WO2020232998A1 - Medical image evaluation method and apparatus, computer device and storage medium - Google Patents

Abstract

The present application relates to the technical field of artificial intelligence, and provides a medical image evaluation method and apparatus, a computer device and a storage medium. The medical image evaluation method comprises: obtaining a medical image to be evaluated and preprocessing same to obtain a binarization image; scoring the binarization image according to a metal artifact scoring item in a preset scoring library to obtain a metal artifact scoring result; sending the medical image, a basic scoring item corresponding to the medical image, the metal artifact scoring item and the metal artifact scoring result to at least two evaluation users for user scoring; receiving target scoring results fed back by the evaluation users, and calculating and outputting a comprehensive score corresponding to the medical image in combination of preset weight coefficients of the evaluation users; and comparing the comprehensive score with a preset threshold range, and determining the grade of the comprehensive score as an evaluation result for outputting. Therefore, the remote quality control examination on the medical image on the Internet is achieved, the evaluation users do not need to go to the site for examination, and the working efficiency of quality control examination is improved.

Description

Medical image evaluation method, device, computer equipment and storage medium

This application is based on the Chinese invention patent application filed on May 22, 2019 with the application number 201910426634.6 and titled "Medical Image Evaluation Method, Device, Computer Equipment and Storage Medium", and claims its priority.

Technical field

This application relates to the field of artificial intelligence technology, in particular to a medical image evaluation method, device, computer equipment and storage medium

Background technique

At present, medical imaging is one of the important technologies for assisted diagnosis of diseases. The quality level of its images has a great relationship with the diagnosis results of the disease. The inventor realized that if the quality level of the images is too low, it will seriously affect the diagnosis results of the disease. Therefore, the requirements for image quality are high, and hospital image quality needs to be assessed regularly. The current assessment method is mainly from experts in the medical field to the hospital for quality control assessment of medical images, and remote quality control of medical images cannot be performed on the Internet. Inspection results in a large workload and time-consuming process, which reduces the efficiency of image quality control inspection.

Summary of the invention

The embodiments of the present application provide a medical image evaluation method, device, computer equipment, and storage medium to solve the problem that the quality control inspection of medical images cannot be performed remotely on the Internet, and the work efficiency of the medical image quality control inspection is reduced.

A medical imaging evaluation method, including:

Obtain medical images to be evaluated;

Preprocessing the medical image to obtain a binary image;

The binarized image is scored according to the metal artifact score item in a preset score library to obtain a metal artifact score result, wherein the preset score library includes the basic score item corresponding to the medical image and the Metal artifact score item;

Sending the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

Receiving the target scoring result fed back by the evaluating user, combining with the preset weight coefficient of the evaluating user, calculating and outputting a comprehensive score corresponding to the medical image;

The comprehensive score is compared with a preset threshold range to determine the level of the comprehensive score and output as an evaluation result.

A medical image evaluation device, including:

The first acquisition module is used to acquire the medical image to be evaluated;

The preprocessing module is used to preprocess the medical image to obtain a binary image;

The automatic scoring module is used for scoring the binarized image according to the metal artifact scoring items in the preset scoring library to obtain the metal artifact scoring result, wherein the preset scoring library includes the corresponding medical image The basic scoring item and the metal artifact scoring item;

The user scoring module is configured to send the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

A calculation module, configured to receive the target scoring result fed back by the evaluation user, and combine the predetermined weight coefficient of the evaluation user to calculate and output a comprehensive score corresponding to the medical image;

The output module is used to compare the comprehensive score with a preset threshold range, determine the level of the comprehensive score, and output it as an evaluation result.

A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and capable of running on the processor, and the processor implements the above medical image evaluation method when the computer readable instructions are executed A step of.

A non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the above medical image evaluation method is implemented step.

The details of one or more embodiments of the present application are presented in the following drawings and description, and other features and advantages of the present application will become apparent from the description, drawings and claims.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

Fig. 1 is a flowchart of a medical image evaluation method provided by an embodiment of the present application;

2 is a flowchart of step S1 in the medical image evaluation method provided by an embodiment of the present application;

FIG. 3 is a flowchart of step S2 in the medical image evaluation method provided by the embodiment of the present application;

4 is a flowchart of step S21 in the medical image evaluation method provided by the embodiment of the present application;

FIG. 5 is a flowchart of determining an evaluation user in the medical image evaluation method provided by an embodiment of the present application;

Fig. 6 is a schematic diagram of a medical image evaluation device provided by an embodiment of the present application;

Fig. 7 is a basic structural block diagram of a computer device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of this application.

The data processing method provided in this application is applied to the server, and the server can be implemented by an independent server or a server cluster composed of multiple servers. In one embodiment, as shown in FIG. 1, a medical image evaluation method is provided, including the following steps:

S1: Obtain medical images to be evaluated.

In the embodiments of this application, medical imaging is one of the important technologies for disease-assisted diagnosis. The quality of medical imaging will directly affect the doctor’s diagnosis decision. Therefore, it is necessary to perform quality control checks on the medical imaging, and the medical imaging to be evaluated is used. Medical images for quality control inspections.

Specifically, the medical image to be evaluated is directly obtained through the image database. Among them, the image database refers to a database dedicated to storing medical images.

S2: Preprocess the medical image to obtain a binary image.

In the embodiment of the present application, preprocessing refers to an image processing step of processing a medical image into a binary image. Binarization refers to setting the pixel value of the pixel on the image to 0 or 255, which means that the entire image presents an obvious visual effect of only black and white.

Specifically, the medical image is imported into a preset port for preprocessing to obtain a binary image. Among them, the preset port refers to an image processing port dedicated to preprocessing medical images.

S3: Scoring the binarized image according to the metal artifact scoring item in the preset scoring library to obtain a metal artifact scoring result, where the preset scoring library includes basic scoring items and metal artifact scoring items corresponding to the medical image.

In the embodiment of the present application, the binarized image includes its corresponding filming type, and the filming type may specifically be CT type, CR type, and so on. The metal artifact scoring result can directly reflect the scoring situation of the metal artifact scoring item in the medical image, and reduce the workload of the user to score the metal artifact scoring item.

Specifically, the legal filming type that is the same as the filming type corresponding to the binarized image is queried from the preset scoring library, and when the legal filming type that is the same as the filming type is queried, the metal artifact scoring item corresponding to the legal filming type is obtained, When the metal artifact score item in the binarized image has metal artifacts, that is, there are white pixels in the metal artifact score item in the binarized image, the metal artifact score result corresponding to the metal artifact score item is determined to be 0 ; When there is no metal artifact in the metal artifact score item in the binarized image, that is, there is no white pixel in the metal artifact score item in the binarized image, the metal artifact score result corresponding to the metal artifact score item Determined as the pre-set score value in the metal artifact score item.

Among them, the preset scoring library refers to a database specifically used to store legal filming types and scoring standards corresponding to legal filming types.

It should be noted that the metal artifact scoring standard corresponding to the legal filming type is the metal artifact scoring standard corresponding to the medical image.

For example, the presence of metal artifacts is the presence or absence of metal artifacts in the upper half of the image, and the pre-set score value in the metal artifacts score is 10. If there are metal artifacts in the upper half of the binarized image , The metal artifact score corresponding to the metal artifact score item is 0. If there is no metal artifact in the upper half of the binarized image, the metal artifact score corresponding to the metal artifact score item is 10 .

S4: Send the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring.

In the embodiments of the present application, the scoring user refers to an expert in the medical field who is specifically responsible for scoring medical images. According to a preset method, the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result are randomly sent to a preset number of evaluation users for user scoring. Among them, the preset mode may be specifically in the form of email, or may be set according to the actual needs of the user. The preset number is at least 2, but it can also be 5. There is no restriction here.

For example, if there are 5 evaluation users, and the preset number is 2, then 2 of the 5 evaluation users are randomly selected according to the preset method, and the medical image, the basic scoring item corresponding to the medical image, and the metal artifact are scored. The item and metal artifact scoring results are sent to the selected 2 evaluation users for user scoring.

It should be noted that the basic scoring items include the scoring of technical operations and the scoring of image content. Technical operations and image content can be set according to the actual needs of users. For example, technical operations can be patient data, image display requirements, etc. The content includes image shooting location, image level, etc.

S5: Receive the target scoring result fed back by the evaluation user, and combine the evaluation user's preset weight coefficient to calculate and output a comprehensive score corresponding to the medical image.

In the embodiment of the present application, when the target evaluation result sent by the evaluation user is detected, the comprehensive score corresponding to the medical image to be evaluated obtained in step S1 is calculated according to the target scoring result and the preset weight coefficient corresponding to the scoring user.

S6: Compare the comprehensive score with the preset threshold range, determine the grade of the comprehensive score, and output it as the evaluation result.

In the examples of this application, the evaluation results of medical images are mainly divided into 4 grades: A, B, C, and D. The grade of A is the highest, which means the quality of the corresponding medical image is the highest, and the grade of B is the highest, which means the corresponding medical image. The quality of is the second highest, and so on, the grade of D is the lowest, which means the quality of the corresponding medical image is the lowest. And each level has its corresponding preset threshold range.

Specifically, the comprehensive score is matched with the preset threshold range corresponding to each level. If the comprehensive score is within the preset threshold range corresponding to a certain level, it means that the comprehensive score belongs to the level within the preset threshold range, and This level is output as the evaluation result. Among them, the preset threshold range can be 91-100, and the specific value range is set according to the actual needs of the user, and there is no limitation here.

For example, the preset threshold ranges corresponding to the quality levels of medical images A, B, C, and D are: 91-100, 71-90, 51-70, and 0-50, respectively. If the overall score of the medical image is 95, then Indicates that the quality level corresponding to the medical image is A.

In this embodiment, the binarized image is obtained by image processing the medical image to be evaluated, and the binarized image is scored according to the metal artifact score item to obtain the metal artifact score result, and then the medical image and the medical image corresponding to the basic The scoring items, metal artifact scoring items, and metal artifact scoring results are sent to at least two evaluation users for user scoring, and the target scoring results fed back by the evaluation users are calculated to obtain a comprehensive score, and the comprehensive score is compared with the preset threshold range , Determine the level of the comprehensive score as the output of the evaluation result. In this way, the quality control inspection of medical images can be performed remotely on the Internet, and the accuracy of the medical image quality evaluation can be ensured by combining the target scoring results of the evaluation users, avoiding the need for the evaluation users to go to the hospital to conduct quality control assessments, and effectively reducing manual intervention Improve the work efficiency of medical image quality control inspection.

In one embodiment, as shown in FIG. 2, in step S1, acquiring the medical image to be evaluated includes the following steps:

S11: According to the preset filming type, obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table.

Specifically, the preset filming type is matched with the record type in the preset data table, and when the record type that is the same as the preset filming type is matched, the number of inspections per month corresponding to the record type is obtained, and the preset All inspections in the month are summed to get the total number of inspections in the preset month.

Among them, the preset filming type refers to the filming type selected by the user for quality control inspection, such as CT type, CR type, and so on.

The preset data table refers to a data table specially used to store the record type and the number of inspections corresponding to the month of the record type.

The preset month can be from October to December, and the specific value range is set according to the actual needs of the user, and there is no limitation here.

S12: Multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections.

Specifically, according to the total number of inspections obtained in step S11, the total number of inspections is multiplied by the quality control coefficient, and the obtained product is used as the total number of quality control inspections that are preset to participate in quality control inspections in the future months. Among them, the quality control coefficient is a constant set by the user according to actual needs, and its specific value can be 1% or 10%, and there is no limitation here.

For example, if the total number of inspections is 100 and the quality control coefficient is 10%, the next six months are preset for the next six months, and the total number of inspections 100 is multiplied by the quality control coefficient 10%, and the product obtained is 10 as the quality control that will participate in the quality control inspection in the next six months Check the total.

S13: Use the total number of quality control inspections and the preset base to calculate the remainder to obtain the monthly target quality control quantity.

Specifically, the total number of quality control inspections obtained in step S12 is divided by a preset base number, and the obtained quotient is used as the target quality control quantity for each month. Among them, the preset base may be 5, and its specific value may be set according to the actual needs of the user, and there is no limitation here.

It should be noted that when the total number of quality control inspections is divided by the preset base, if there is a remainder, the value of the quotient will be rounded, and the rounded quotient will be used as the target quality control quantity; if there is no remainder, the corresponding The quotient obtained after division is used as the target quality control quantity.

For example, when the total number of quality control inspections is 100 and the preset base is 6, there is a remainder of 4 after dividing 100 by 6 to obtain 16, and the quotient after rounding is 16, then the target quality control quantity is 16; when the total number of quality control inspections When the preset base is 6, and the quotient obtained by dividing 120 by 6 is 20, the target quality control quantity is 20.

S14: Obtain the medical images to be evaluated in the target quality control quantity from the image database.

Specifically, when it is detected that the current date is the preset date, the medical images stored in the current month of the preset filming type are queried from the image database. If relevant medical images are queried, the queried medical images are determined to be pending The medical image to be evaluated, and extract the medical image to be evaluated in the target quality control quantity.

It should be noted that if the relevant medical image is not queried, it means that the corresponding medical image is not stored in the image database in the current month, and the medical image is not extracted.

For example, the preset date is the last day of each month, there are 100 medical images of October CT type in the image database, and the target quality control number is 10. When the relevant medical images in the medical image database are inquired in October, if The preset filming type is CT. Since CT medical images are queried from the image database, the CT medical images are determined as medical images to be evaluated, and 10 medical images are randomly extracted; if the preset filming type is CR type, because no CR type medical image is found from the image database, no extraction processing is performed.

In this embodiment, the total number of quality control inspections is calculated, and then the total number of quality control inspections is used to calculate the target quality control quantity for each month, and finally the medical image of the target quality control quantity is obtained, so as to achieve accurate acquisition of the monthly participation quality control The medical image of the examination improves the work efficiency of subsequent participation in the medical image quality control examination.

In one embodiment, as shown in FIG. 3, in step S2, preprocessing the medical image to obtain a binary image includes the following steps:

S21: Perform gray-scale processing on the medical image to obtain a gray-scale image.

In the embodiments of this application, grayscale means that in the RGB model, if R=G=B, the color represents only one grayscale color, and the value of R=G=B is called the grayscale value. Therefore, Each pixel of the grayscale image only needs one byte to store the gray value, and the gray range is 0-255.

Through the gray-scale processing of the medical image, the pixel values of all pixels in the medical image are adjusted to 0-255, and the gray-scale image of the medical image is obtained.

S22: Scan each pixel in the grayscale image.

Specifically, scan each pixel in the grayscale image.

S23: If the pixel value of the pixel is smaller than the pixel threshold of the metal artifact, then the pixel value of the pixel is set to 0.

In the embodiment of the present application, if the pixel value of the pixel is smaller than the pixel threshold of the metal artifact, the pixel value of the pixel is set to 0, that is, the pixel becomes black. Among them, the pixel threshold of metal artifacts may specifically be 50, or it may be set according to the actual needs of the user, and there is no limitation here.

It should be noted that the pixel threshold of metal artifacts is specifically used to distinguish whether a pixel is a metal artifact. If the pixel value of a pixel is less than the pixel threshold of a metal artifact, the pixel is not a metal artifact; if the pixel is If the pixel value of is greater than or equal to the pixel threshold of the metal artifact, the pixel is a metal artifact.

S24: If the pixel value of the pixel point is greater than or equal to the pixel threshold value of the metal artifact, then the pixel value of the pixel point is set to 255.

Specifically, if the pixel value of the pixel point is greater than or equal to the pixel threshold value of the metal artifact, the pixel value of the pixel point is set to 255, that is, the pixel point becomes white.

S25: The grayscale image is converted into a binary image.

In the embodiment of this application, based on the grayscale image obtained in step S21, in order to make the pixel value of the image only present 0 or 255, that is, the image only presents two colors of black and white, it is necessary to further perform the grayscale image Binarization processing, the image after the binarization processing is the binarized image.

Specifically, after completing the pixel value setting of the pixel according to steps S22 to S24, the grayscale image is converted into a binary image.

It should be noted that the white part in the binarized image is a metal artifact.

In this embodiment, by first performing gray-scale processing on the medical image, and then performing the binarization process to obtain a binarized image, the pixel value of the pixel in the medical image can be set to 0 or 255, that is, the pixel in the medical image The dots appear black or white, which can effectively identify features in medical images and further improve the accuracy of subsequent medical image quality control inspections.

In an embodiment, as shown in FIG. 4, in step S21, that is, performing gray-scale processing on the medical image to obtain a gray-scale image includes the following steps:

S211: traverse the pixels in the medical image to obtain the RGB component value of each pixel.

Specifically, the pixels in the medical image are traversed according to a preset traversal mode to obtain the RGB component value of each pixel, where R, G, and B represent the colors of the three channels of red, green, and blue, respectively.

Among them, the preset traversal method can specifically be based on the upper left pixel of the medical image as the starting point, and traverse row by row from top to bottom from left to right, or it can be traversed from the center line of the medical image to both sides at the same time. It can also be other traversal methods, and there is no restriction here.

S212: According to the RGB component values of the pixels, perform gray-scale processing on the medical image according to formula (1):

g(x,y)=k ₁ *R(x,y)+k ₂ *G(x,y)+k ₃ *B(x,y) Formula (1)

Among them, x and y are the abscissa and ordinate of each pixel in the medical image, g(x,y) is the gray value of the pixel (x,y) after grayscale processing, R(x,y) Is the color component of the R channel of the pixel (x,y), G(x,y) is the color component of the G channel of the pixel (x,y), and B(x,y) is the pixel (x,y) The color components of the B channel, k ₁ , k ₂ and k ₃ are all constants.

In the embodiments of this application, in order to achieve accurate extraction of the information content of the medical image, the medical image needs to be grayed out first. Among them, the parameter values of k ₁ , k ₂ and k ₃ can be performed according to actual application needs. Setting is not limited here. By adjusting the value range of k ₁ , k ₂ , and k ₃ , the proportions of R channel, G channel and B channel can be adjusted respectively.

The RGB model is a commonly used way of expressing color information. It uses the brightness of the three primary colors of red, green and blue to quantitatively represent colors. This model is also called the additive color mixing model, which is a method in which RGB three-color light is superimposed on each other to achieve color mixing, so it is suitable for display of luminous bodies such as displays.

Grayscale means that in the RGB model, if R=G=B, the color represents only one grayscale color. The value of R=G=B is called the grayscale value. Therefore, each pixel of the grayscale image Only one byte is needed to store the gray value, and the gray range is 0-255.

It should be noted that in the embodiment of the present application, the gray value of the medical image is weighted by formula (1). In other embodiments, the component method, the maximum value method, or the average value method may also be used to gray the medical image. There are no restrictions here.

In this embodiment, by traversing the pixels in the medical image and obtaining the RGB component value of the corresponding pixel, according to the obtained RGB component value of each pixel, the medical image is grayed out using formula (1), In this way, the pixel value range of the pixels in the medical image is set between 0-255, which further reduces the amount of raw medical image data and improves the calculation efficiency in subsequent processing calculations.

In one embodiment, as shown in Fig. 5, after step S3 and before step S4, the medical image evaluation method further includes the following steps:

S7: Obtain the hospital identification information corresponding to the medical image from the preset database.

Specifically, the hospital identification information corresponding to the medical image is directly obtained through the preset database. Among them, the preset database refers to a database specially used for storing medical images and hospital identification information corresponding to the medical images.

S8: Determine and evaluate the user by matching the hospital identification information with the identification information in the user database.

Specifically, the legal user is obtained from the user database, and the identification information corresponding to the legal user is matched with the hospital identification information. If the hospital identification information is the same as the identification information, it means that the legal user is a staff member of the hospital, and The legal user is excluded; if the hospital identification information is not the same as the identity identification information, it means that the legal user is a staff member in another hospital, and the legal user is determined as an evaluation user.

Among them, the user database refers to the storage of legal users who participate in the manual scoring of medical images, and each legal user has its corresponding identification information, which corresponds to the hospital identification information of the hospital where the legal user is located The same, for example, the hospital identification information of W Hospital is W, and if the legal user is a staff member of W Hospital, the identification information of the legal user and the hospital identification information are both W.

For example, there are three hospitals A, B, and C. The corresponding hospital identification information is A, B, and C. There are legitimate users a, b, and c in the user database, and the corresponding identification information is A, B, and C, respectively. The hospital identification information corresponding to the image Q is A, and the hospital identification information A is matched with the identification information A, B, and C respectively. Since the identification information A corresponding to the legal user a is the same as the hospital identification information A, it means the legal user a For the staff of hospital A, the legal user a is excluded; since the identification information B and C corresponding to the legal users b and c are different from the hospital identification information A, it means that the legal users b and c are both staff in other hospitals , And determine both b and c as evaluation users.

In this embodiment, the evaluation user is determined by matching the hospital identification information and the identity information, which can accurately select the appropriate evaluation user to analyze the medical image, and avoid the occurrence of the evaluation user as the hospital staff corresponding to the medical image, which may lead to cheating. In order to ensure the accuracy of medical image quality control inspection.

In one embodiment, in step S5, receiving the target score result fed back by the evaluating user, combining with the preset weight coefficient of the evaluating user, calculating and outputting the comprehensive score corresponding to the medical image includes the following steps:

Calculate the comprehensive score corresponding to the medical image according to formula (2):

Among them, X is the comprehensive score, w _n is the target evaluation result fed back by the nth evaluation user, f _n is the preset weight coefficient of the nth evaluation user, and n is a constant.

In the embodiment of the present application, the comprehensive score is used to evaluate the quality of the medical image. Among them, the parameter value of f _n can be set according to the needs of the actual application, and there is no limitation here. By adjusting the value range of f _n The proportion of the target evaluation results feedback from the corresponding evaluation users can be adjusted respectively.

In this embodiment, formula (2) can be used to quickly and accurately calculate the comprehensive score corresponding to the medical image, improve the accuracy of subsequent evaluation of the medical image using the comprehensive score, and further improve the work efficiency of the medical image quality control inspection.

In an embodiment, after step S6, the medical image evaluation method further includes the following steps:

According to the evaluation results, the quality of the medical equipment corresponding to the medical image is assessed, the medical equipment with unqualified quality is determined, and the medical equipment information corresponding to the medical image is sent to the target user for confirmation.

In the embodiments of the present application, medical equipment refers to machinery and equipment used to shoot medical images. The evaluation result is used to reflect the quality of the medical image. The quality of the medical equipment can be directly reflected through the quality of the medical image, and the evaluation result includes the medical equipment information corresponding to the medical image. For example, the medical equipment information corresponding to the medical image T is the medical equipment of the T1 hospital .

Specifically, according to the medical equipment information corresponding to the medical image in the evaluation result and the target quality control quantity in step 13, the evaluation result corresponding to the same medical equipment information of the target quality control quantity is selected, if the target quality control quantity is greater than or equal to the preset quantity If the evaluation result corresponding to the same medical equipment information is D, it means that the quality of the medical equipment corresponding to the evaluation result is unqualified, and the medical equipment information corresponding to the medical image is sent to the target user for confirmation in a preset manner.

For example, if there is a target quality control number of 5 and an evaluation result of 10, 5 of the evaluation results include the medical equipment information corresponding to the medical image as the medical equipment of the F1 hospital, and 2 evaluation results are D; the other 5 evaluation results include The medical equipment information corresponding to the medical image is the medical equipment of the F2 hospital, and one evaluation result is D; if the preset number is 2, because the medical equipment corresponding to the F1 hospital has 2 evaluation results of the evaluation result, it means The quality of the medical equipment of the F1 hospital is unqualified, so the medical equipment information of the F1 hospital is sent to the target user for confirmation in a preset manner.

Further, the target user can check and process the medical equipment in time based on the acquired information of the unqualified medical equipment, and improve the efficiency of monitoring the quality of the medical equipment.

In this embodiment, the quality of the medical equipment corresponding to the medical image is assessed according to the evaluation result, and the information of the unqualified medical equipment is sent to the target user for confirmation, thereby automatically reminding the user of the medical equipment of the unqualified quality to help the user The quality of medical equipment is intelligently monitored to avoid the need for users to manually analyze the quality of medical equipment during the quality control inspection process, thereby improving the work efficiency of the medical image quality control inspection.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

In one embodiment, a medical image evaluation device is provided, and the medical image evaluation device corresponds to the medical image evaluation method in the above-mentioned embodiment one-to-one. As shown in FIG. 6, the medical image evaluation device includes a first acquisition module 61, a preprocessing module 62, an automatic scoring module 63, a user scoring module 64, a calculation module 65 and an output module 66. The detailed description of each functional module is as follows:

The first acquisition module 61 is used to acquire medical images to be evaluated;

The preprocessing module 62 is used to preprocess the medical image to obtain a binary image;

The automatic scoring module 63 is used for scoring the binarized image according to the metal artifact scoring items in the preset scoring library to obtain the metal artifact scoring result. The preset scoring library includes the basic scoring items and metal artifacts corresponding to the medical image. Artifact score item;

The user scoring module 64 is configured to send the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

The calculation module 65 is configured to receive the target scoring result fed back by the evaluation user, and combine the evaluation user's preset weight coefficient to calculate and output the comprehensive score corresponding to the medical image;

The output module 66 is used to compare the comprehensive score with the preset threshold range, determine the level of the comprehensive score, and output it as the evaluation result.

Further, the first obtaining module 61 includes:

The total acquisition sub-module is used to obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table according to the preset filming type;

The multiplication sub-module is used to multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections;

The remainder calculation sub-module is used to calculate the remainder by using the total number of quality control inspections and the preset base number to obtain the target quality control quantity for each month;

The second acquisition sub-module is used to acquire the medical images to be evaluated in the target quality control quantity from the image database.

Further, the preprocessing module 62 includes:

The gray-scale sub-module is used to perform gray-scale processing on medical images to obtain gray-scale images;

Scanning sub-module, used to scan each pixel in the grayscale image;

The first comparison sub-module is configured to set the pixel value of the pixel to 0 if the pixel value of the pixel is smaller than the pixel threshold of the metal artifact;

The second comparison sub-module is used to set the pixel value of the pixel to 255 if the pixel value of the pixel is greater than or equal to the pixel threshold of the metal artifact;

The conversion sub-module is used for converting grayscale images into binary images.

Further, the gray-scale sub-module includes:

The traversal unit is used to traverse the pixels in the medical image and obtain the RGB component value of each pixel;

The grayscale calculation unit is used to perform grayscale processing on medical images according to the RGB component values of the pixels according to formula (1):

g(x,y)=k ₁ *R(x,y)+k ₂ *G(x,y)+k ₃ *B(x,y) Formula (1)

Among them, x and y are the abscissa and ordinate of each pixel in the medical image, g(x,y) is the gray value of the pixel (x,y) after grayscale processing, R(x,y) Is the color component of the R channel of the pixel (x,y), G(x,y) is the color component of the G channel of the pixel (x,y), and B(x,y) is the pixel (x,y) The color components of the B channel, k ₁ , k ₂ and k ₃ are all constants.

Further, the medical image evaluation device further includes:

The third acquisition module is used to acquire the hospital identification information corresponding to the medical image from the preset database;

The matching module is used to determine and evaluate users by matching the hospital identification information with the identification information in the user database.

Further, the calculation module 65 includes:

The comprehensive score calculation sub-module is used to calculate the comprehensive score corresponding to the medical image according to formula (2):

Among them, X is the comprehensive score, w _n is the target evaluation result fed back by the nth evaluation user, f _n is the preset weight coefficient of the nth evaluation user, and n is a constant.

Further, the medical image evaluation device further includes:

The confirmation module is used to perform quality assessment on the medical equipment corresponding to the medical image according to the evaluation result, determine the medical equipment with unqualified quality, and send the medical equipment information corresponding to the medical image to the target user for confirmation.

Some embodiments of the application disclose computer equipment. For details, please refer to FIG. 7, which is a block diagram of the basic structure of the computer device 90 in an embodiment of the present application.

As shown in FIG. 7, the computer device 90 includes a memory 91, a processor 92, and a network interface 93 that are communicatively connected to each other through a system bus. It should be pointed out that FIG. 7 only shows a computer device 90 with components 91-93, but it should be understood that it is not required to implement all of the illustrated components, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes but is not limited to microprocessors, dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Programmable Gate Array (Field-Programmable Gate Array, FPGA), Digital Processor (Digital Signal Processor, DSP), embedded devices, etc.

The computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.

The memory 91 includes at least one type of readable storage medium, the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static memory Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, the memory 91 may be an internal storage unit of the computer device 90, such as a hard disk or memory of the computer device 90. In other embodiments, the memory 91 may also be an external storage device of the computer device 90, such as a plug-in hard disk equipped on the computer device 90, a smart memory card (Smart Media Card, SMC), and a secure digital (Secure Digital, SD) card, Flash Card, etc. Of course, the memory 91 may also include both the internal storage unit of the computer device 90 and its external storage device. In this embodiment, the memory 91 is generally used to store an operating system and various application software installed in the computer device 90, such as computer readable instructions of the medical image evaluation method. In addition, the memory 91 can also be used to temporarily store various types of data that have been output or will be output.

The processor 92 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 92 is generally used to control the overall operation of the computer device 90. In this embodiment, the processor 92 is configured to run computer-readable instructions or processed data stored in the memory 91, for example, computer-readable instructions for running the medical image evaluation method.

The network interface 93 may include a wireless network interface or a wired network interface, and the network interface 93 is generally used to establish a communication connection between the computer device 90 and other electronic devices.

This application also provides another implementation manner, that is, to provide a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores the medical imaging data information entry process, the medical The image data information entry process can be executed by at least one processor, so that the at least one processor executes the steps of any one of the aforementioned medical image evaluation methods.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a computer device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

Finally, it should be noted that, obviously, the embodiments described above are only a part of the embodiments of this application, not all of them. The drawings show the preferred embodiments of this application, but do not limit the patents of this application. range. This application can be implemented in many different forms. On the contrary, the purpose of providing these examples is to make the understanding of the disclosure of this application more thorough and comprehensive. Although this application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it is still possible for those skilled in the art to modify the technical solutions described in each of the foregoing specific implementations, or equivalently replace some of the technical features. . All equivalent structures made using the contents of the description and drawings of this application, directly or indirectly used in other related technical fields, are similarly within the scope of patent protection of this application.

Claims (20)

1. A medical image evaluation method, characterized in that the medical image evaluation method includes:

   Obtain medical images to be evaluated;

   Preprocessing the medical image to obtain a binary image;

   The binarized image is scored according to the metal artifact score item in a preset score library to obtain a metal artifact score result, wherein the preset score library includes the basic score item corresponding to the medical image and the Metal artifact score item;

   Sending the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

   Receiving the target scoring result fed back by the evaluating user, combining with the preset weight coefficient of the evaluating user, calculating and outputting a comprehensive score corresponding to the medical image;

   The comprehensive score is compared with a preset threshold range to determine the level of the comprehensive score and output as an evaluation result.
2. The medical image evaluation method of claim 1, wherein the step of obtaining the medical image to be evaluated comprises:

   According to the preset filming type, obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table;

   Multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections;

   Use the total number of quality control inspections and the preset base to calculate the remainder to obtain the monthly target quality control quantity;

   Acquire the medical images to be evaluated for the target quality control quantity from an image database.
3. The medical image evaluation method of claim 1, wherein the step of preprocessing the medical image to obtain a binary image comprises:

   Performing gray-scale processing on the medical image to obtain a gray-scale image;

   Scanning each pixel in the grayscale image;

   If the pixel value of the pixel is less than the pixel threshold of the metal artifact, then the pixel value of the pixel is set to 0;

   If the pixel value of the pixel point is greater than or equal to the pixel threshold value of the metal artifact, then the pixel value of the pixel point is set to 255;

   The grayscale image is converted into the binarized image.
4. The medical image evaluation method according to claim 3, wherein the step of performing grayscale processing on the medical image to obtain a grayscale image comprises:

   Traverse the pixels in the medical image to obtain the RGB component value of each pixel;

   According to the RGB component values of the pixels, the medical image is grayed out according to the following formula:

   g(x,y)=k ₁ *R(x,y)+k ₂ *G(x,y)+k ₃ *B(x,y)

   Where x and y are the abscissa and ordinate of each pixel in the medical image, g(x,y) is the gray value of the pixel (x,y) after grayscale processing, R(x,y) is the color component of the R channel of the pixel (x,y), G(x,y) is the color component of the G channel of the pixel (x,y), B(x, y) is the color component of the B channel of the pixel (x, y), and k ₁ , k ₂ and k ₃ are all constants.
5. The medical image evaluation method according to claim 1, wherein after the step of scoring the binarized image according to a scoring standard in a preset scoring library to obtain an initial scoring result, the Before the step of sending the medical image, the scoring criteria corresponding to the medical image, and the initial scoring result to the evaluation user for user scoring, the medical image evaluation method further includes:

   Acquiring the hospital identification information corresponding to the medical image from a preset database;

   The evaluation user is determined by matching the hospital identification information with the identification information in the user database.
6. The medical image evaluation method according to claim 1, wherein said receiving the target scoring result fed back by the evaluation user, combined with the preset weight coefficient of the evaluation user, calculates and outputs the comprehensive corresponding to the medical image The scoring steps include:

   Calculate the comprehensive score corresponding to the medical image according to the following formula:

   

   Where X is the comprehensive score, w _n is the target evaluation result fed back by the n-th evaluation user, f _n is a preset weight coefficient of the n-th evaluation user, and n is a constant.
7. The medical image evaluation method according to claim 1, wherein after the step of comparing the comprehensive score with a preset threshold range to determine the level of the comprehensive score, and outputting as the evaluation result, the medical Image evaluation methods also include:

   According to the evaluation result, the quality of the medical equipment corresponding to the medical image is assessed, the medical equipment with unqualified quality is determined, and the medical equipment information corresponding to the medical image is sent to the target user for confirmation.
8. A medical image evaluation device, characterized in that, the medical image evaluation device comprises:

   The first acquisition module is used to acquire the medical image to be evaluated;

   The preprocessing module is used to preprocess the medical image to obtain a binary image;

   The automatic scoring module is used for scoring the binarized image according to the metal artifact scoring items in the preset scoring library to obtain the metal artifact scoring result, wherein the preset scoring library includes the corresponding medical image The basic scoring item and the metal artifact scoring item;

   The user scoring module is configured to send the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

   A calculation module, configured to receive the target scoring result fed back by the evaluation user, and combine the predetermined weight coefficient of the evaluation user to calculate and output a comprehensive score corresponding to the medical image;

   The output module is used to compare the comprehensive score with a preset threshold range, determine the level of the comprehensive score, and output it as an evaluation result.
9. The medical image evaluation device according to claim 8, wherein the first acquisition module comprises:

   The total acquisition sub-module is used to obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table according to the preset filming type;

   The multiplication sub-module is used to multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections;

   The remainder seeking sub-module is used to calculate the remainder by using the total number of quality control inspections and the preset base number to obtain the target quality control quantity for each month;

   The second acquisition sub-module is used to acquire the medical images to be evaluated of the target quality control quantity from an image database.
10. 9. The medical image evaluation device of claim 8, wherein the preprocessing module comprises:

    The gray-scale sub-module is used to perform gray-scale processing on the medical image to obtain a gray-scale image;

    A scanning sub-module for scanning each pixel in the grayscale image;

    The first comparison sub-module is configured to set the pixel value of the pixel point to 0 if the pixel value of the pixel point is less than the pixel threshold value of the metal artifact;

    The second comparison sub-module is configured to set the pixel value of the pixel to 255 if the pixel value of the pixel is greater than or equal to the pixel threshold of the metal artifact;

    The conversion sub-module is used to convert the grayscale image into the binary image.
11. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and capable of running on the processor, wherein the processor executes the computer-readable instructions as follows step:

    Obtain medical images to be evaluated;

    Preprocessing the medical image to obtain a binary image;

    The binarized image is scored according to the metal artifact score item in a preset score library to obtain a metal artifact score result, wherein the preset score library includes the basic score item corresponding to the medical image and the Metal artifact score item;

    Sending the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

    Receiving the target scoring result fed back by the evaluating user, combining with the preset weight coefficient of the evaluating user, calculating and outputting a comprehensive score corresponding to the medical image;

    The comprehensive score is compared with a preset threshold range to determine the level of the comprehensive score and output as an evaluation result.
12. The computer device according to claim 11, wherein the step of obtaining the medical image to be evaluated comprises:

    According to the preset filming type, obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table;

    Multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections;

    Use the total number of quality control inspections and the preset base to calculate the remainder to obtain the target quality control quantity for each month;

    Acquire the medical images to be evaluated for the target quality control quantity from an image database.
13. The computer device of claim 11, wherein the step of preprocessing the medical image to obtain a binary image comprises:

    Performing gray-scale processing on the medical image to obtain a gray-scale image;

    Scanning each pixel in the grayscale image;

    If the pixel value of the pixel is less than the pixel threshold of the metal artifact, then the pixel value of the pixel is set to 0;

    If the pixel value of the pixel point is greater than or equal to the pixel threshold value of the metal artifact, then the pixel value of the pixel point is set to 255;

    The grayscale image is converted into the binarized image.
14. The computer device of claim 13, wherein the step of performing gray-scale processing on the medical image to obtain a gray-scale image comprises:

    Traverse the pixels in the medical image to obtain the RGB component value of each pixel;

    According to the RGB component values of the pixels, the medical image is grayed out according to the following formula:

    g(x,y)=k ₁ *R(x,y)+k ₂ *G(x,y)+k ₃ *B(x,y)

    Wherein, x and y are the abscissa and ordinate of each pixel in the medical image, g(x,y) is the gray value of the pixel (x,y) after grayscale processing, R(x,y) is the color component of the R channel of the pixel (x,y), G(x,y) is the color component of the G channel of the pixel (x,y), B(x, y) is the color component of the B channel of the pixel (x, y), and k ₁ , k ₂ and k ₃ are all constants.
15. The computer device according to claim 11, wherein after the step of scoring the binarized image according to the scoring criteria in a preset scoring library to obtain an initial scoring result, the medical image Before the step of sending the scoring standard corresponding to the medical image and the initial scoring result to the evaluation user for user scoring, the processor executes the computer-readable instruction further including the following steps:

    Acquiring the hospital identification information corresponding to the medical image from a preset database;

    The evaluation user is determined by matching the hospital identification information with the identification information in the user database.
16. A non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores computer-readable instructions, wherein the computer-readable instructions when executed by a processor cause The processor executes the following steps:

    Obtain medical images to be evaluated;

    Preprocessing the medical image to obtain a binary image;

    The binarized image is scored according to the metal artifact score item in a preset score library to obtain a metal artifact score result, wherein the preset score library includes the basic score item corresponding to the medical image and the Metal artifact score item;

    Sending the medical image, the basic scoring item corresponding to the medical image, the metal artifact scoring item, and the metal artifact scoring result to at least two evaluation users for user scoring;

    Receiving the target scoring result fed back by the evaluating user, combining with the preset weight coefficient of the evaluating user, calculating and outputting a comprehensive score corresponding to the medical image;

    The comprehensive score is compared with a preset threshold range to determine the level of the comprehensive score and output as an evaluation result.
17. The non-volatile computer-readable storage medium of claim 16, wherein the step of obtaining the medical image to be evaluated comprises:

    According to the preset filming type, obtain the total number of examinations of medical images corresponding to the preset filming type in the preset month from the preset data table;

    Multiply the total number of inspections by the quality control coefficient to obtain the total number of quality control inspections;

    Use the total number of quality control inspections and the preset base to calculate the remainder to obtain the monthly target quality control quantity;

    Acquire the medical images to be evaluated for the target quality control quantity from an image database.
18. The non-volatile computer-readable storage medium according to claim 16, wherein the step of preprocessing the medical image to obtain a binary image comprises:

    Performing gray-scale processing on the medical image to obtain a gray-scale image;

    Scanning each pixel in the grayscale image;

    If the pixel value of the pixel is less than the pixel threshold of the metal artifact, then the pixel value of the pixel is set to 0;

    If the pixel value of the pixel point is greater than or equal to the pixel threshold value of the metal artifact, then the pixel value of the pixel point is set to 255;

    The grayscale image is converted into the binarized image.
19. The non-volatile computer-readable storage medium according to claim 18, wherein the step of performing gray-scale processing on the medical image to obtain a gray-scale image comprises:

    Traverse the pixels in the medical image to obtain the RGB component value of each pixel;

    According to the RGB component values of the pixels, the medical image is grayed out according to the following formula:

    g(x,y)=k ₁ *R(x,y)+k ₂ *G(x,y)+k ₃ *B(x,y)

    Wherein, x and y are the abscissa and ordinate of each pixel in the medical image, g(x,y) is the gray value of the pixel (x,y) after grayscale processing, R(x,y) is the color component of the R channel of the pixel (x,y), G(x,y) is the color component of the G channel of the pixel (x,y), B(x, y) is the color component of the B channel of the pixel (x, y), and k ₁ , k ₂ and k ₃ are all constants.
20. The non-volatile computer-readable storage medium of claim 16, wherein the binarized image is scored according to the scoring criteria in the preset scoring library, and after the step of obtaining the initial scoring result Before the step of sending the medical image, the scoring criteria corresponding to the medical image, and the initial scoring result to the evaluation user for user scoring, when the computer-readable instructions are executed by a processor, The aforementioned processor also executes the following steps:

    Acquiring the hospital identification information corresponding to the medical image from a preset database;

    The evaluation user is determined by matching the hospital identification information with the identification information in the user database.

Images