A method and system for evaluating the standardization of ultrasonic scanning

Abstract

The present invention discloses a method and system for evaluating the standardization of ultrasonic scanning. The method includes: S1, obtaining an ultrasonic image to be evaluated and gray-processing the ultrasonic image, wherein the ultrasonic image includes attribute information; S2, matching the attribute information of the ultrasonic image to be evaluated in a preset template image library to obtain a matched template image; S3, matching the ultrasonic image after gray-scale processing with the matched template image using a normalized correlation coefficient to obtain a result matrix; S4, selecting a matching result whose matching result is greater than a preset threshold in the result matrix, and counting the proportion of the number of matching results to the number of templates in the template image library to determine whether it meets the preset requirements. If so, the ultrasonic image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements. The present invention can assist grassroots doctors in judging whether the image printing quality meets the requirements, so as to master the image printing skills of ultrasonic images more quickly and proficiently.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic technology, and more specifically, to a method and system for evaluating the standardization of ultrasonic scanning. Background Art

[0002] Ultrasound imaging is an imaging diagnostic method with extremely high professional requirements. It has been widely used because of its non-radiation and wide range of examinations. However, there are currently too few professional ultrasound doctors in China, far from meeting the demand for ultrasound doctors at the grassroots level. At this stage, online and offline training can be used to guide grassroots doctors to learn the use of ultrasound. In addition, the domestic market only has document-based image quality descriptions, or words and deeds from ultrasound experts, but there is no professional evaluation system to determine whether grassroots medical staff meet the requirements for the use of ultrasound. In order to avoid missed diagnoses and misdiagnoses caused by unprofessional grassroots medical staff, it is necessary to develop a standardized evaluation method and system for ultrasound scanning. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for evaluating the standardization of ultrasonic scanning to overcome the defects of the prior art.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] A method for evaluating the standardization of ultrasonic scanning comprises the following steps:

[0006] S1. Acquire an ultrasound image to be evaluated and perform grayscale processing on the ultrasound image, wherein the ultrasound image includes attribute information;

[0007] S2, matching the attribute information of the ultrasound image to be evaluated in a preset template image library to obtain a matched template image;

[0008] S3, matching the grayscale processed ultrasound image with the matched template image using a normalized correlation coefficient to obtain a result matrix;

[0009] S4. Select matching results whose matching results are greater than a preset threshold in the result matrix, and count whether the number of matching results accounts for the number of templates in the template image library to meet the preset requirements. If yes, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements.

[0010] Furthermore, the attribute information of the ultrasound image in step S1 includes the imaging location and the name of the lesion.

[0011] Furthermore, the step of establishing the preset template image library in step S2 includes:

[0012] S20, creating a dynamic array, where the dynamic array is used to collect the widths and heights of all ultrasound template images of the same type;

[0013] S21, stitching all ultrasound template images of the same type in the dynamic array into one image through a stitching algorithm;

[0014] S22. Repeat steps S20-S21 to obtain images stitched from all different types of ultrasound images, and form a template image library from all images.

[0015] Furthermore, after obtaining the matched template image, step S2 further includes: obtaining the width and height of the template image.

[0016] Furthermore, the step S3 is specifically as follows: connecting the grayscale processed ultrasound image and the matched template image to a template matching function, wherein the template matching function adopts a normalized correlation coefficient matching method.

[0017] Furthermore, the matching step in step S3 is to traverse the entire image of the template image in sequence with a search box of the size of the ultrasound image to be evaluated, with each row traversed W-w+1 times and each column traversed H-h+1 times. The matching result matrix is ​​(W-w+1, H-h+1), wherein w and h are the width and height of the ultrasound image to be evaluated, respectively, and W and H are the height and width of the template image, respectively.

[0018] Furthermore, the formula of the normalized correlation coefficient matching method is:

[0019] ;

[0020] Wherein, T` is the template image, I` is the ultrasound image to be evaluated, x, y are the coordinates of the upper left corner element of the current search box in the I` matrix, and x', y' are the element coordinates of the matrix of I` framed by T` and the search box.

[0021] Furthermore, the preset threshold in step S4 is 90%, and when the number of matching results accounts for more than 20% of the number of templates in the template image library, the preset requirement is met.

[0022] The present invention also provides a system based on the above-mentioned ultrasound scanning standardization evaluation method, comprising:

[0023] An acquisition module, used for acquiring an ultrasonic image to be evaluated and performing grayscale processing on the ultrasonic image, wherein the ultrasonic image includes attribute information;

[0024] A first matching module, used for matching the attribute information of the ultrasound image to be evaluated in a preset template image library to obtain a matched template image;

[0025] A second matching module is used to match the grayscale processed ultrasound image with the matched template image using a normalized correlation coefficient to obtain a result matrix;

[0026] A judgment and selection module is used to select matching results whose matching results are greater than a preset threshold in the result matrix, and to count whether the number of matching results accounts for the number of templates in the template image library to meet the preset requirements. If yes, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements;

[0027] The acquisition module, the first matching module, the second matching module and the judgment and selection module are connected in sequence.

[0028] Compared with the prior art, the advantages of the present invention are that the present invention can assist primary care doctors in determining whether the printing quality meets the requirements, so as to master the printing skills of ultrasound images more quickly and proficiently, improve the printing quality and efficiency, and save labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 It is a flow chart of the ultrasonic scanning standardization evaluation method of the present invention.

[0031] Figure 2 It is a flow chart of step S2 in the present invention.

[0032] Figure 3 It is a schematic diagram of the ultrasonic scanning standardization evaluation system of the present invention.

[0033] Figure 4 is an exemplary system architecture diagram in which the present invention can be applied. DETAILED DESCRIPTION

[0034] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0035] See also Figure 1 and Figure 2 As shown, this embodiment discloses a method for evaluating the standardization of ultrasonic scanning, comprising the following steps:

[0036] Step S1, obtaining an ultrasonic image to be evaluated and performing grayscale processing on the ultrasonic image, wherein the ultrasonic image includes attribute information.

[0037] Specifically, the ultrasound images to be evaluated are generally obtained in medical institutions such as towns and villages. Usually, the relationship between the similarity and color of the images is not very large, so this embodiment processes the ultrasound image into a grayscale image to reduce the complexity of the later calculation. Specifically, the cvtColor interface can be used to convert the ultrasound image to be evaluated into a grayscale image Img_gray. Of course, the image color can also be retained according to special needs.

[0038] Specifically, the attribute information of the ultrasound image includes the imaging location and the name of the lesion.

[0039] Step S2: matching is performed in a preset template image library according to the attribute information of the ultrasound image to be evaluated to obtain a matched template image.

[0040] Specifically, the matched template image is represented by template, and the width and height of the template image template need to be obtained through shape[:2] to facilitate subsequent calculations. The specific code is as follows:

[0041] template_h, template_w = template.shape[:2]

[0042] See also Figure 2 As shown, the steps of establishing the preset template image library in this embodiment include:

[0043] Step S20: Create a dynamic array, which is used to collect the width and height of all ultrasound template images of the same type. Specifically, the dynamic array can be represented by code as follows:

[0044] double* ImageQ = new double[Img_Width * Img_Height * number]

[0045] Among them, Img_Width and Img_Height are the width and height of each ultrasound template image, and number is the number of templates.

[0046] Step S21: stitching all ultrasound template images of the same type in the dynamic array into one image through a stitching algorithm.

[0047] Specifically, all templates are stitched into an image ImageQ through the opencv stitching algorithm Stitcher. The implementation code is as follows:

[0048] Ptr stitcher = Stitcher::create(mode);

[0049] Stitcher::Status status = stitcher->stitch(imgs, pano);

[0050] The first line of code creates a pointer to the stitching Stitcher, the second line of code calls the stitching algorithm, the input parameter represented by imgs is a vector of a series of Mat objects, and the output result represented by pano is the Mat object after stitching.

[0051] Step S22, repeating steps S20-S21 to obtain images stitched together from all different types of ultrasound images, and forming a template image library from all images.

[0052] Step S3: Match the grayscale processed ultrasound image with the matched template image using a normalized correlation coefficient to obtain a result matrix.

[0053] Specifically, the grayscale processed ultrasound image Img_gray and the matched template image template are connected to the template matching function matchTemplate (an interface), and the template matching function adopts the normalized correlation coefficient matching method. A result matrix result is obtained. Specifically, the implementation code is as follows:

[0054] matchTemplate(InputArray image, InputArray templ, OutputArray result, int method)

[0055] image: Input a grayscale processed ultrasound image to be matched, supporting 8U or 32F.

[0056] templ: Input a template image, the same type as image.

[0057] result: Output matrix to save the result, 32F type.

[0058] method: the data comparison method to be used. In this embodiment, the normalized correlation coefficient matching method is adopted.

[0059] Specifically, during matching, a search box of the size of the ultrasound image to be evaluated is used to traverse the entire image of the template image in sequence, with each row traversed W-w+1 times and each column traversed H-h+1 times. The result matrix obtained by matching is (W-w+1, H-h+1), wherein w and h are the width and height of the ultrasound image to be evaluated, respectively, and W and H are the height and width of the template image, respectively.

[0060] Specifically, the formula of the normalized correlation coefficient matching method described in this embodiment is:

[0061] ;

[0062] Wherein, T` is the template image, I` is the ultrasound image to be evaluated, x, y are the coordinates of the upper left corner element of the current search box in the I` matrix, and x', y' are the element coordinates of the matrix of I` framed by T` and the search box.

[0063] The normalized correlation coefficient matching method is used: a perfect match will get 1, a perfect negative correlation match will get -1, and a complete mismatch will get 0.

[0064] Step S4, selecting matching results whose matching results are greater than a preset threshold in the result matrix, and counting the proportion of the number of matching results to the number of templates in the template image library to see whether they meet the preset requirements; if so, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements.

[0065] Specifically, the preset threshold is 90%, that is, matching results with a matching rate greater than 90% are selected from the results, and the preset requirement is met when the number of matching results accounts for more than 20% of the number of templates in the template image library.

[0066] See also Figure 3 As shown, the present invention also provides a system based on the above-mentioned ultrasound scanning standardization evaluation method, including: an acquisition module 1, used to acquire an ultrasound image to be evaluated and grayscale process the ultrasound image, wherein the ultrasound image includes attribute information; a first matching module 2, used to match the attribute information of the ultrasound image to be evaluated in a preset template image library to obtain a matched template image; a second matching module 3, used to match the ultrasound image after grayscale processing with the matched template image using a normalized correlation coefficient to obtain a result matrix; a judgment and selection module 4, used to select a matching result whose matching result is greater than a preset threshold in the result matrix, and count whether the number of the matching results accounts for the number of templates in the template image library to meet the preset requirements, if yes, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements; the acquisition module 1, the first matching module 2, the second matching module 3 and the judgment and selection module 4 are connected in sequence.

[0067] See also Figure 4 , which is a system architecture diagram for a specific application of the present invention, and the system architecture may include terminal devices 101, 102, a base terminal 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, the base terminal 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0068] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and grassroots end 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. Terminal devices 101, 102, and grassroots end 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert compression standard audio layer 4) players, laptop portable computers and desktop computers, etc. Server 105 can be a server that provides various services, such as a background server that supports the pages displayed on terminal devices 101, 102, and grassroots end 103. Server 105 can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0069] It should be noted that the ultrasound scanning standardization evaluation method provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the ultrasound scanning standardization evaluation method system is generally set in the terminal devices 101 and 102. The grassroots terminal 40 is connected to grassroots medical institutions such as towns and villages, and is used to store some ultrasound images to be evaluated. There is an "Evaluation" button on the page of the ultrasound scanning standardization evaluation system. By clicking the "Evaluation" button, you can choose to call the ultrasound image to be evaluated in the grassroots terminal 40 for matching.

[0070] It should be understood that Figure 1The number of terminal devices, base terminals, networks and servers in the embodiment is only for illustration. Any number of terminal devices, base terminals, networks and servers may be provided according to the implementation requirements.

[0071] The present invention can assist primary care physicians in determining whether the imaging quality meets the requirements, so as to more quickly and skillfully master the imaging skills of ultrasound images, improve imaging quality and efficiency, and save labor costs.

[0072] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, the patent owner may make various variations or modifications within the scope of the appended claims. As long as they do not exceed the protection scope described in the claims of the present invention, they should be within the protection scope of the present invention.

Claims

1. A method for evaluating the standardization of ultrasonic scanning, characterized in that: The following steps are involved: S1. Acquire an ultrasound image to be evaluated and perform grayscale processing on the ultrasound image, wherein the ultrasound image includes attribute information; S2, matching the attribute information of the ultrasound image to be evaluated in a preset template image library to obtain a matched template image; S3, matching the grayscale processed ultrasound image with the matched template image using a normalized correlation coefficient to obtain a result matrix; S4, selecting matching results whose matching results are greater than a preset threshold in the result matrix, and counting whether the number of the matching results accounts for the number of templates in the template image library to meet the preset requirements, if yes, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements; The steps of establishing the preset template image library in step S2 include: S20, creating a dynamic array, where the dynamic array is used to collect the widths and heights of all ultrasound template images of the same type; S21, stitching all ultrasound template images of the same type in the dynamic array into one image through a stitching algorithm; S22. Repeat steps S20-S21 to obtain images stitched from all different types of ultrasound images, and form a template image library from all images.

2. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: The attribute information of the ultrasound image in step S1 includes the imaged location and the name of the lesion.

3. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: After obtaining the matched template image, step S2 further includes: obtaining the width and height of the template image.

4. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: The step S3 specifically includes: connecting the grayscale processed ultrasound image and the matched template image to a template matching function, wherein the template matching function adopts a normalized correlation coefficient matching method.

5. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: The matching step in step S3 is to traverse the entire image of the template image in sequence with a search box of the size of the ultrasound image to be evaluated, with each row traversed W-w+1 times and each column traversed H-h+1 times. The result matrix obtained by matching is (W-w+1, H-h+1), wherein w and h are respectively the width and height of the ultrasound image to be evaluated, and W and H are respectively the height and width of the template image.

6. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: The formula of the normalized correlation coefficient matching method is: ； Wherein, T' is the template image, I' is the ultrasound image to be evaluated, x, y are the coordinates of the upper left corner element of the current search box in the I' matrix, and x', y' are the element coordinates of the matrix of I' framed by T' and the search box.

7. The ultrasonic scanning standardization evaluation method according to claim 1 is characterized in that: The preset threshold in step S4 is 90%, and the preset requirement is met when the number of matching results accounts for more than 20% of the number of templates in the template image library.

8. A system according to any one of claims 1 to 7 for evaluating the standardization of ultrasonic scanning, characterized in that: include: An acquisition module, used for acquiring an ultrasonic image to be evaluated and performing grayscale processing on the ultrasonic image, wherein the ultrasonic image includes attribute information; A first matching module, used for matching the attribute information of the ultrasound image to be evaluated in a preset template image library to obtain a matched template image; A second matching module is used to match the grayscale processed ultrasound image with the matched template image using a normalized correlation coefficient to obtain a result matrix; A judgment and selection module is used to select matching results whose matching results are greater than a preset threshold in the result matrix, and to count whether the number of matching results accounts for the number of templates in the template image library to meet the preset requirements. If yes, the ultrasound image to be evaluated meets the evaluation requirements, otherwise it does not meet the evaluation requirements; The acquisition module, the first matching module, the second matching module and the judgment and selection module are connected in sequence.

Images