or assist in explaining how to adjust the probe position to obtain the matching result of the standard image. Real-time images for image matching.

The implementation of the present invention can obtain the following beneficial effects: through the similarity matching between the real-time image and the library image, the present invention can automatically feed back the correctness of the user's current scanning operation, and judge whether the obtained image is a standard image of a certain tissue or organ; Further based on the above matching results, the present invention can automatically call out the graphic information corresponding to the clinical standard section of the image when the standard image is obtained, overcoming the cumbersome operation that requires the user to manually select the scanning section in the prior art; or it can be used in the future When a standard image can be obtained, it can provide users with instant guidance on how to adjust the position of the probe, which greatly improves the user's learning efficiency and enables the user to quickly improve the level of image scanning.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work. In the attached picture:

Fig. 1 is an exemplary flowchart of the ultrasonic scanning method of the present invention;

Fig. 2 is an exemplary flow chart of the ultrasonic scanning method in the first embodiment of the present invention;

Fig. 3 is an exemplary flow chart of the ultrasonic scanning method in the second embodiment of the present invention;

Fig. 4 is the schematic diagram of the position of feature point and its corresponding matching point position in real-time image on library image;

Fig. 5 is an exemplary flow chart of the ultrasonic scanning method in the third embodiment of the present invention;

Fig. 6 is an exemplary block diagram of the ultrasonic scanning system of the present invention;

Fig. 7a is an exemplary block diagram of an ultrasonic scanning system in a specific embodiment of the present invention;

Fig. 7b is another exemplary block diagram of an ultrasound scanning system in a specific embodiment of the present invention.

Detailed ways

The present invention will be described in detail below through specific embodiments. It should be understood that although the word "image" is generally used hereinafter, that is, the specific type of image is not described, but since the present invention belongs to the field of ultrasound imaging technology, "image" especially refers to ultrasound images.

The present invention proposes a system scheme for intelligently assisting beginners of ultrasonic equipment to rapidly improve the ultrasonic scanning technology and knowledge level, and especially proposes an ultrasonic-assisted scanning method and system. Fig. 1 is an exemplary flow chart of the ultrasonic scanning method of the present invention, the basic steps of which are: the delayed focused pulse is sent to the probe through the transmitting circuit, the probe transmits ultrasonic waves to the body under test, and receives the ultrasonic wave from the subject after a certain delay. Measure the ultrasonic waves reflected from the body. The echo signal enters the beamformer, completes the focus delay, weighting and channel summation, and obtains the real-time ultrasonic image (hereinafter referred to as the real-time image) through signal processing, and then performs image processing on the currently acquired real-time image and the pre-established library information Matching, outputting the image help information required by the real-time image according to the matching result, and displaying the information and the real-time image on the monitor.

The "image matching" described above especially refers to the similarity matching between real-time images and gallery information, and this process may particularly include the following two steps: A, building a gallery and B, similarity matching calculation.

This step A is an offline step, that is, the image library has been established before scanning, and only the corresponding library images need to be retrieved from the image library during the actual scanning process. The image library involved in the present invention includes a detailed human body section ultrasonic library. On a normal human body, a probe placement position is determined at fixed micro-distance intervals for each organ or tissue in the transverse, longitudinal, and oblique directions. At each probe position, with the probe vertical to the body surface as the reference, it swings to both sides at a fixed small angle, and stores an ultrasound picture every time it swings as a library image in the image library. The above-mentioned library images should especially include standard images that can reflect clinical standard slices. Each library image in the library contains information on the direction of the cut plane and the angle of the probe swing. Among them, the standard images (especially standard sonographic images) used in the clinic and a series of library images corresponding to the probe positions of the standard images need to be specially marked, and the probe position corresponding to the clinical standard section and the human body contour model of the current probe position are recorded. .

This step B is performed based on the unique features of each library image in the image library, for example, what area of a certain image has what shape of hyperecho, etc. Accordingly, the present invention performs correlation calculation based on the pattern matching algorithm, based on image features of library images and real-time images, and the image with the highest correlation is considered to belong to the corresponding matching image. The present invention can realize image matching by using a pattern matching method based on image blocks or feature points. The above step B will be expanded in detail below in specific embodiments.

The image matching result of the present invention may include: whether the matching is successful; whether the slice reflected by the successfully matched real-time image corresponds to the slice at the standard probe position; and whether the slice reflected by the real-time image corresponding to the standard probe position corresponds to the slice at the standard probe position The clinical standard section. According to the above image matching results, the "image help information" described above may include the following categories:

Unmatched: If the real-time image obtained by the user’s scan cannot match any library image, indicating that the current real-time image does not have a corresponding section in the library image, a prompt message will be given while displaying the reference phantom of the tested body. Indicates that the current scanning operation is incorrect, and prompts the user how to move the probe in the reference phantom. That is, the image help information at this time includes reference phantom information, matching failure information, and adjustment prompt information.

Successful matching but non-standard probe position: If the real-time slice reflected by the successfully matched real-time image does not correspond to the slice at the standard probe position (that is, corresponds to the slice at the non-standard probe position), the output reference phantom will be displayed at this time , a probe position mark (different from the mark of the standard probe position) appears at the real-time slice position, informing the user that there is no standard slice under the probe placement position, and prompting the user to adjust according to the standard probe position on the reference phantom. That is, the image help information at this time includes reference phantom information, real-time & standard probe position information and adjustment prompt information.

At the standard probe position but not the clinical standard view: if the real-time view reflected by the real-time image corresponding to the standard probe position does not correspond to the clinical standard view at the standard probe position (that is, conforms to the non-clinical standard view at the standard probe position), this When displaying the output reference phantom, the current probe position is highlighted (such as highlighting or special color marks, etc.), prompting the user how much the current probe should be deflected to the left or right, and giving feedback to the user about the current probe placement position Whether there is information on the clinical standard cut plane, so that the user can adjust the probe angle according to the feedback. That is, the image help information at this time includes reference phantom information, highlighted probe position information, adjustment prompt information, and clinical standard section judgment information.

At the standard probe position and clinical standard cut plane: the matching result indicates that the user’s scan operation is correct. At this time, not only the probe mark corresponding to the standard probe position is highlighted on the reference phantom, but also displayed (for example, in the help information area ) Graphical information corresponding to the clinical standard section, such as standard sonograms, anatomical diagrams, scanning technique diagrams, scanning techniques, etc. That is, the image help information at this time includes reference phantom information, highlighted probe position information, and help information corresponding to clinical standard slices.

The detailed implementation process of the ultrasound-assisted scanning of the present invention will be described below through specific embodiments.

Embodiment 1: Matching method based on image blocks (similarity calculation)

As shown in FIG. 2 , it discloses an ultrasound-assisted scanning method according to a first embodiment of the present invention. This embodiment realizes image matching based on a pattern matching method of image blocks. This embodiment can be divided into two stages: a pattern matching stage of determining matching points (step S12 ) and a searching stage of screening optimal matching library images (step S13 ). Among them, the matching points that match all the feature points one by one are determined on the real-time image through similarity calculation, and the library image with the highest similarity is screened out according to the matching degree of all feature points in each library image with the corresponding matching points. Here, the matching The degree especially refers to the similarity between the two.

Before determining the matching points, the method also includes a preparatory stage of establishing feature points of the library image. In order to improve the processing efficiency, the preparation stage is usually completed before the matching starts, and only the determined feature points need to be called during the real-time operation (step S11).

A number of feature points are determined for each library image in the image library, and the number of feature points can be set as required, for example, 20 feature points are selected for each image. The feature points can be established in various ways; for example, several points with relatively obvious features can be manually determined as feature points, such as edge contour points of various organs or intersection points of tissues in the image. Since the amount of data in the image library is usually relatively large, it is also possible to automatically calculate the feature points of each library image through a specific program. One of the methods for automatically calculating image feature points is:

Step 1: Divide the library image into several subregions.

Step 2: Establish a feature point P _ij in each sub-region, and P _ij represents the jth feature point of the i-th image. The method for confirming the feature points of the sub-area can be selected as required, for example, the point with the largest gradient or grayscale in the sub-area can be selected as the feature point of the sub-area.

The pattern matching stage of determining matching points (step S12) requires determining the matching points of each feature point of each library image on the real-time image, which includes the following sub-steps:

S121: Get each feature point of each library image in the image library, and determine the search range of each feature point on the current real-time image. The search range is an empirical parameter, which can be set as required. For example, according to the coordinates of the current feature point, the neighborhood of the corresponding point on the real-time scanning image is taken as the search range, for example, the size of the neighborhood may be 200*200.

S122: Take a certain feature point P _ij , and determine a neighborhood block with a size of W*H centered on the current feature point on the library image as a template.

S123: Within the determined search range, center on a plurality of pixels in the region, and determine a neighborhood block with the same size (W*H) as the template above, for subsequent similarity calculation. In order to ensure the matching accuracy, each pixel in the area can be selected as the center, and each feature point of each library image can be matched one by one. However, considering the amount of calculation, it is also possible to determine a neighborhood block at intervals of N points when searching for matching points, so as to improve the overall calculation speed. After searching for a better point, check one by one around the point.

S124: Calculate the similarity value between the template of the library image and the neighborhood block of the real-time image, and take the center of the most similar neighborhood block as the corresponding matching point of the template feature point in the real-time image. Specifically, first select a library image, then calculate the similarity value between the template of each feature point of the library image and each neighborhood block of the real-time image, and determine the template with the highest similarity value for each feature point template Neighborhood block, according to which the matching points corresponding to all the feature points in each library image are obtained. Reselect another library image and repeat the above steps until the matching points of all feature points of all library images are obtained. There are many methods for measuring the similarity between templates and neighborhood blocks, such as Euclidean distance, Cosine similarity, cumulative pixel difference, cumulative correlation coefficient, etc., and different measurement methods have different definitions of similarity. In other words, the meaning of "the highest similarity value" described above actually means that the template is most similar to the neighborhood block.

One of the methods to measure the similarity between the template and the neighborhood blocks is to calculate the sum of the absolute values of the pixel differences between the template and the neighborhood blocks. Right now

$\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; =</span>\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}<span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; |</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

In the above formula, E1 represents the sum of the absolute value of the pixel difference between the template and the neighborhood block, Ω is the neighborhood, _IL and I _R represent the gray value of the pixel in the template and the neighborhood block, respectively. It can be seen from formula (1) that the smaller the similarity value, the better the similarity.

Another way to measure the similarity between the template and the neighborhood blocks is to calculate the sum of the correlation coefficients between the template and the pixels of the neighborhood blocks. Right now

$\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; =</span>\frac{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}}{\sqrt{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}\sqrt{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

In the above formula, E2 represents the sum of the correlation coefficients between the template and the pixels of the neighborhood block, Ω is the neighborhood, _IL and I _R represent the gray value of the pixels of the template and the neighborhood block, respectively. From formula (1), it can be seen that the larger the similarity value, the better the similarity.

When using the methods of formulas (1) and (2) to calculate the similarity value, the corresponding matching point most similar to a certain feature point is the point with the smallest E1 value or the largest E2 value. In addition, it should be understood that not every feature point has a corresponding matching point. According to the characteristics of the pixel difference method and the correlation coefficient method, when there is no matching point for a certain feature point, a fixed similarity value is assigned to the feature point, a larger value is assigned under the pixel difference method, and a smaller value.

S125: Using the similarity value most similar to a certain feature point as a criterion for finding a matching point. This step is a preferred step. An empirical parameter E_Thre (also called the first matching standard value) can be further defined to judge whether the calculated center of the most similar neighborhood block is indeed a matching point where feature points exist in the real-time image. For example, in the case of formula (1) as the measurement formula, if the similarity value of a certain point is greater than E_Thre, it means that the feature point does not have a corresponding matching point in the real-time image. In the case of formula (2) as the measurement formula , if the similarity value of the corresponding point is less than E_Thre, it means that the feature point does not have a corresponding matching point in the real-time image.

The search stage of screening the optimal matching library image (step S13) requires to filter out a library image in the image library that is most similar to the real-time image. In this embodiment 1, all feature points of a single library image and their positions on the real-time image The similarity of matching points realizes the above screening. It is based on the theoretical basis that if the real-time image and a library image are not in the same section, then the library image will have many feature points that do not have matching points in the real-time image; if they are the same section, the library image Most of the feature points have matching points in the real-time image. Therefore, a method of searching for the image most similar to the current real-time image in the library image is to calculate the sum of the similarity values between each feature point in each library image and the corresponding matching point in the real-time image (step S131), namely

E _i =ΣE _ij (3)

Where E _i is the total similarity value of the i-th library image, and E _ij is the similarity value of the j-th feature point in the i-th library image, which can be calculated by the method shown in formula (1) or (2). As mentioned above, if there is no matching point for the jth feature point on the real-time image, a fixed constant can be used as its similarity value (ie, the fixed similarity value above) to compensate the feature point for which there is no matching point. For example, for formula (1), a larger value can be set as the similarity value of the feature point, and for formula (2), a smaller value can be set to replace the similarity value of the feature point, for example, set to 0. After the E _i of all library images are calculated, the library image corresponding to the optimal similarity value is selected as the library image with the best similarity to the current real-time image.

Step S132: Another empirical parameter threshold (that is, the first slice matching threshold) can be set to determine whether the current real-time image and the searched library image with the best similarity are the same slice. The empirical parameter can be based on the similarity measure used The formula is OK. For example, when using formula (1), if the optimal similarity value is greater than the set slice matching threshold, it is considered that the current real-time image does not have an image with the same slice in the image library; when using formula (2), if the optimal similarity If the degree value is less than the set slice matching threshold, it is considered that the current real-time image does not have an image with the same slice in the image database.

In Embodiment 1 of the present invention, through the similarity calculation in steps S12 and S13, the most similar library images can be screened out in the image library. However, this method relies too much on the calculation results of the similarity. Due to the noise of the ultrasound image, it may affect the selection of the most similar library image in some cases.

Embodiment 2: Matching method based on image blocks (topological properties)

As shown in Fig. 3, it reveals the ultrasound-assisted scanning method of the second embodiment of the present invention, this embodiment also implements image matching based on the pattern matching method of image blocks, and is also divided into two stages: determine the pattern of matching points The matching stage (step S22) and the search stage of screening the best matching library images (step S23). The specific process of determining the matching point is the same as that in Embodiment 1, and will not be repeated here. In this embodiment, when screening the optimal matching library images, the topological properties of the feature points are used for screening instead of the similarity calculation results. For the feature points of each library image, its relative position relationship on the plane is fixed. If the current real-time image and the library image are in the same section, although there is a certain translation, rotation and scaling between the two, these feature points Corresponding points in the real-time image should approximately maintain these relative positional relationships (as shown in Figure 4). Step S23 includes the following sub-steps:

S231: Calculate the angle θ _ij between each feature point of each library image and its adjacent feature points;

S232: When a certain feature point and its adjacent feature points have corresponding matching points, calculate the included angle between the matching point of the feature point on the real-time image and the matching point of its adjacent feature points Call a preset fixed angle when the feature point lacks the corresponding matching point (for example, set to 360°) as the included angle between the matching point of this feature point on the real-time image and the matching point of its adjacent feature points.

S233: Calculate the sum of the differences between the included angles of all the feature points of each library image and the corresponding matching point angles, and determine the library image corresponding to the smallest included angle difference accordingly. Right now

S234: Compare the determined minimum angle difference with a second slice matching threshold, and if the minimum angle difference is smaller than the second slice matching threshold, use the corresponding library image as an optimal matching library image for the real-time image. This step is also a preferred step for improving the accuracy of matching judgment.

Alternative Implementation: Matching Point Confirmation Process with Reduced Calculation

When determining the matching points in the above-mentioned embodiments 1 and 2, if the size of the template is large, a large amount of calculation will result. In another alternative embodiment, the present invention determines the matching points of the feature points of each library image based on the following steps, and the specific method described in any one of embodiments 1 and 2 can be used when screening the optimal matching library image. First, the search range corresponding to each feature point is still determined on the real-time image, and the specific process is the same as in the above two embodiments.

Then determine a template of a specific size centered on each feature point on the library image. After the template image A is taken out, A is an m*n matrix (m, n is the size of the template), and the template of A'A is calculated. Eigenvalue λ=[λ ₁ ,...,λ _n ] (A' is the transpose of matrix A).

Also within the determined search range, take multiple pixels in the area as the center and take out the image B corresponding to the neighborhood block of the same size. Here, you can also choose each pixel as the center, or choose a pixel point every N pixels as the neighborhood block center. Then calculate the neighborhood block eigenvalue ρ=[ρ ₁ , . . . , ρ _n ] of B′B (B′ is the transpose of matrix B).

Then use the above formula (1) or (2) to measure the similarity between the template feature value λ and the neighborhood block feature value ρ, and use the similarity calculation result as the similarity between the template of the library image and the neighborhood block of the real-time image value, and the point with the best similarity can be selected as the matching point of a specific feature point. For example, when using formula (1) to calculate, select the point with the smallest similarity value. Also preferably, a matching standard value can be preset; after obtaining the optimal similarity value, it is judged whether the value conforms to the range defined by the matching standard value, thereby further increasing the accuracy of the matching operation.

This embodiment simplifies the m*n template to be represented by n eigenvalues, which can basically express the main characteristics of the template image, and can greatly simplify the calculation when using formula (1) or formula (2) for similarity calculation quantity.

Image block-based matching methods only calculate feature points on library images, while searching for matching points of feature points in real-time images through similarity matching. Due to the uncertainty of the target position in the real-time image, the search range is generally relatively large, resulting in a relatively large amount of calculation for this method. Another method for correlation matching of real-time images and library images is an image matching method based on feature points. See embodiment 3 for specific description.

Embodiment 3: Matching method based on feature points

As shown in FIG. 5 , it discloses an ultrasound-assisted scanning method according to a third embodiment of the present invention. This embodiment realizes image matching based on a pattern matching method of feature points. This embodiment can be divided into three stages: determining the feature points of the library image and the real-time image (step S31 ), establishing the corresponding relationship of feature points (step S32 ), and searching for the optimal matching library image (step S33 ). Among them, the corresponding relationship between the feature points of the real-time image and the library image is established by similarity calculation, according to the number of corresponding feature points of each library image, or according to the similarity of the feature points that have a corresponding relationship between each library image and the real-time image The sum of degree values is used to filter out the best matching library image. The "corresponding feature point" here refers to a point in the library image that has a corresponding relationship with the feature point of the real-time image.

Step S31: Obtain feature points of each library image and real-time image of the plurality of library images respectively. The specific implementation method includes calculating the feature points at the same time: using the same method to calculate the feature points for the real-time image and the library image. Commonly used feature points include corner points, inflection points, edge points, etc. Commonly used calculation methods include selecting the point with the largest gradient in a sub-region as a feature point; or calculating the local autocorrelation in four directions for each point in the image, and then selecting Take the minimum value from the correlation result as the feature value of the point, or further judge whether the value is greater than the empirical threshold, and only consider the point as a feature point when it exceeds the empirical threshold. The specific implementation method also includes calculating the feature points of the library image first, and then calculating the feature points of the real-time image in real time by using the same calculation method. The feature points of the library image can be calculated and stored first, thereby reducing the amount of calculation during the scanning process.

Step S32: A large number of feature points are obtained from the real-time image and each library image, but not all feature points have a corresponding relationship, and a large part of the feature points of the real-time image may not have corresponding points in the library image. The purpose of this step is to establish the corresponding relationship between the feature points of the real-time image and the feature points of each library image through similarity calculation. specifically:

Step S321: Firstly, on the real-time image and each library image, a neighborhood block of the same size is determined centering on each feature point.

Step S322: Calculate the similarity value of two neighborhood blocks of the library image and the real-time image, and use the feature point of the library image with the best similarity value as the corresponding feature point of the real-time image. Specifically, first select a feature point on the real-time image, then select a library image, and calculate the similarity between the neighborhood block of each feature point in the library image and the neighborhood block of the feature point in the real-time image value, take the feature point with the best similarity value on the library image as the corresponding feature point of the feature point in the real-time image; reselect another library image and repeat the above steps until the corresponding feature point of the feature point on all library images is obtained . Then another feature point of the real-time image is reselected, and its corresponding feature points on all library images are obtained according to the above process. Here, the feature points on the library image and the real-time image that have a corresponding relationship are preferably referred to as feature point pairs.

The calculation of the similarity value can specifically adopt the following two methods. One is to calculate the similarity value between the library image and the real-time image by calculating the sum of the absolute values of the pixel differences of the neighborhood blocks:

$\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}<span\; class="notranslate">\; |</span>\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; |</span>$

Where E3 represents the sum of the absolute value of the pixel difference between the neighborhood blocks of the library image and the real-time image, and Il and Ir represent the gray value of the pixels in the neighborhood blocks of the library image and the real-time image respectively.

The other is to calculate the similarity value of the two by calculating the sum of the correlation coefficients of the pixels of the neighborhood blocks of the library image and the real-time image:

$\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; =</span>\frac{\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; IlIr</span>}}{\sqrt{\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; Il</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}\sqrt{\underset{\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; Ir</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}$

Where E4 represents the sum of the correlation coefficients of the pixels in the neighborhood blocks of the library image and the real-time image, and Il and Ir represent the gray values of the pixels in the neighborhood blocks of the library image and the real-time image respectively.

S323: This step is a preferred step. The optimal similarity value obtained in step S322 is compared with a predetermined second matching standard value. If it exceeds the range limited by the matching standard value, it is considered that there is actually no corresponding feature point matching the feature point of the real-time image in the library image. Through step S32, it can be determined whether each feature point of the real-time image has a corresponding feature point in each image, especially the pair of corresponding feature points and their similarity can be determined.

Step S33: According to the number of corresponding feature points of each library image, or according to the sum of the similarity values of feature point pairs that have a corresponding relationship between each library image and the real-time image, filter out the optimal matching library image. An optimal matching library image screening method is to select a library image with the largest number of corresponding feature points as the matching image. At the same time, an empirical threshold can be set. If the number of feature points matched with the real-time image is less than the threshold, the matching is considered unsuccessful, and the current real-time image does not have a corresponding section in the library image. Another optimal matching library image screening method is to select the library image with the optimal sum of the similarity values of the feature point pairs between the current real-time image and a single library image as the matching image. Judgment of successful match. As mentioned above, when there is no corresponding feature point for a feature point of the real-time image, a fixed similarity value is given.

The above-mentioned embodiments 1-3 all use the entire image library as the search object. Generally, in order to improve the effectiveness of auxiliary scanning, the library images in the image library have a large number, including ultrasound images of various specific tissues or organs under various orientations and imaging angles. In view of the comprehensive consideration of scanning accuracy and scanning speed, the ultrasonic-assisted scanning method of the present invention can receive user input before scanning, determine the name of the organ & tissue of the body to be scanned, and then call the library image When only multiple library images satisfying the name of the organ are used, the calculation range of image matching is significantly reduced without affecting the accuracy of image matching calculation.

Referring to Fig. 6, the present invention also provides an ultrasound-assisted scanning system, which can instantly feedback the correctness of the user's operation through real-time image matching, and guide the user to improve scanning skills by providing detailed graphic information. Specifically, the ultrasound-assisted scanning system includes an imaging subsystem, a scanning auxiliary subsystem and a display subsystem. The imaging subsystem includes a probe 11 and an imaging module 12; wherein the probe 11 is in direct contact with the body under test, and is used to transmit ultrasonic waves to the body under test and receive echo signals reflected by the body under test at a certain probe position, and the imaging module 12 is Signal processing is performed on the echo signal to obtain a real-time image at the current probe position. The scanning auxiliary subsystem includes an image library 13 and an image matching module 14; the image library 13 is used to store a plurality of library images established in advance, and the image matching module 14 is used to combine the real-time images generated by the imaging module 12 with the images in the image library 13 Similarity matching is performed on the library images, so that the correctness of the ultrasound scanning operation at the current probe position can be judged or fed back in real time. The display subsystem includes a display 15 and an output configuration module 16; the output configuration module 16 communicates with the image matching module 14 and the library image 13, and after the image matching module 14 obtains a determined matching result, it enables the display 15 to output various matching results. Corresponding graphic information, such as but not limited to the current real-time image, graphic explanations for adjusting the probe position, graphic information corresponding to standard images, etc.

Referring further to FIGS. 7 a and 7 b , the image matching module 14 of the ultrasound-assisted scanning system includes a library image feature point acquisition unit 141 , a real-time image matching point determination unit 142 and an optimal matching library image screening unit 143 . The library image feature point acquiring unit 141 is used to call the predetermined feature point of each library image of a plurality of library images. It is described here that the feature points of the library image are determined in advance in order to improve the calculation speed of the actual scan, but it does not exclude that the present invention can be realized by determining the feature points of the library image in real time. The real-time image matching point determination unit 142 is configured to determine a matching point corresponding to each feature point of each library image in the real-time image through similarity calculation. The invention adopts a pattern matching method based on image blocks or feature points to realize similarity matching calculation. The optimal matching library image screening unit 143 screens out the library image with the highest similarity among multiple library images according to the matching degree of all feature points in a single library image and the corresponding matching points, as the optimal matching library image of the current real-time image .

In one embodiment, the real-time image matching point determination unit 142 first determines the search range corresponding to each feature point on the real-time image according to each feature point determined by the library image feature point acquisition unit 141, for example, taking a neighborhood of the corresponding coordinate point for the search range. Then, a template of a specific size is determined centering on each feature point on the library image, and a neighborhood block with the same size as the template is determined centering on multiple pixels within the search range. After determining the template of each feature point and a plurality of neighborhood blocks corresponding to it, the real-time image matching point determination unit 142 then calculates the similarity values of each template of the library image and all neighborhood blocks in the real-time image, which can be based on the above The pixel difference or correlation coefficient method described in this paper is carried out, and the center of the neighborhood block with the best similarity value with a certain template is used as the matching point corresponding to the feature point.

In one embodiment, the real-time image matching point determination unit 142 first determines the search range corresponding to each feature point on the real-time image according to each feature point determined by the library image feature point acquisition unit 141, for example, taking a neighborhood of the corresponding coordinate point for the search range. Then, a template of a specific size is determined centering on each feature point on the library image, and a neighborhood block with the same size as the template is determined centering on multiple pixels within the search range. After taking out the corresponding template image A and the neighborhood block image B (both A and B are m*n matrices), the real-time image matching point determination unit 142 calculates the template eigenvalues of A'A respectively λ=[λ ₁ ,...,λ _n ] (A' is the transpose of matrix A) and the eigenvalues of the neighborhood blocks of B'B ρ=[ρ ₁ ,…,ρ _n ] (B' is the transpose of matrix B), and according to the above-described The method of pixel difference or correlation coefficient calculates the similarity between the template feature value λ and the neighborhood block feature value ρ. The similarity calculation result can reflect the similarity value between each template of the library image and the neighborhood block of the real-time image, and the real-time image matching point determination unit 142 uses the center of the neighborhood block with the best similarity value with a certain template as the The matching point corresponding to the feature point.

In an embodiment, the real-time image matching point determining unit 142 also presets matching standard values. After obtaining the neighborhood block most similar to a certain template, compare the similarity value of the two with the matching standard value. Only when the optimal similarity value satisfies the range limited by the matching standard value, it is considered that the current neighborhood block indeed corresponds to the template, and its center is indeed the matching point of the feature point of the template. Different similarity calculation methods have different metrics. For example, when using the pixel difference method, the optimal similarity value should not exceed the matching standard value; on the contrary, when using the correlation coefficient method, the optimal similarity value should not be less than the matching standard value. .

In one embodiment, the optimal matching library image screening unit 143 calculates the sum of the similarity values between all the feature points of each library image and the corresponding matching points, so as to determine the total similarity value between the library image and the real-time image. It should be noted that not every feature point has a matching point in the real-time image, so when the feature point lacks a corresponding matching point, a fixed similarity value is assigned to the feature point. The one with the best total similarity value among all the library images is the best matching library image of the current real-time image.

In one embodiment, the optimal matching library image screening unit 143 completes the screening according to the relative positional relationship between each feature point. First, the optimal matching library image screening unit 143 calculates the angle between each feature point of each library image and its adjacent feature points, which is recorded as the feature point angle; then calculates the matching point of the feature point on the real-time image and its corresponding angle The angle between the matching points adjacent to the feature point is recorded as the matching point angle. Similarly, when there is no matching point for a certain feature point, a preset fixed angle is called as the included angle between the matching point of the feature point on the real-time image and the matching points of its adjacent feature points. The optimal matching library image screening unit 143 then calculates the sum of the differences between the included angles of all feature points of each library image and the corresponding matching point angles, and accordingly determines the library image corresponding to the smallest angle difference, and the library image is The best matching library image for the current live image.

In an embodiment, the optimal matching library image screening unit 143 also presets a slice matching threshold. After obtaining the minimum angle difference or the optimal similarity value, it is compared with the slice matching threshold. Only when the minimum angle difference or the optimal similarity value satisfies the range limited by the slice matching threshold, the corresponding library image is selected as the optimal matching library image.

In one embodiment, the image matching module 14 of the ultrasound-assisted scanning system includes a feature point acquisition unit 141', a feature point correspondence establishment unit 142', and an optimal matching library image screening unit 143'. The feature point acquisition unit 141' acquires the feature points of each library image and real-time image respectively, and pays special attention to using the same method to determine the feature points of both. The feature point correspondence establishment unit 142' establishes the correspondence between the feature points of the real-time image and the feature points of each library image through similarity calculation, thereby determining whether each feature point of the real-time image has a correspondence in each library image feature points, and record two feature points with corresponding relationship as a feature point pair. The optimal matching library image screening unit 143' selects the optimal matching library image according to the number of corresponding feature points of each library image, or according to the sum of the similarity values of feature point pairs that have a corresponding relationship between each library image and the real-time image. Match library images.

In one embodiment, the feature point correspondence establishment unit 142' first determines neighborhood blocks of the same size with each feature point as the center on the real-time image and each library image, and then calculates each neighborhood block of the real-time image The similarity value with all neighborhood blocks of each library image is obtained to obtain the neighborhood block most similar to a certain neighborhood block of the real-time image in each library image. The centers of the two most similar neighborhood blocks in the real-time image and the library image are feature point pairs, and the feature points on the library image are especially called corresponding feature points.

In one embodiment, the feature point correspondence establishment unit 142' compares the calculated optimal similarity value with a predetermined matching standard value. If the optimal similarity value satisfies the range defined by the matching standard value, the center of the neighborhood block corresponding to the library image is taken as the corresponding feature point of the feature point of the real-time image on the library image.

In one embodiment, the output configuration module 16 configures the display 15 to output different graphic and text help information according to the specific matching result of the image matching module 14 . The image library 13 pre-stores corresponding data (such as images, probe marks, text guidance information, etc.) required to assist users in efficient scanning. The output configuration module 16 retrieves corresponding data information from the image library 13 according to the received matching result, and displays it on the display 15 in real time, so as to form a good interaction with the user. The specific matching results and graphic help information have been expanded in detail above, and will not be repeated here.

Those skilled in the art can understand that although the ultrasound-assisted scanning system described above includes an image library, an image matching module and an output configuration module, the above-mentioned components may not be integrated in the ultrasonic diagnostic instrument, but as a The plug-in is only connected to the instrument when the user needs the instrument to provide auxiliary scanning to form the described ultrasound-assisted scanning system.

The above detailed development of the ultrasound-assisted scanning method and system reveals the significant advantages of the present invention compared to the existing teaching system: 1. The real-time feedback mechanism enables the user to know whether the current scanning operation meets the clinical medical requirements; 2. Standard images The automatic call-out mechanism can save the user from manually selecting the required standard image, and the overall user-friendliness is stronger; 3. The probe adjustment prompt mechanism can enable users, especially beginners, to understand how to correctly adjust the probe position and improve Learning efficiency.

Those skilled in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, Random access memory, disk or CD, etc.

The above content is a further detailed description of the present invention in conjunction with specific embodiments, and it cannot be assumed that the specific implementation of the present invention is limited to these descriptions. Those of ordinary skill in the technical field to which the present invention belongs can also make some simple deduction or replacement without departing from the concept of the present invention.

Claims (22)

1. An ultrasound-assisted scanning method, comprising transmitting ultrasonic waves to the body under test at a probe position, receiving the echo signal reflected by the body under test and generating a current real-time image accordingly; It is characterized in that it also includes: calling a plurality of library images from a pre-established image library, the plurality of library images including standard images reflecting clinical standard slices of the body under test; performing similarity matching on the generated real-time image to the plurality of library images; and Output the matching result of the real-time image and the plurality of library images, and call the graphic information corresponding to the standard image according to the matching result or assist in explaining how to adjust the position of the probe to obtain a real-time image matching the standard image . 2 . The ultrasound-assisted scanning method according to claim 1 , wherein a pattern matching method based on image blocks or feature points is used to perform similarity matching on the real-time image and the plurality of library images. 3 . 3. The ultrasound-assisted scanning method according to claim 2, wherein the similarity matching of the real-time image and the plurality of library images using a pattern matching method based on image blocks comprises: calling the predetermined feature points of each library image of the plurality of library images; determining matching points corresponding to each feature point of each library image in the real-time image through similarity calculation; and The library image with the highest similarity is selected from the plurality of library images according to the degree of matching between all the feature points of each library image and the corresponding matching points, and used as the optimal matching library image of the current real-time image. 4. The ultrasound-assisted scanning method according to claim 3, wherein determining the matching point corresponding to each feature point of each library image by similarity calculation comprises: determining a search range corresponding to each feature point on the real-time image; Determining a template of a specific size centered on each feature point on the library image; Determining a plurality of neighborhood blocks with the same size as the template within the search range and centering on a plurality of pixels therein; Calculate the similarity value between the template of the library image and the neighborhood block of the real-time image, and use the center of the neighborhood block with the best similarity value relative to a template as the feature point corresponding to the template matching point. 5. The ultrasound-assisted scanning method according to claim 3, wherein determining the matching point corresponding to each feature point of each library image by similarity calculation comprises: determining a search range corresponding to each feature point on the real-time image; Determining a template of a specific size centered on each feature point on the library image, and calculating template feature values of the template and its transposed image; Determining a plurality of neighborhood blocks with the same size as the template within the search range centered on a plurality of pixels therein, and calculating the neighborhood block feature values of the neighborhood blocks and their transposed images; Calculate the similarity between the template feature value and the neighborhood block feature value, and use the similarity calculation result as the similarity value between the template of the library image and the neighborhood block of the real-time image, and compare it with a certain For the template, the center of the neighborhood block with the best similarity value is used as the matching point corresponding to the feature point of the template. 6. The ultrasound-assisted scanning method according to claim 4 or 5, wherein, after calculating the template of the library image and the similarity value of the neighborhood blocks of the real-time image, the method further comprises : comparing the optimal similarity value with a predetermined first matching standard value; If the optimal similarity value satisfies the range defined by the first matching standard value, the center of its corresponding neighborhood block is taken as the matching point corresponding to the feature point. 7. The ultrasound-assisted scanning method according to claim 4 or 5, wherein calculating the template of the library image and the similarity value of the neighborhood block of the real-time image comprises: Calculate the similarity value between the template and the neighborhood block by calculating the sum of the absolute values of the pixel differences: $\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; =</span>\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}<span\; class="notranslate">\; |</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; |</span>$ Wherein E represents the sum of the absolute value of the pixel difference between the template and the neighborhood block, _IL and I _R represent the template and the gray value of the pixel in the neighborhood block respectively; or include: Calculate the similarity value of the two by calculating the sum of the correlation coefficients between the template and the pixels of the neighborhood block: $\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; =</span>\frac{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}}{\sqrt{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; L</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}\sqrt{\underset{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{{\mathrm{<span\; class="notranslate">\; I</span>}}_{\mathrm{<span\; class="notranslate">\; R</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}$ Where E2 represents the sum of the correlation coefficients between the template and the pixels of the neighborhood block, _IL and I _R represent the gray values of the template and the pixels of the neighborhood block, respectively. 8. The ultrasound-assisted scanning method according to claim 4 or 5, wherein determining the neighborhood blocks of the real-time image comprises: determining the neighborhood block within the search range with each pixel within it as the center; or A center is selected at intervals of N pixels within the search range to determine the neighborhood block. 9. The ultrasound-assisted scanning method according to claim 3, wherein the screening of the optimal matching library images of the real-time images comprises: calculating the difference between all feature points of each library image and the similarity values of the corresponding matching points and, the library image with the optimal sum of similarity values is used as the optimal matching library image of the real-time image: E _i =ΣE _ij Wherein, E _i is the total similarity value between the i-th library image and the real-time image; E _ij is the similarity value between the j-th feature point and the corresponding matching point in the i-th image when there is a corresponding matching point in the feature point , when the feature point lacks a corresponding matching point, E _ij is a preset fixed similarity value of the jth feature point. 10. The ultrasound-assisted scanning method according to claim 3, wherein the screening of the optimal matching library image of the real-time image comprises: Calculate the angle between each feature point of each library image and its adjacent feature points; When the feature point has a corresponding matching point, calculate the angle between the matching point of the feature point on the real-time image and the matching point of the adjacent feature point, and call a preset when the feature point lacks a corresponding matching point. The fixed angle is used as the included angle between the matching point of the feature point on the real-time image and the matching point of its adjacent feature point; Calculate the sum of the difference between all the feature point angles of each library image and the corresponding matching point angles, and determine the library image corresponding to the minimum angle difference accordingly; Comparing the minimum angle difference with a second slice matching threshold, if the minimum angle difference is smaller than the second slice matching threshold, using the corresponding library image as the optimal matching library of the real-time image image. 11. The ultrasound-assisted scanning method according to claim 2, wherein the similarity matching of the real-time image and the plurality of library images using a pattern matching method based on feature points comprises: Obtaining feature points of each library image of the plurality of library images and the real-time image respectively; Establishing the correspondence between the feature points of the real-time image and the feature points of each library image through similarity calculation, so as to determine whether each feature point of the real-time image has a corresponding feature point in each library image; The optimal matching library image is screened out according to the number of corresponding feature points of each library image, or according to the sum of similarity values of feature points having a corresponding relationship between each library image and the real-time image. 12. The ultrasound-assisted scanning method according to claim 11, wherein establishing the correspondence between the feature points of the real-time image and the feature points of each library image by similarity calculation comprises: Determining neighborhood blocks of the same size with each feature point as the center on the real-time image and each library image; Calculating the similarity values between a certain neighborhood block of the real-time image and all neighborhood blocks of a certain library image, so as to determine the neighborhood block with the highest similarity to the neighborhood block of the real-time image on the library image ; comparing the optimal similarity value with a predetermined second matching standard value; If the optimal similarity value satisfies the range defined by the second matching standard value, then use the center of the neighborhood block corresponding to the library image as the corresponding feature point of the real-time image on the library image Feature points. 13. The ultrasound-assisted scanning method according to claim 12, wherein calculating the similarity value between a certain neighborhood block of the real-time image and all neighborhood blocks of a certain library image comprises: Calculate the similarity value of both by calculating the sum of the absolute values of the pixel differences of the neighborhood blocks of the library image and the real-time image: $\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}<span\; class="notranslate">\; |</span>\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; |</span>$ Wherein E3 represents the sum of the absolute values of the pixel differences of the neighborhood blocks of the library image and the real-time image, and Il and Ir represent the grayscale values of pixels in the neighborhood blocks of the library image and the real-time image respectively ; or include: Calculate the similarity value of the two by calculating the sum of the correlation coefficients of the pixels of the neighborhood blocks of the library image and the real-time image: $\mathrm{<span\; class="notranslate">\; E.</span>}\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; =</span>\frac{\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}\mathrm{<span\; class="notranslate">\; IlIr</span>}}{\sqrt{\underset{\mathrm{<span\; class="notranslate">\; Il</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; Il</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}\sqrt{\underset{\mathrm{<span\; class="notranslate">\; Ir</span>}<span\; class="notranslate">\; \&Element;</span>\mathrm{<span\; class="notranslate">\; \&Omega;</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; Ir</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}}$ Where E4 represents the sum of the correlation coefficients of the pixels in the neighborhood blocks of the library image and the real-time image, and Il and Ir represent the gray values of the pixels in the neighborhood blocks of the library image and the real-time image respectively. 14. The ultrasound-assisted scanning method according to claim 1, wherein the matching result comprises: Whether the real-time image matches the library image successfully; Whether the section reflected by the successfully matched live image corresponds to the section at the standard probe position; and Whether the cut plane reflected by the real-time image corresponding to the standard probe position conforms to the clinical standard cut plane at the standard probe position. 15. The ultrasound-assisted scanning method according to claim 14, characterized in that the method further comprises: if the real-time image does not match the library image successfully, displaying and outputting the reference body of the body under test phantom, and prompt how to adjust the position of the probe on the reference phantom; If the slice reflected by the successfully matched real-time image corresponds to the slice at the non-standard probe position, then display and output the reference phantom of the body under test, mark the probe position corresponding to the real-time image on the reference phantom, and prompting how to adjust the position of the probe on the reference phantom; If the slice reflected by the real-time image corresponding to the standard probe position conforms to the non-clinical standard slice at the standard probe position, then display and output the reference phantom of the body under test, and highlight the standard probe position on the reference phantom , and prompt how to adjust the probe angle on the reference phantom to obtain the clinical standard cut plane; If the cut plane reflected by the real-time image corresponding to the standard probe position conforms to the clinical standard cut plane at the standard probe position, then display and output the reference phantom of the body under test, and highlight the standard probe position on the reference phantom, And display the graphic information corresponding to the clinical standard cut plane. 16. The ultrasound-assisted scanning method according to claim 1, wherein, before calling a plurality of library images, the method further comprises: input the name of the tissue or organ of the body to be scanned; and A plurality of library images corresponding to the names of the tissues or organs are retrieved from a pre-established image library. 17. An ultrasound-assisted scanning system, comprising: The probe is used to transmit ultrasonic waves to the body under test at a probe position and receive echo signals reflected by the body under test; an imaging module, configured to process the echo signal and generate a current real-time image accordingly; a display for displaying said real-time image generated by the output; It is characterized in that the ultrasound-assisted scanning system also includes: The image library is used to store a plurality of library images established in advance, and the plurality of library images include standard images reflecting clinical standard sections of the body under test; An image matching module, communicatively connected with the imaging module and the image library, for matching the generated real-time images with the plurality of library images for similarity matching; and The output configuration module is used to enable the display to output the matching results of the real-time image and the multiple library images, and call the graphic information corresponding to the standard image according to the matching results or assist in explaining how to adjust the position of the probe to A live image matching the standard image is obtained. 18. The ultrasound-assisted scanning system according to claim 17, wherein the image matching module comprises: A library image feature point acquisition unit, configured to call the predetermined feature points of each library image of the plurality of library images; A real-time image matching point determination unit, configured to determine a matching point corresponding to each feature point of each library image in the real-time image through similarity calculation; and The optimal matching library image screening unit is used to filter out the library image with the highest similarity among multiple library images according to the matching degree of all the feature points of each library image and the corresponding matching points, as the most recent real-time image. Excellent match library images. 19. The ultrasound-assisted scanning system according to claim 17, characterized in that, The real-time image matching point determination unit is used for: determining a search range corresponding to each feature point on the real-time image; Determining a template of a specific size centered on each feature point on the library image; Determining a plurality of neighborhood blocks with the same size as the template within the search range and centering on a plurality of pixels therein; Calculate the similarity value of each template of the library image and all neighborhood blocks in the real-time image, and use the center of the neighborhood block with the best similarity value relative to a certain template of the library image as the Matching points corresponding to the feature points of the template; or The real-time image matching point determination unit is used for: determining a search range corresponding to each feature point on the real-time image; Determining a template of a specific size centered on each feature point on the library image, and calculating template feature values of the template and its transposed image; Determining a plurality of neighborhood blocks with the same size as the template within the search range centered on a plurality of pixels therein, and calculating the neighborhood block feature values of the neighborhood blocks and their transposed images; Calculate the similarity between the template feature value and the neighborhood block feature value, use the similarity calculation result as the similarity value between the template of the library image and the neighborhood block of the real-time image, and compare the For a certain template of the library image, the center of the neighborhood block with the best similarity value is used as the matching point corresponding to the feature point of the template. 20. The ultrasound-assisted scanning system according to claim 18, characterized in that, The optimal matching library image screening unit is used for: Calculate the sum of the similarity values of all feature points and corresponding matching points of each library image, and use the optimal library image of the sum of similarity values as the optimal matching library image of the real-time image; or The optimal matching library image screening unit is used for: Calculate the angle between each feature point of each library image and its adjacent feature points; When the feature point has a corresponding matching point, calculate the angle between the matching point of the feature point on the real-time image and the matching point of the adjacent feature point, and call a preset when the feature point lacks a corresponding matching point. The fixed angle is used as the included angle between the matching point of the feature point on the real-time image and the matching point of its adjacent feature point; Calculate the sum of the difference between all the feature point angles of each library image and the corresponding matching point angles, and determine the library image corresponding to the minimum angle difference accordingly; Comparing the minimum angle difference with a second slice matching threshold, if the minimum angle difference is smaller than the second slice matching threshold, using the corresponding library image as the optimal matching library of the real-time image image. 21. The ultrasound-assisted scanning system according to claim 17, wherein the image matching module comprises: A feature point acquiring unit, configured to acquire feature points of each library image of the plurality of library images and the real-time image respectively; The feature point correspondence establishment unit is used to establish the correspondence between the feature points of the real-time image and the feature points of each library image through similarity calculation, so as to determine that each feature point of the real-time image is in each library image. Whether there is a corresponding feature point in the image; and The optimal matching library image screening unit is used to filter out the optimal match according to the number of corresponding feature points of each library image, or according to the sum of the similarities between each library image and the corresponding feature points of the real-time image library images. 22. The ultrasound-assisted scanning system according to claim 21, wherein the feature point correspondence establishment unit is used for: Determining neighborhood blocks of the same size with each feature point as the center on the real-time image and each library image; Calculating the similarity values between a certain neighborhood block of the real-time image and all neighborhood blocks of each library image, so as to determine that the library image has an optimal similarity with respect to the neighborhood block of the real-time image Neighborhood blocks of values; comparing the optimal similarity value with a predetermined second matching standard value; If the optimal similarity value satisfies the range defined by the second matching standard value, then use the center of the neighborhood block corresponding to the library image as the corresponding feature point of the real-time image on the library image Feature points.