A method, device and computer storage medium for analyzing and controlling medical imaging quality

Abstract

The present invention discloses a method, device and computer storage medium for analyzing and controlling image medical quality. The method includes: obtaining basic information corresponding to the patient currently undergoing CT image scanning in the target department; obtaining the corresponding CT image taken by the patient, and performing preliminary analysis to extract the scanning parameters and acquisition parameters corresponding to the CT image; collecting the baseline parameters of the CT image; building a CT image quality analysis model based on the collected information; performing preliminary analysis and in-depth analysis on the quality corresponding to the CT image; the present invention effectively solves the problem that the current technology has obvious limitations in the analysis of medical image quality by collecting and analyzing the image quality parameters of the CT images taken by the patient in multiple dimensions, improves the accuracy of the quality analysis of the CT images taken by the patient, and thus greatly reduces the misjudgment rate of the doctor in diagnosing the patient's condition.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical imaging quality, and relates to a medical imaging quality analysis and control method, equipment and a computer storage medium. Background Art

[0002] With the rapid development of electronic technology and the steady improvement of computer technology, medical imaging technology has become increasingly mature. Imaging equipment such as CT, MRI, and PET have been continuously updated and widely used in clinical practice, providing an important window for doctors to observe changes in the morphology and function of internal organs and tissues of the human body.

[0003] The quality of medical images taken by CT imaging equipment directly affects the doctor's analysis of the patient's condition to a certain extent, and further determines the doctor's diagnosis and treatment effect on the patient's condition. It can be seen that it is very important to analyze the quality of images. The current quality analysis of medical images taken by patients mainly focuses on the analysis of the quality of medical imaging equipment used to take patients. Obviously, although the quality of medical imaging equipment reflects the quality of medical images to a certain extent, there are many imaging factors in the quality of medical images, such as the operator's shooting technology problems and subsequent image processing problems. Therefore, the current analysis of medical image quality has obvious limitations, and it is impossible to improve the accuracy of medical image quality analysis, and thus it is impossible to effectively reduce the doctor's misdiagnosis rate of the patient's condition. At the same time, the current analysis of medical image quality belongs to a single-dimensional quality analysis, which cannot ensure that the medical images taken by patients can reflect the true situation of the patient's condition to the greatest extent, and thus it is impossible to improve the doctor's pertinence in diagnosing and treating the patient's condition, and to a certain extent it is impossible to improve the efficiency and effect of diagnosis and treatment of the patient's condition. Summary of the invention

[0004] In view of this, in order to solve the problems raised in the above background technology, a method, device and computer storage medium for analyzing and controlling the quality of CT medical images are proposed, which realizes accurate analysis and efficient processing of the quality of CT images taken by patients;

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A first aspect of the present invention provides a method for analyzing and controlling the quality of medical imaging, the method comprising the following steps:

[0007] Step 1: Obtaining basic patient information: Obtain the electronic medical records corresponding to the patient currently undergoing CT imaging scans in the target department, and extract the basic information corresponding to the patient from the electronic medical records, wherein the basic information corresponding to the patient specifically includes the preset detection site and the preset detection lesion type corresponding to the patient;

[0008] Step 2: CT image extraction and preliminary analysis: After the patient has completed CT image shooting, the CT image corresponding to the patient is obtained, and based on the CT image corresponding to the patient, the scanning parameters and acquisition parameters corresponding to the CT image are extracted;

[0009] Step 3: CT image benchmark parameter acquisition: Based on the acquisition parameters corresponding to the CT image, the number of scanning layers corresponding to the CT image is extracted, and then the CT image is divided into layers, and each layer region is numbered 1, 2, ...i, ...n in sequence. The image displayed in each layer region is imported into the image benchmark parameter extraction model, and the benchmark parameters corresponding to the image displayed in each layer region are extracted;

[0010] Step 4: Build a CT image quality analysis model: Build a CT image quality analysis model based on the basic information corresponding to the patient, the scanning parameters and acquisition parameters corresponding to the CT image, and the benchmark parameters corresponding to the displayed image in each layer area;

[0011] Step 5: Preliminary analysis of CT image quality: Substitute the scanning parameters, acquisition parameters and reference parameters corresponding to the displayed image in each layer area of ​​the CT image into the CT image quality analysis model, conduct a preliminary analysis of the CT image quality, and obtain a comprehensive quality index corresponding to the CT image;

[0012] Step 6: In-depth analysis of CT image quality: based on the comprehensive quality index corresponding to the CT image, the comprehensive quality index corresponding to the CT image is compared with the preset standard quality index corresponding to the CT image. If the comprehensive quality index corresponding to the CT image is less than the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of unqualified quality, and the unqualified quality image is analyzed. If the comprehensive quality index corresponding to the CT image is greater than or equal to the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of qualified quality.

[0013] Step 7. Feedback of CT image quality analysis results: When the CT image is of unqualified quality, the quality abnormality factors corresponding to the unqualified image and the corresponding treatment measures for each quality abnormality factor are sent to the equipment control manager of the target department for image acquisition control.

[0014] Preferably, the scanning parameters corresponding to the CT image specifically include the tube voltage, tube current, exposure time and shooting orientation parameters corresponding to the CT image; the acquisition parameters corresponding to the CT image specifically include the number of scanning slices corresponding to the CT image and the thickness corresponding to each scanning slice of the CT image, wherein the shooting orientation parameters corresponding to the CT image are the shooting inclination angle, shooting window width and shooting window position.

[0015] Preferably, the benchmark parameters corresponding to the displayed images in each layer area are specifically represented by the noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the displayed images in each layer area, wherein the artifact parameters include artifact status and artifact type, and the artifact type includes equipment artifacts, metal artifacts and personnel motion artifacts.

[0016] Preferably, the specific construction process of the CT image quality analysis model includes the following steps:

[0017] Extracting the preset detection part and the preset detection lesion type corresponding to the patient from the basic information corresponding to the patient, and based on the preset detection part and the preset lesion type corresponding to the patient, extracting various standard scanning parameters and various standard acquisition parameters corresponding to the patient from the image detection database;

[0018] The standard scanning parameters corresponding to the patient are used as the first image-assisted quality factor, and the standard acquisition parameters corresponding to the patient are used as the second image-assisted quality factor. At the same time, the standard benchmark parameters corresponding to the CT image are extracted from the image detection database, and the standard benchmark parameters corresponding to the CT image are used as the main image quality factor. According to the first image-assisted quality factor and the second image-assisted quality factor, an image quality auxiliary analysis model is constructed, and the main image quality analysis model is constructed with the main image quality factors. The main image quality analysis model and the image quality auxiliary analysis model are integrated to generate a CT image quality analysis model.

[0019] Preferably, the preliminary analysis of the quality of the CT image specifically includes analyzing the scanning parameters, acquisition parameters and reference parameters corresponding to the CT image and the displayed images in each layer area of ​​the CT image, and the specific analysis process includes the following steps:

[0020] Obtain each scanning parameter corresponding to the CT image, compare each scanning parameter corresponding to the CT image with the first image auxiliary quality factor in the image quality auxiliary analysis model, calculate the comprehensive qualified index of the CT image scanning parameters, and record it as β1;

[0021] Acquire each acquisition parameter corresponding to the CT image, compare each acquisition parameter corresponding to the CT image with the second image auxiliary quality factor in the image quality auxiliary analysis model, calculate the comprehensive qualified index of the CT image acquisition parameters, and record it as β2;

[0022] Obtaining each benchmark parameter corresponding to the displayed image in each layer area of ​​the CT image, comparing each benchmark parameter corresponding to the displayed image in each layer area with the main image quality factor in the main image quality analysis model, and calculating the comprehensive qualified index of the CT image benchmark parameter, which is recorded as δ;

[0023] The comprehensive qualified index of the CT image scanning parameters, the comprehensive qualified index of the CT image acquisition parameters, and the comprehensive qualified index of the CT image benchmark parameters are imported into the CT image quality analysis model, and the comprehensive quality index corresponding to the CT image is output, which is denoted as λ, wherein the CT image quality analysis model is specifically expressed as λ′=[ε1*(α1*β1+α2*β2)+ε2*δ]*η, ε1 and ε2 respectively represent the image weight corresponding to the preset image auxiliary quality factor and the image weight corresponding to the image main quality factor, η represents the preset detection quality image weight corresponding to the preset detection part of the patient, α1 and α2 respectively represent the image weight corresponding to the CT image scanning parameters and the image weight corresponding to the CT image acquisition parameters, wherein ε1+ε2=1, α1+α2=1.

[0024] Preferably, the statistical process of the comprehensive qualified index of the CT image scanning parameters and the comprehensive qualified index of the CT image acquisition parameters comprises the following steps:

[0025] 1) Based on the scanning parameters corresponding to the CT image, extract the tube voltage, tube current and exposure time corresponding to the CT image, record the tube voltage, tube current and exposure time corresponding to the CT image as the exposure information corresponding to the CT image, and calculate the exposure information qualification index of the CT image using the exposure information qualification index calculation formula, which is recorded as μ1;

[0026] 2) Extract the shooting inclination angle, shooting window width and shooting window position corresponding to the CT image from the corresponding scanning parameters of the CT image, and use the shooting orientation qualified index calculation formula to calculate the shooting orientation qualified index of the CT image, recorded as μ2, and substitute the CT image exposure information qualified index μ1 and the CT image shooting orientation qualified index μ2 into the CT image scanning parameter comprehensive qualified index calculation formula The comprehensive qualified index of the CT image scanning parameters is obtained, where: is the preset correction coefficient, k is the preset constant;

[0027] 3) Based on the acquisition parameters corresponding to the CT image, the number of scanning slices corresponding to the CT image and the thickness of each scanning slice are extracted, and the number of scanning slices corresponding to the CT image is compared with the number of standard scanning slices corresponding to the CT image to obtain the qualified index of the number of scanning slices corresponding to the CT image. At the same time, the thickness corresponding to each scanning layer of the CT image is compared with the standard thickness corresponding to each scanning layer of the CT image to confirm the qualified index of the scanning layer thickness of the CT image, which is recorded as φ. The qualified index of the number of scanning layers corresponding to the CT image and the comprehensive qualified index of the scanning layer thickness of the CT image are substituted into the formula The comprehensive qualified index of the CT image acquisition parameters is obtained, and b1 and b2 are preset coefficients respectively.

[0028] Preferably, the specific statistical process of the comprehensive qualified index of the CT image benchmark parameters is as follows:

[0029] Based on the reference parameters corresponding to the displayed image in each layer area, the noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the displayed image in each layer area are extracted, and the noise value, contrast, sharpness, resolution and visibility corresponding to the displayed image in each layer area are used as image quality information. The image quality information comprehensive qualified index corresponding to the CT image is calculated using the image quality information comprehensive qualified index calculation formula and recorded as ψ1;

[0030] Based on the artifact parameters corresponding to the displayed images in each layer area, the artifact status corresponding to the displayed images in each layer area is obtained, and the qualified index of the shooting environment corresponding to the CT image is confirmed, which is recorded as ψ2″′;

[0031] Based on the image quality information qualification index corresponding to the CT image and the shooting environment qualification index corresponding to the CT image, the comprehensive qualification index δ corresponding to the CT image benchmark parameters is calculated using the CT image benchmark parameter comprehensive qualification index, wherein the calculation formula of the CT image benchmark parameter comprehensive qualification index is δ=c1*ψ1+c2*ψ2″′, c1 and c2 respectively represent the image weight influence weight corresponding to the image quality and the image quality influence weight corresponding to the shooting environment, and c1+c2=1.

[0032] Preferably, the specific analysis process for analyzing the unqualified quality image is: when the CT image is an unqualified quality image, each scanning parameter, each acquisition parameter and each benchmark parameter corresponding to the CT image are extracted, and the CT image quality factor analysis model is extracted from the image analysis database, and the scanning parameters, each acquisition parameter and each benchmark parameter corresponding to the CT image are imported into the CT image quality abnormality analysis model, and the quality abnormality factors corresponding to the CT image and the corresponding treatment measures of each quality abnormality factor are output.

[0033] The second aspect of the present invention provides a device, comprising: a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in the present invention.

[0034] A third aspect of the present invention provides a computer storage medium having a computer program burned therein, wherein the computer program implements the method of the present invention when running in the memory of a server.

[0035] Beneficial effects of the present invention:

[0036] (1) The present invention provides a method for analyzing and controlling the quality of medical images. By collecting and analyzing the basic information of the patient and the scanning parameters, acquisition parameters and reference parameters corresponding to the CT images, the present invention realizes a multi-dimensional analysis of the CT images taken by the patient. This effectively solves the obvious limitations of the current technology in the analysis of the quality of medical images, improves the accuracy of the quality analysis of the CT images taken by the patient, and thus greatly reduces the misjudgment rate of the doctor's diagnosis of the patient's condition. At the same time, through the multi-dimensional analysis of the parameters affecting the quality of the CT images taken by the patient, it ensures that the medical images taken by the patient can reflect the true condition of the patient's condition to the greatest extent, improves the pertinence of the doctor's diagnosis and treatment of the patient's condition, and to a certain extent effectively promotes the doctor's diagnosis and treatment efficiency and treatment effect of the patient's condition.

[0037] (2) The present invention constructs a CT image quality analysis model based on the collected parameters affecting CT image quality in various dimensions, thereby effectively improving the analysis rate of CT image quality. At the same time, by constructing the model, the analysis time of CT image quality is effectively saved, which greatly improves the standardization and rationality of CT image quality analysis.

[0038] (3) The present invention greatly improves the timeliness of handling CT image quality issues by sending abnormal image shooting instructions and image failure types to the equipment control management personnel of the target department, effectively avoids the probability of similar problems, and thus ensures the quality of CT images taken by patients and improves the scientificity and accuracy of patient condition analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 It is a step diagram for implementing the method of the present invention. DETAILED DESCRIPTION

[0041] The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. The technical personnel in the relevant technical field may make various modifications or supplements to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0042] See also Figure 1 As shown, a method for analyzing and controlling the quality of medical imaging includes the following steps:

[0043] Step 1: Obtaining basic patient information: Obtain the electronic medical records corresponding to the patient currently undergoing CT imaging scans in the target department, and extract the basic information corresponding to the patient from the electronic medical records, wherein the basic information corresponding to the patient specifically includes the preset detection site and the preset detection lesion type corresponding to the patient;

[0044] Step 2: CT image extraction and preliminary analysis: After the patient completes CT image shooting, obtain the corresponding CT image of the patient. Based on the CT image corresponding to the patient, extract the scanning parameters and acquisition parameters corresponding to the CT image. The scanning parameters corresponding to the CT image specifically include the tube voltage, tube current, exposure time and shooting orientation parameters corresponding to the CT image; the acquisition parameters corresponding to the CT image specifically include the number of scanning layers corresponding to the CT image and the thickness of each scanning layer of the CT image. Among them, the shooting orientation parameters corresponding to the CT image are the shooting inclination angle, shooting window width and shooting window position.

[0045] Step 3: CT image benchmark parameter acquisition: Based on the acquisition parameters corresponding to the CT image, the number of scanning layers corresponding to the CT image is extracted, and then the CT image is divided into layers. The layers are numbered 1, 2, ...i, ...n in sequence, and the images displayed in the layers are imported into the image benchmark parameter extraction model to extract the benchmark parameters corresponding to the images displayed in the layers. The benchmark parameters corresponding to the images displayed in the layers are specifically expressed as noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the images displayed in the layers. The artifact parameters include artifact status and artifact type. The artifact type includes equipment artifact, metal artifact and personnel motion artifact.

[0046] Exemplarily, the acquired artifact type is used to provide a data basis for the subsequent output of the quality abnormality factors corresponding to the CT image and the treatment measures corresponding to each quality abnormality factor.

[0047] Step 4: Build a CT image quality analysis model: Build a CT image quality analysis model based on the basic information corresponding to the patient, the scanning parameters and acquisition parameters corresponding to the CT image, and the benchmark parameters corresponding to the displayed image in each layer area of ​​the CT image. The specific construction process is as follows:

[0048] A1. extracting the preset detection part and the preset detection lesion type corresponding to the patient from the basic information corresponding to the patient, and based on the preset detection part and the preset lesion type corresponding to the patient, extracting various standard scanning parameters and various standard acquisition parameters corresponding to the patient from the image detection database;

[0049] A2. The standard scanning parameters corresponding to the patient are used as the first image-assisted quality factor, and the standard acquisition parameters corresponding to the patient are used as the second image-assisted quality factor. At the same time, the standard benchmark parameters corresponding to the CT image are extracted from the image detection database, and the standard benchmark parameters corresponding to the CT image are used as the main image quality factor. According to the first image-assisted quality factor and the second image-assisted quality factor, an image quality auxiliary analysis model is constructed, and the main image quality analysis model is constructed with the main image quality factors. The main image quality analysis model and the image quality auxiliary analysis model are integrated to generate a CT image quality analysis model.

[0050] The embodiment of the present invention constructs a CT image quality analysis model based on the collected CT image quality influencing parameters of each dimension, thereby effectively improving the analysis rate of CT image quality. At the same time, by constructing the model, the analysis time of CT image quality is effectively saved, which greatly improves the standardization and rationality of CT image quality analysis.

[0051] Step 5: Preliminary analysis of CT image quality: Substitute the scanning parameters, acquisition parameters and reference parameters corresponding to the displayed image in each layer area of ​​the CT image into the CT image quality analysis model, conduct a preliminary analysis of the CT image quality, and obtain a comprehensive quality index corresponding to the CT image;

[0052] It should be noted that the preliminary analysis of the quality of the CT image specifically includes analyzing the scanning parameters, acquisition parameters and reference parameters corresponding to the CT image and the displayed images in each layer area of ​​the CT image. The specific analysis process includes the following steps:

[0053] F1, obtaining each scanning parameter corresponding to the CT image, comparing each scanning parameter corresponding to the CT image with the first image auxiliary quality factor in the image quality auxiliary analysis model, and calculating the comprehensive qualified index of the CT image scanning parameters, and recording it as β1;

[0054] Specifically, the statistical process of the comprehensive qualified index of the CT image scanning parameters includes the following steps:

[0055] 1) Based on the scanning parameters corresponding to the CT image, the tube voltage, tube current and exposure time corresponding to the CT image are extracted, and the tube voltage, tube current and exposure time corresponding to the CT image are recorded as the exposure information corresponding to the CT image. The exposure information qualification index of the CT image is calculated using the exposure information qualification index calculation formula, which is recorded as μ1. The specific calculation formula for the exposure information qualification index is: μ1 represents the qualified index of the exposure information of the CT image, σ1, σ2, σ3 represent the preset coefficients respectively, Δv, Δa, Δt represent the preset permitted tube voltage difference, permitted tube current difference, permitted exposure time difference respectively, mv, ma, pt represent the tube voltage, tube current, exposure time corresponding to the CT image respectively, mv′, ma′, pt′ represent the standard tube voltage, standard tube current, standard exposure time corresponding to the CT image respectively.

[0056] 2) Extract the shooting inclination angle, shooting window width and shooting window position corresponding to the CT image from the corresponding scanning parameters in the CT image, and calculate the shooting orientation qualification index of the CT image using the shooting orientation qualification index calculation formula, which is recorded as μ2. The shooting orientation qualification index calculation formula is specifically: μ2 represents the qualified index of the CT image shooting orientation, τ1, τ2, τ3 represent the preset coefficients, Δj, Δc, Δw represent the preset permitted shooting tilt angle difference, permitted shooting window width difference, permitted shooting window position difference, qj, ck, cw represent the shooting tilt angle, shooting window width, shooting window position corresponding to the CT image, qj′, ck′, cw′ represent the standard shooting tilt angle, standard shooting window width, standard shooting window position corresponding to the CT image, and substitute the CT image exposure information qualified index μ1 and the CT image shooting orientation qualified index μ2 into the calculation formula of the comprehensive qualified index of the CT image scanning parameters. The comprehensive qualified index of the CT image scanning parameters is obtained, where: is the preset correction coefficient, k is the preset constant;

[0057] F2, obtaining the acquisition parameters corresponding to the CT image, comparing the acquisition parameters corresponding to the CT image with the second image auxiliary quality factor in the image quality auxiliary analysis model, and calculating the comprehensive qualified index of the CT image acquisition parameters, which is recorded as β2. The specific statistical process is as follows:

[0058] F2-1 Based on the acquisition parameters corresponding to the CT image, the number of scanning layers corresponding to the CT image and the thickness of each scanning layer are extracted, and the number of scanning layers corresponding to the CT image is compared with the number of standard scanning layers corresponding to the CT image. If they are consistent, the qualified index of the number of scanning layers corresponding to the CT image is recorded as Otherwise, it is recorded as In this way, the qualified index of the number of scanning layers corresponding to the CT image is obtained The value is or

[0059] F2-2 Compare the thickness corresponding to each scanning layer of the CT image with the standard thickness corresponding to each scanning layer of the CT image, confirm the qualified index of the scanning layer thickness of the CT image, recorded as φ, and substitute the qualified index of the number of scanning layers corresponding to the CT image and the comprehensive qualified index of the scanning layer thickness of the CT image into the formula , obtain the comprehensive qualified index of the CT image acquisition parameters;

[0060] Exemplarily, the specific confirmation process of the CT image scanning layer thickness comprehensive qualified index is: the scanning layers corresponding to the CT image are numbered in sequence according to the scanning order, marked as 1, 2, ...i, ...n, and the CT image scanning layer thickness qualified index is calculated using a calculation formula, and the specific calculation formula is: n represents the number of CT image scanning layers, h i Indicates the thickness corresponding to the i-th scanning layer of the CT image, h′ i Indicates the standard thickness corresponding to the i-th scanning layer of the CT image.

[0061] F3, obtaining the benchmark parameters corresponding to the displayed image in each layer area of ​​the CT image, comparing the benchmark parameters corresponding to the displayed image in each layer area with the main image quality factor in the main image quality analysis model, and calculating the comprehensive qualified index of the CT image benchmark parameters, which is recorded as δ;

[0062] Specifically, the specific statistical process of the comprehensive qualified index of the CT image benchmark parameters is as follows:

[0063] F3-1. Based on the reference parameters corresponding to the displayed image in each layer area, the noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the displayed image in each layer area are extracted, and the noise value, contrast, sharpness, resolution and visibility corresponding to the displayed image in each layer area are used as image quality information. The image quality information comprehensive qualified index corresponding to the CT image is calculated using the image quality information comprehensive qualified index calculation formula and recorded as ψ1;

[0064] The statistical process of the comprehensive qualified index of the image quality information corresponding to the CT image is as follows: each image quality information is recorded as q, q = s1 or s2 or s3 or s4 or s5, s1, s2, s3, s4, s5 are respectively represented as noise value, contrast, sharpness, resolution, visibility, and the image quality information corresponding to the displayed image in each layer area is substituted into the formula. Among them, ψ1 is the comprehensive qualified index of the image quality information corresponding to the CT image, d1, d2, d3, d4, d5 are preset coefficients, s1′, s2′, s3′, s4′, s5′ represent the standard noise value, contrast, sharpness, resolution, visibility corresponding to the CT image, s1 i ,s2 i ,s3 i ,s4 i ,s5 i They represent the noise value, contrast, sharpness, resolution, and visibility of the image displayed in the i-th layer area, respectively. i represents the layer area number, i=1, 2, ... n.

[0065] F3-2. Based on the artifact parameters corresponding to the displayed image in each layer area, the artifact state corresponding to the displayed image in each layer area is obtained, and the qualified index of the shooting environment corresponding to the CT image is confirmed, which is recorded as ψ2″′. The specific confirmation process of the qualified index of the shooting environment corresponding to the CT image is as follows: if the artifact state of the displayed image in a certain layer area is that artifacts exist, the qualified index of the shooting environment corresponding to the CT image is recorded as ψ2, and the number of layer areas with artifacts is counted. If the artifact state of the displayed image in each layer area does not contain artifacts, the qualified index of the shooting environment corresponding to the CT image is recorded as ψ2′, wherein ψ2=ψ2″*y, ψ2″ is the qualified index of the shooting environment corresponding to the artifact in a single layer area, and y refers to the number of layer areas with artifacts. In this way, the qualified index of the shooting environment corresponding to the CT image is obtained, which is recorded as ψ2″′, and ψ2″′ takes the value of ψ2 or ψ2′;

[0066] F3-3. Based on the image quality information qualification index corresponding to the CT image and the shooting environment qualification index corresponding to the CT image, the comprehensive qualification index δ corresponding to the CT image benchmark parameters is calculated using the CT image benchmark parameter comprehensive qualification index, wherein the calculation formula for the CT image benchmark parameter comprehensive qualification index is δ=c1*ψ1+c2*ψ2″′, c1 and c2 respectively represent the image weight influence weight corresponding to the image quality and the image quality influence weight corresponding to the shooting environment, and c1+c2=1.

[0067] F4. Import the comprehensive qualified index of the CT image scanning parameters, the comprehensive qualified index of the CT image acquisition parameters, and the comprehensive qualified index of the CT image benchmark parameters into the CT image quality analysis model, and output the comprehensive quality index corresponding to the CT image, denoted as λ, wherein the CT image quality analysis model is specifically expressed as λ′=[ε1*(α1*β1+α2*β2)+ε2*δ]*η, ε1 and ε2 respectively represent the image weight corresponding to the preset image auxiliary quality factor and the image weight corresponding to the image main quality factor, η represents the preset detection quality image weight corresponding to the preset detection part of the patient, α1 and α2 respectively represent the image weight corresponding to the CT image scanning parameters and the image weight corresponding to the CT image acquisition parameters, wherein ε1+ε2=1, α1+α2=1.

[0068] The embodiment of the present invention collects and analyzes the patient's basic information, scanning parameters, acquisition parameters and reference parameters corresponding to the CT images, thereby realizing multi-dimensional analysis of the CT images taken by the patient, effectively solving the problem that the current technology has obvious limitations in the quality analysis of medical images, improving the accuracy of the quality analysis of the CT images taken by the patient, and thus greatly reducing the misjudgment rate of the doctor's diagnosis of the patient's condition. At the same time, through the multi-dimensional analysis of the parameters affecting the quality of the CT images taken by the patient, it is ensured that the medical images taken by the patient can reflect the true situation of the patient's condition to the greatest extent, thereby improving the pertinence of the doctor's diagnosis and treatment of the patient's condition, and to a certain extent, effectively promoting the doctor's diagnosis and treatment efficiency and treatment effect of the patient's condition.

[0069] Step 6: In-depth analysis of CT image quality: based on the comprehensive quality index corresponding to the CT image, the comprehensive quality index corresponding to the CT image is compared with the preset standard quality index corresponding to the CT image. If the comprehensive quality index corresponding to the CT image is less than the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of unqualified quality, and the unqualified quality image is analyzed. If the comprehensive quality index corresponding to the CT image is greater than or equal to the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of qualified quality.

[0070] It should be noted that the specific analysis process for analyzing images with unqualified quality is as follows: when the CT image is an image with unqualified quality, the scanning parameters, acquisition parameters and benchmark parameters corresponding to the CT image are extracted, and the CT image quality factor analysis model is extracted from the image analysis database, the scanning parameters, acquisition parameters and benchmark parameters corresponding to the CT image are imported into the CT image quality abnormality analysis model, and the quality abnormality factors corresponding to the CT image and the corresponding treatment measures for each quality abnormality factor are output.

[0071] Specifically, the specific output process of outputting the quality abnormality factors and treatment measures corresponding to the CT image is analyzed by taking the exposure time in the CT image scanning parameters as an example in a specific embodiment, which is specifically: importing each scanning parameter, each acquisition parameter and each benchmark parameter corresponding to the CT image into the CT image quality factor analysis model; if the exposure time in the CT image scanning parameters meets the corresponding scanning time quality factor in the CT image quality factor analysis model, then the scanning time quality factor is recorded as the CT image quality abnormality factor, and the difference between the exposure time of the CT image and its standard exposure time is obtained; if the difference between the exposure time of the CT image and its standard exposure time is greater than 0, the treatment measure of the CT image quality abnormality factor is to reduce the exposure time; if the difference between the exposure time of the CT image and its standard exposure time is less than 0, the treatment measure of the CT image quality abnormality factor is to increase the exposure time; the specific value of the increased exposure time or reduced exposure time of the CT image is the difference between the exposure time of the CT image and its standard exposure time.

[0072] Step 7. Feedback of CT image quality analysis results: When the CT image is of unqualified quality, the quality abnormality factors corresponding to the unqualified image and the corresponding treatment measures for each quality abnormality factor are sent to the equipment control manager of the target department for image acquisition control.

[0073] The embodiment of the present invention greatly improves the timeliness of handling CT image quality issues by sending abnormal image shooting instructions and image failure types to the equipment control management personnel of the target department, effectively avoids the probability of occurrence of similar problems, thereby ensuring the quality of CT images taken by patients and improving the scientificity and accuracy of patient condition analysis.

[0074] The present invention provides a device, comprising: a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in the present invention.

[0075] The present invention also provides a computer storage medium, wherein the computer storage medium is burned with a computer program, and the computer program implements the method of the present invention when running in the memory of a server.

[0076] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A method for analyzing and controlling the quality of medical imaging, characterized in that: include: Step 1: Obtaining basic patient information: Obtain the electronic medical records corresponding to the patient currently undergoing CT imaging scans in the target department, and extract the basic information corresponding to the patient from the electronic medical records, wherein the basic information corresponding to the patient specifically includes the preset detection site and the preset detection lesion type corresponding to the patient; Step 2: CT image extraction and preliminary analysis: After the patient has completed CT image shooting, the CT image corresponding to the patient is obtained, and based on the CT image corresponding to the patient, the scanning parameters and acquisition parameters corresponding to the CT image are extracted; Step 3: CT image benchmark parameter acquisition: Based on the acquisition parameters corresponding to the CT image, the number of scanning layers corresponding to the CT image is extracted, and then the CT image is divided into layers, and each layer region is numbered 1, 2, ...i, ...n in sequence. The image displayed in each layer region is imported into the image benchmark parameter extraction model, and the benchmark parameters corresponding to the image displayed in each layer region are extracted; Step 4: Build a CT image quality analysis model: Build a CT image quality analysis model based on the basic information corresponding to the patient, the scanning parameters and acquisition parameters corresponding to the CT image, and the benchmark parameters corresponding to the displayed image in each layer area; Step 5: Preliminary analysis of CT image quality: Substitute the scanning parameters, acquisition parameters and reference parameters corresponding to the displayed image in each layer area of ​​the CT image into the CT image quality analysis model, conduct a preliminary analysis of the CT image quality, and obtain a comprehensive quality index corresponding to the CT image; Step 6: In-depth analysis of CT image quality: based on the comprehensive quality index corresponding to the CT image, the comprehensive quality index corresponding to the CT image is compared with the preset standard quality index corresponding to the CT image. If the comprehensive quality index corresponding to the CT image is less than the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of unqualified quality, and the unqualified quality image is analyzed. If the comprehensive quality index corresponding to the CT image is greater than or equal to the preset standard quality index corresponding to the CT image, the CT image is recorded as an image of qualified quality. Step 7. Feedback of CT image quality analysis results: When the CT image is of unqualified quality, the quality abnormality factors corresponding to the unqualified image and the corresponding treatment measures for each quality abnormality factor are sent to the equipment control manager of the target department for image acquisition control.

2. The method for analyzing and controlling medical imaging quality according to claim 1, characterized in that: The scanning parameters corresponding to the CT image specifically include the tube voltage, tube current, exposure time and shooting orientation parameters corresponding to the CT image; the acquisition parameters corresponding to the CT image specifically include the number of scanning layers corresponding to the CT image and the thickness corresponding to each scanning layer of the CT image, wherein the shooting orientation parameters corresponding to the CT image are the shooting inclination angle, shooting window width and shooting window position.

3. The method for analyzing and controlling medical imaging quality according to claim 1, characterized in that: The various benchmark parameters corresponding to the displayed images in the various layer areas are specifically represented by the noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the displayed images in the various layer areas, wherein the artifact parameters include artifact status and artifact type, and the artifact type includes equipment artifacts, metal artifacts and personnel motion artifacts.

4. The method for analyzing and controlling medical imaging quality according to claim 1, characterized in that: The specific construction process of the CT image quality analysis model includes the following steps: Extracting the preset detection part and the preset detection lesion type corresponding to the patient from the basic information corresponding to the patient, and based on the preset detection part and the preset lesion type corresponding to the patient, extracting various standard scanning parameters and various standard acquisition parameters corresponding to the patient from the image detection database; The standard scanning parameters corresponding to the patient are used as the first image-assisted quality factor, and the standard acquisition parameters corresponding to the patient are used as the second image-assisted quality factor. At the same time, the standard benchmark parameters corresponding to the CT image are extracted from the image detection database, and the standard benchmark parameters corresponding to the CT image are used as the main image quality factor. According to the first image-assisted quality factor and the second image-assisted quality factor, an image quality auxiliary analysis model is constructed, and the main image quality analysis model is constructed with the main image quality factors. The main image quality analysis model and the image quality auxiliary analysis model are integrated to generate a CT image quality analysis model.

5. The method for analyzing and controlling the quality of medical imaging according to claim 4, characterized in that: The preliminary analysis of the quality of the CT image specifically includes analyzing the scanning parameters, acquisition parameters and reference parameters of the CT image corresponding to the displayed image in each layer area of ​​the CT image. The specific analysis process includes the following steps: Obtain each scanning parameter corresponding to the CT image, compare each scanning parameter corresponding to the CT image with the first image auxiliary quality factor in the image quality auxiliary analysis model, calculate the comprehensive qualified index of the CT image scanning parameters, and record it as β1; Acquire each acquisition parameter corresponding to the CT image, compare each acquisition parameter corresponding to the CT image with the second image auxiliary quality factor in the image quality auxiliary analysis model, calculate the comprehensive qualified index of the CT image acquisition parameters, and record it as β2; Obtaining each benchmark parameter corresponding to the displayed image in each layer area of ​​the CT image, comparing each benchmark parameter corresponding to the displayed image in each layer area with the main image quality factor in the main image quality analysis model, and calculating the comprehensive qualified index of the CT image benchmark parameter, which is recorded as δ; The comprehensive qualified index of the CT image scanning parameters, the comprehensive qualified index of the CT image acquisition parameters, and the comprehensive qualified index of the CT image benchmark parameters are imported into the CT image quality analysis model, and the comprehensive quality index corresponding to the CT image is output, which is denoted as λ, wherein the CT image quality analysis model is specifically expressed as λ′=[ε1*(α1*β1+α2*β2)+ε2*δ]*η, ε1 and ε2 respectively represent the image weight corresponding to the preset image auxiliary quality factor and the image weight corresponding to the image main quality factor, η represents the preset detection quality image weight corresponding to the preset detection part of the patient, α1 and α2 respectively represent the image weight corresponding to the CT image scanning parameters and the image weight corresponding to the CT image acquisition parameters, wherein ε1+ε2=1, α1+α2=1.

6. The method for analyzing and controlling the quality of medical imaging according to claim 5, characterized in that: The statistical process of the comprehensive qualified index of the CT image scanning parameters and the comprehensive qualified index of the CT image acquisition parameters comprises the following steps: 1) Based on the scanning parameters corresponding to the CT image, extract the tube voltage, tube current and exposure time corresponding to the CT image, record the tube voltage, tube current and exposure time corresponding to the CT image as the exposure information corresponding to the CT image, and calculate the exposure information qualification index of the CT image using the exposure information qualification index calculation formula, which is recorded as μ1; 2) Extract the shooting inclination angle, shooting window width and shooting window position corresponding to the CT image from the corresponding scanning parameters of the CT image, and use the shooting orientation qualified index calculation formula to calculate the shooting orientation qualified index of the CT image, recorded as μ2, and substitute the CT image exposure information qualified index μ1 and the CT image shooting orientation qualified index μ2 into the CT image scanning parameter comprehensive qualified index calculation formula The comprehensive qualified index of the CT image scanning parameters is obtained, where: is the preset correction coefficient, k is the preset constant; 3) Based on the acquisition parameters corresponding to the CT image, the number of scanning slices corresponding to the CT image and the thickness of each scanning slice are extracted, and the number of scanning slices corresponding to the CT image is compared with the number of standard scanning slices corresponding to the CT image to obtain the qualified index of the number of scanning slices corresponding to the CT image. At the same time, the thickness corresponding to each scanning layer of the CT image is compared with the standard thickness corresponding to each scanning layer of the CT image to confirm the qualified index of the scanning layer thickness of the CT image, which is recorded as φ. The qualified index of the number of scanning layers corresponding to the CT image and the comprehensive qualified index of the scanning layer thickness of the CT image are substituted into the formula The comprehensive qualified index of the CT image acquisition parameters is obtained, and b1 and b2 are preset coefficients respectively.

7. The method for analyzing and controlling the quality of medical imaging according to claim 5, characterized in that: The specific statistical process of the comprehensive qualified index of the CT image benchmark parameters is as follows: Based on the reference parameters corresponding to the displayed image in each layer area, the noise value, contrast, sharpness, resolution, visibility and artifact parameters corresponding to the displayed image in each layer area are extracted, and the noise value, contrast, sharpness, resolution and visibility corresponding to the displayed image in each layer area are used as image quality information. The image quality information comprehensive qualified index corresponding to the CT image is calculated using the image quality information comprehensive qualified index calculation formula and recorded as ψ1; Based on the artifact parameters corresponding to the displayed images in each layer area, the artifact status corresponding to the displayed images in each layer area is obtained, and the qualified index of the shooting environment corresponding to the CT image is confirmed, which is recorded as ψ2″′; Based on the image quality information qualification index corresponding to the CT image and the shooting environment qualification index corresponding to the CT image, the comprehensive qualification index δ corresponding to the CT image benchmark parameters is calculated using the CT image benchmark parameter comprehensive qualification index, wherein the calculation formula of the CT image benchmark parameter comprehensive qualification index is δ=c1*ψ1+c2*ψ2″′, c1 and c2 respectively represent the image weight influence weight corresponding to the image quality and the image quality influence weight corresponding to the shooting environment, and c1+c2=1.

8. The method for analyzing and controlling medical imaging quality according to claim 1, characterized in that: The specific analysis process of analyzing the unqualified quality image is as follows: when the CT image is an unqualified quality image, each scanning parameter, each acquisition parameter and each benchmark parameter corresponding to the CT image are extracted, and a CT image quality factor analysis model is extracted from an image analysis database, each scanning parameter, each acquisition parameter and each benchmark parameter corresponding to the CT image are imported into the CT image quality abnormality analysis model, and the quality abnormality factors corresponding to the CT image and the corresponding treatment measures of each quality abnormality factor are output.

9. A device, characterized in that: include: A processor, and memory and network interfaces connected to the processor; The network interface is connected to a non-volatile memory in the server; When running, the processor retrieves a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in any one of claims 1 to 8.

10. A computing storage medium, characterized in that: The computer storage medium is burned with a computer program, and when the computer program is executed in the memory of the server, the method described in any one of claims 1 to 8 is implemented.

Images