CN116012324A

CN116012324A - Medical image quality control method and device and electronic device

Info

Publication number: CN116012324A
Application number: CN202211681232.9A
Authority: CN
Inventors: 周奇明; 杜立辉; 姚卫忠
Original assignee: Zhejiang Huanuokang Technology Co ltd
Current assignee: Zhejiang Huanuokang Technology Co ltd
Priority date: 2022-12-27
Filing date: 2022-12-27
Publication date: 2023-04-25

Abstract

The application relates to a medical image quality control method, a medical image quality control device and an electronic device. The medical image quality control method comprises the following steps: acquiring medical images acquired by an endoscope; identifying a target part in the medical image by using the first network model, and generating a first identification result of the target part; evaluating the image quality of the medical image; identifying a target part in the medical image by using the second network model, and generating a second identification result of the target part; and generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image. According to the method and the device, the problem that high-quality images are difficult to obtain from massive image data in the related technology is solved, and the quality of the output medical images is guaranteed.

Description

Medical image quality control method and device and electronic device

Technical Field

The present disclosure relates to the field of medical data processing technologies, and in particular, to a medical image quality control method, device and electronic device.

Background

With the development of medical technology, the variety of medical devices is becoming more and more popular. The scanning technology of different medical equipment is also various, and different medical images can be obtained by different scanning technologies and imaging modes, so that massive image data are generated. Meanwhile, for image diagnosis, the quality is the sum of properties of the image itself or the property of the examination itself, which determines whether clinical diagnosis can be satisfied or not, which is the subject of evaluation. The quality of the image affects the diagnostic value of the doctor. Therefore, obtaining a high-quality image from a large amount of image data is a problem to be solved.

At present, no effective solution is proposed for the problem of acquiring high-quality images from massive image data.

Disclosure of Invention

The embodiment of the application provides a medical image quality control method, a medical image quality control device and an electronic device, which are used for at least solving the problem that messy codes exist in audit data in the related technology.

In a first aspect, an embodiment of the present application provides a medical image quality control method, which is characterized in that the method includes:

acquiring medical images acquired by an endoscope;

identifying a target part in the medical image by using a first network model, and generating a first identification result of the target part;

performing image quality evaluation on the medical image;

identifying a target part in the medical image by using a second network model, and generating a second identification result of the target part;

and generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image.

In some of these embodiments, the method further comprises:

and carrying out image analysis on the target image to generate an analysis report of the target part.

In some embodiments, the identifying a target site in the medical image using the first network model, generating a first identification of the target site includes:

inputting the medical image into a detection network to obtain detection areas of N anatomical marks;

sending the images corresponding to the detection areas of the N anatomical landmarks into a classification network to obtain a third recognition result of the target part; wherein N is a positive integer;

inputting the medical image into a segmentation network to obtain segmentation areas of M anatomical marks;

inputting the segmented regions of the M anatomical landmarks into a retrieval network to obtain a fourth recognition result of the target part; wherein M is a positive integer;

and generating a first identification result of the target part according to the third identification result and the fourth identification result.

In some of these embodiments, the performing an image quality assessment on the medical image comprises:

and respectively carrying out noise detection, definition detection, brightness detection and color detection on the medical image, and evaluating the image quality of the medical image according to a detection result.

In some of these embodiments, the method further comprises: and obtaining the angle information of the endoscope and the speed information of the endoscope by using the second network model.

In some embodiments, the identifying a target site in the medical image using a second network model, the generating a second identification of the target site includes:

performing feature extraction on the medical image by utilizing a pre-trained space-time feature extraction network;

and obtaining a second identification result of the target part according to the extracted characteristics.

In some embodiments, the generating a target image for the medical image quality control based on the first identification result of the target region, the image quality evaluation result, and the second identification result of the target region includes:

determining a final recognition result of the target part according to the first recognition result of the target part and the second recognition result of the target part;

and generating a target image according to the final identification result and the image quality evaluation result so as to control the medical image.

In a second aspect, an embodiment of the present application further provides a medical image quality control apparatus, including:

the device comprises:

the medical image acquisition module is used for acquiring medical images acquired by the endoscope;

the first part identification module is used for identifying a target part in the medical image by using a first network model and generating a first identification result of the target part;

the image quality analysis module is used for evaluating the image quality of the medical image;

the second part identification module is used for identifying a target part in the medical image by using a second network model and generating a second identification result of the target part;

and the target image acquisition module is used for generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image.

In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the medical image quality control method according to the first aspect when executing the computer program.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored thereon, which when executed by a processor implements the medical image quality control method according to the first aspect described above.

Compared with the related art, the medical image quality control method, the device and the electronic device provided by the embodiment of the application acquire medical images acquired by the endoscope; identifying a target part in the medical image by using the first network model, and generating a first identification result of the target part; evaluating the image quality of the medical image; identifying a target part in the medical image by using the second network model, and generating a second identification result of the target part; and generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image. The method solves the problem that the high-quality image is difficult to acquire from massive image data in the related technology, and ensures the quality of the output medical image. The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

FIG. 1 is a block diagram of hardware architecture for performing a medical image quality control method according to an embodiment of the present application;

FIG. 2 is a flow chart of a medical image quality control method according to an embodiment of the present application;

FIG. 3 is a flow chart of a medical image quality control method according to a preferred embodiment of the present application;

fig. 4 is a block diagram of a medical image quality control apparatus according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described and illustrated below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present application, are within the scope of the present application based on the embodiments provided herein.

It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the embodiments described herein can be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar terms herein do not denote a limitation of quantity, but rather denote the singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein refers to two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.

The method embodiment provided in this embodiment may be executed in a terminal, a computer or a similar computing device. Taking the operation on the terminal as an example, fig. 1 is a block diagram of the hardware structure of the terminal for executing a medical image quality control method according to an embodiment of the present application. As shown in fig. 1, the terminal may include one or more processors 102 (only one is shown in fig. 1) (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting on the structure of the terminal described above. For example, the terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for generating audit data in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104, thereby performing various functional applications and data processing, that is, implementing the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. The specific example of the network described above may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

The embodiment also provides a medical image quality control method. Fig. 2 is a flowchart of a medical image quality control method according to an embodiment of the present application, as shown in fig. 2, the flowchart includes the following steps:

step S202, acquiring medical images acquired by an endoscope.

Specifically, the terminal may acquire medical image data from the PACS system (Picture Archiving and Communication Systems, image archiving and communication system), or may receive medical image data generated in real time by the medical device or medical image data uploaded by the user in real time. The medical image data in the PACS system are data stored in a digital mode through various interfaces of various medical images generated in daily life. For example, medical images generated by medical equipment such as nuclear magnetism, magnetic resonance, CT (Computed Tomography ), ultrasound, various X-ray machines, various infrared instruments, microscopes and the like are digitally stored through corresponding interfaces.

The endoscope PACS system applies an advanced digital processing technology to the field of endoscopes, integrates high-definition acquisition, processing, video recording, diagnosis and editing, image-text printing, medical record management, statistical analysis, clinical browsing, case ordering, teaching, quality control and remote rebroadcasting (high-resolution full-digital dynamic real-time network transmission under ERCP radiography is also realized), and is organically combined with a hospital HIS and other department PACS systems to promote informatization and digital construction of an endoscope room, and the contained management concept and collaborative management mode are really worth of users.

Step S204, a target part in the medical image is identified by using the first network model, and a first identification result of the target part is generated.

Specifically, the first network model is an identification model, and the identification of the target part is performed on the current medical image by pre-establishing the identification model, so as to generate a first identification result of the target part. The recognition model is a model which is obtained by training a large number of medical image data samples in advance, and the trained recognition model is used for recognizing a target part of medical image data. The recognition model includes, but is not limited to, any one or more of a decision tree model, a logistic regression model, a neural network model, and a support vector machine model.

Step S206, evaluating the image quality of the medical image.

Specifically, the image quality evaluation of the medical image includes noise evaluation, brightness evaluation, sharpness evaluation, and color evaluation, respectively. And 4 different feature extraction networks are used for extracting features of the medical image respectively, and finally, the obtained results of the 4 classification networks are comprehensively processed to obtain the comprehensive score of the image quality, so that the influence among the extraction processes of different image features in the training and using processes is reduced.

Further, the noise evaluation comprises conducting guided filtering on the medical image to obtain a denoised blurred image, and extracting noise information of the image to conduct noise evaluation through subtraction operation on the denoised blurred image and an input image; the brightness evaluation comprises calculating the mean value and variance of the picture on the gray scale, when brightness abnormality exists, the mean value deviates from the mean point (128 can be assumed), and the variance is also smaller; by calculating the mean and variance of the gray scale image, whether the image is overexposed or underexposed can be estimated; the definition evaluation comprises the steps of calculating a second derivative of the picture by using a Laplacian, reflecting edge information of the picture, and enabling the picture with the same things to have high definition and the variance of the corresponding picture after being filtered by the Laplacian to be larger; color estimation involves converting an RGB image into CIE Lab space, where L represents image brightness, a represents image red/green components, b represents image yellow/blue components, and color estimation of a medical image is performed by calculating the mean and variance of the image over the a and b components.

Step S208, the target part in the medical image is identified by using the second network model, and a second identification result of the target part is generated.

Specifically, the second network model is a space-time feature extraction network model, and the feature extraction is carried out on the medical image by utilizing the pre-trained space-time feature extraction network model;

Step S210, generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part, so as to control the quality of the medical image.

Specifically, the first recognition result of the target part generated in step S204, the result of the quality scoring of the medical image in step S206, and the second recognition result of the target part obtained in step S208 are comprehensively analyzed, the medical image of the current key part is preferably processed, and the optimal medical picture in the currently acquired medical image is output in real time.

Based on the steps S202 to S210, acquiring medical images acquired by an endoscope; identifying a target part in the medical image by using the first network model, and generating a first identification result of the target part; evaluating the image quality of the medical image; identifying a target part in the medical image by using the second network model, and generating a second identification result of the target part; and generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image, solving the problem that the high-quality image is difficult to acquire from massive image data in the related technology, and ensuring the quality of the output medical image.

In some of these embodiments, the method further includes performing an image analysis of the target image to generate an analysis report of the target site.

Specifically, health analysis is performed on the target image output by each target part of the current patient, so as to obtain an analysis report of the target part of the patient.

In some of these embodiments, identifying the target site in the medical image using the first network model, generating the first identification of the target site includes:

sending the images corresponding to the detection areas of the N anatomical landmarks into a classification network to obtain a third identification result of the target part; wherein N is a positive integer;

In some of these embodiments, image quality assessment of the medical image includes:

and respectively carrying out noise detection, definition detection, brightness detection and color detection on the medical image, and evaluating the image quality of the medical image according to the detection result.

In some of these embodiments, the method further comprises: and obtaining the angle information of the endoscope and the speed information of the endoscope by using a second network model.

Specifically, a pre-trained space-time feature extraction network is utilized to extract features of the medical image; and obtaining the angle information of the endoscope and the speed information of the endoscope according to the extracted characteristics.

Further, key features (such as a center point, a boundary point and the like of the nasopharynx) are extracted from the medical image through a space-time feature extraction model, feature offset of a previous frame image and a current frame image is obtained through matching with the feature points of the previous frame image, and current endoscope speed, angle information of an endoscope and the like are obtained.

In some of these embodiments, identifying the target site in the medical image using the second network model, generating the second identification of the target site includes:

In some embodiments, generating the target image for medical image quality control based on the first identification result of the target region, the image quality assessment result, and the second identification result of the target region includes:

Specifically, the second identification result of the target portion is obtained through step S208, the output results of step S204, step S206 and step S208 are comprehensively analyzed to obtain the key portion to which the current image belongs, then each key portion is preferably processed, and the optimal picture in the current acquired medical image picture is output in real time.

The embodiments of the present application are described and illustrated below by means of preferred embodiments.

Fig. 3 is a flowchart of a medical image quality control method according to a preferred embodiment of the present application. As shown in fig. 3, the preferred step flow includes the steps of:

step S302, obtaining an endoscopic image.

Step S304, identify the key position in the endoscope image.

Specifically, by establishing 4 deep learning networks: a detection network, a classification network, a segmentation network and a retrieval network; dividing 4 deep learning networks into two branches, wherein one branch is a detection network and a classification network; the other branch is a splitting network and a retrieving network. Firstly, a first branch sends an endoscopic image to a detection network to obtain detection areas of n anatomical marks of the image, then sends original pictures corresponding to the anatomical marks of the n images to a class network, and judges key parts to which the image belongs;

/>

wherein, the liquid crystal display device comprises a liquid crystal display device,

to detect the network, x _i For the input ith image data, +.>

For N detection results, N is 0,1,2 …, N.

for classifying networks, +.>

Adjusting the n anatomical landmark images to the same size by means of resize, y _oc And outputting the result for the classification network.

Then, the other branch sends the endoscopic image to a segmentation network to obtain m segmentation areas of anatomical marks corresponding to the image, and sends the m segmentation areas to a retrieval network to obtain the key parts of the image;

to split the network, x _i For the input ith image data, +.>

For M segmentation results, M ε 0,1,2 …, M.

to retrieve a network; />

In original image x _i Reserving an mth divided area, and filling the rest areas with white; y is _fmoc The result is output for the retrieval network.

Finally, combining the results of the formula (b) and the formula (d), if the result output by the classification network is equal to the result output by the search network, determining the key part as the result output by the classification network, otherwise, outputting the result of the uncertain current key part.

Step S306, the quality of the endoscopic image is analyzed.

Specifically, the image quality analysis mainly consists of 4 parts, namely noise detection, brightness detection, definition detection and color detection. The network structure of each model deep classification network is the same. Finally, comprehensively processing the obtained results of the 4 classification networks to obtainImage quality composite score y _iqa 。

y _α ＝γ _α (x _i )， (f)

Wherein, gamma _α (x _i ) For 4 classified networks, alpha E [ noise, bright, clear, color ]]Representing noise, brightness, sharpness, color classification network, respectively.

Wherein y is _iqa The score is integrated for image quality.

Step S308, analyzing the state of the endoscope through the endoscope image.

Specifically, the state of the endoscope includes speed information, angle information, and the like of the endoscope. A neural network model formed by a convolution long-short-term memory network (ConvLSTM) is established and is used for acquiring characteristic points, key parts and endoscope angles of an endoscope image, wherein the image can acquire the current endoscope speed by matching with the characteristic points of the image of the previous frame.

ES _point ,ES _kp ,ES _angle ＝CONVLSTM(x _i ), (h)

Wherein CONVLSTM (x _i ) ES is a convolutional long-short-term memory network _point For image feature point results, ES _kp As the current key part result, ES _angle Is the endoscope angle result.

ES _speed ＝∑diff(ES _point ,ES′ _point )， (i)

Wherein diff (ES _point ,ES′ _point ) For the characteristic offset of the previous frame image and the current frame image, ES _speed Is the endoscope speed.

Step S310, the key parts of the endoscope image are subjected to optimization processing, and the optimal picture in the current acquired picture is output in real time.

Specifically, the output results of step S304, step S306, and step S308 are comprehensively analyzed to obtain the key part y to which the current image belongs _ketpart 。

If the result of the key location output in step S304 is equal to the result of the key location output in step S308, it is determined that the key location to which the current image belongs is the result of the key location output in step S304, otherwise, it is not determined that the key location to which the current image belongs.

Then each key part is subjected to optimization processing, the optimal picture in the current acquired picture can be output in real time,

and if the image quality comprehensive score is greater than or equal to the set threshold thres, determining that the current image quality is qualified, otherwise, determining that the current picture is unqualified.

Finally, outputting the key part y _ketpart Angle ES corresponding to picture _angle And can output the angle ES of the endoscope in real time _angle Sum speed ES _speed Information. When the endoscopy is finished, a detection report with image information of each key part can also be automatically generated.

In the above step, the optimal picture information of each key part can be selected in combination with the optimal policy, and the detection report can be automatically generated.

Based on the embodiment, the application provides a more accurate, reliable and active self-adaptive method, solves the problems that by combining a deep learning method with a preferred strategy, optimal picture information of each part can be selected, the quality of a current endoscope image is analyzed in real time, and a detection report is automatically generated.

The embodiment also provides a medical image quality control device, which is used for implementing the above embodiment and the preferred implementation, and is not described in detail. As used below, the terms "module," "unit," "sub-unit," and the like may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 4 is a block diagram of a medical image quality control apparatus according to an embodiment of the present application, as shown in fig. 4, the apparatus includes:

a medical image acquisition module 41 for acquiring a medical image acquired by an endoscope;

a first part identifying module 42, configured to identify a target part in the medical image by using the first network model, and generate a first identification result of the target part;

an image quality analysis module 43 for performing image quality evaluation on the medical image;

a second part identifying module 44, configured to identify a target part in the medical image by using the second network model, and generate a second identification result of the target part;

the target image obtaining module 45 is configured to generate a target image according to the first identification result of the target portion, the image quality evaluation result, and the second identification result of the target portion, so as to perform medical image quality control.

The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.

There is also provided in this embodiment an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the above-described embodiments of the medical image quality control method.

Optionally, the intelligent terminal may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.

Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:

s1, acquiring medical images acquired by an endoscope.

S2, identifying a target part in the medical image by using the first network model, and generating a first identification result of the target part.

And S3, evaluating the image quality of the medical image.

S4, identifying a target part in the medical image by using the second network model, and generating a second identification result of the target part;

s5, generating a target image according to the first identification result of the target part, the image quality evaluation result and the second identification result of the target part so as to control the quality of the medical image.

It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and are not described in detail in this embodiment.

In addition, in combination with the medical image quality control method in the above embodiment, the embodiment of the application may be implemented by providing a computer readable storage medium. The computer readable storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the medical image quality control methods of the above embodiments.

The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A medical image quality control method, the method comprising:

acquiring medical images acquired by an endoscope;

performing image quality evaluation on the medical image;

2. The medical image quality control method according to claim 1, wherein the method further comprises:

3. The medical image quality control method according to claim 1, wherein the identifying a target site in the medical image using the first network model, generating a first identification result of the target site includes:

4. The medical image quality control method according to claim 1, wherein the performing image quality evaluation on the medical image includes:

5. The medical image quality control method according to claim 1, wherein the method further comprises: and obtaining the angle information of the endoscope and the speed information of the endoscope by using the second network model.

6. The medical image quality control method according to claim 1, wherein the identifying a target site in the medical image using the second network model, generating a second identification result of the target site includes:

7. The medical image quality control method according to claim 1, wherein the generating a target image based on the first recognition result of the target region, the image quality evaluation result, and the second recognition result of the target region to perform the medical image quality control comprises:

8. A medical image quality control apparatus, the apparatus comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements the medical image quality control method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having stored thereon a computer program, wherein the program is executed by a processor to implement the steps of the medical image quality control method according to any one of claims 1 to 7.