Scanning protocol adjustment method, apparatus, and storage medium

Abstract

This application relates to a scanning protocol adjustment method, apparatus, and storage medium. The method includes: acquiring an initial medical image based on an initial scanning protocol; selecting a target image quality detection model from multiple image quality detection models that matches preset quality influencing factors; inputting the initial medical image into the target image quality detection model, and outputting a target quality assessment result corresponding to the initial medical image through the target image quality detection model; and adjusting a copy scanning protocol based on the target quality assessment result to determine a target scanning protocol; wherein the copy scanning protocol is created and generated according to the initial scanning protocol. The scanning protocol adjustment method provided by this application can improve the efficiency and accuracy of scanning protocol adjustment.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a scanning protocol adjustment method, apparatus, and storage medium. Background Technology

[0002] In medical imaging systems, image quality depends on many factors, such as spatial resolution, tissue contrast, and signal-to-noise ratio. Defects in image quality caused by these factors can be improved through optimization of scanning protocols, such as scanning parameters, resulting in better image quality.

[0003] In related technologies, users typically need to assess image quality based on their personal medical experience and provide corresponding scanning protocol adjustments. This process introduces subjective and variable factors, as different users, such as radiologists, may have different perceptions of image quality. Furthermore, users often cannot comprehensively evaluate image quality by considering multiple factors, making it difficult to guarantee the accuracy of their suggested scanning protocol adjustments.

[0004] Therefore, there is an urgent need for a highly efficient scanning protocol adjustment method in related technologies. Summary of the Invention

[0005] Based on this, and in response to the aforementioned technical problems, this application provides a scanning protocol adjustment method, apparatus, and storage medium, which can solve the problem of inaccurate scanning protocol adjustment in related technologies.

[0006] In a first aspect, embodiments of this application provide a scanning protocol adjustment method, the method comprising:

[0007] Acquire initial medical images based on the initial scanning protocol;

[0008] Select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model;

[0009] The replica scanning protocol is adjusted accordingly based on the target quality assessment results to determine the target scanning protocol; wherein the replica scanning protocol is created and generated according to the initial scanning protocol.

[0010] The scanning protocol adjustment method provided in this application can acquire an initial medical image corresponding to an initial scanning protocol and determine preset quality influencing factors based on actual diagnostic needs. Then, a target image quality detection model corresponding to the preset quality influencing factors can be selected from multiple image quality detection models, and the target image quality detection model outputs a target quality assessment result corresponding to the initial medical image. Finally, the copy scanning protocol can be adjusted based on the target quality assessment result to determine the target scanning protocol. In this method, multiple image quality detection models can meet the detection needs under various dimensions of image quality defects, making the application scenarios of scanning protocol adjustment more diversified. Users can also select different preset quality influencing factors according to actual needs, allowing them to focus on observing the image quality defects they need to observe, achieving efficient monitoring of image quality. Furthermore, the scanning protocol can be automatically adjusted based on the target quality assessment result, thereby greatly improving the quality of the obtained medical images. Finally, since the adjusted scanning protocol is a copy scanning protocol, no changes are made to the initial scanning protocol, thus preserving the initial scanning protocol for easy subsequent image comparison.

[0011] Optionally, in one embodiment of this application, the preset quality influencing factors are determined in at least one of the following ways:

[0012] In response to input commands, determine preset quality influencing factors;

[0013] Based on the characteristic data of the target object, preset quality influencing factors are determined; wherein, the image obtained by scanning the target object is the initial medical image.

[0014] Optionally, in one embodiment of this application, adjusting the copy scanning protocol based on the target quality assessment result to determine the target scanning protocol includes:

[0015] Determine the preset parameter adjustment rules corresponding to the preset quality influencing factors;

[0016] The copy scanning protocol is adjusted accordingly based on the target quality assessment results and the preset parameter adjustment rules to determine the target scanning protocol.

[0017] Optionally, in one embodiment of this application, adjusting the copy scanning protocol based on the target quality assessment result includes:

[0018] Obtain the benchmark evaluation results corresponding to the preset quality influencing factors;

[0019] Based on the comparison between the target quality assessment results and the benchmark assessment results, the copy scanning protocol is adjusted accordingly.

[0020] Optionally, in one embodiment of this application, after adjusting the copy scanning protocol accordingly based on the target quality assessment result to determine the target scanning protocol, the method further includes:

[0021] Acquire the medical image corresponding to the target scanning protocol;

[0022] The comparison results between the medical image and the initial medical image are displayed on the interactive interface.

[0023] Optionally, in one embodiment of this application, the preset quality influencing factors include one or more of the following: image artifact degree, image spatial resolution, image contrast, image signal-to-noise ratio, image background noise, image uniformity, and fat suppression degree.

[0024] Optionally, in one embodiment of this application, the image quality detection model is trained using various medical image samples of different quality defect types, and the various medical image samples are labeled with corresponding quality assessment results.

[0025] Optionally, in one embodiment of this application, the image quality detection model is trained in the following manner:

[0026] Multiple medical image samples are acquired, and the medical image samples are labeled with reference image quality;

[0027] An image quality detection model is constructed, wherein training parameters are set in the image quality detection model;

[0028] The multiple medical image samples are input into the image quality detection model to generate prediction results;

[0029] Based on the difference between the prediction result and the quality of the reference image, the training parameters are iteratively adjusted until the difference meets the preset requirements.

[0030] Secondly, embodiments of this application provide a scanning protocol adjustment device, the device comprising:

[0031] The medical image acquisition module is used to acquire initial medical images based on the initial scanning protocol.

[0032] The quality assessment result determination module is used to select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model;

[0033] The scanning protocol adjustment module is used to adjust the replica scanning protocol accordingly based on the target quality assessment result to determine the target scanning protocol; wherein the replica scanning protocol is generated according to the initial scanning protocol.

[0034] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the methods described in the above embodiments. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0037] Figure 2 A flowchart illustrating a scanning protocol adjustment method provided in one embodiment of this application;

[0038] Figure 3 This is a schematic diagram of the module structure of the scanning protocol adjustment device provided in the embodiments of this application;

[0039] Figure 4 This is a schematic diagram of the module structure of the processing device provided in the embodiments of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application. Furthermore, it is understood that although the efforts made in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, modifications to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0041] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0042] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "a," "an," "a kind," "the," and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms "comprising," "including," "having," and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms "connected," "linked," "coupled," and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "A plurality" used in this application means two or more. The terms "first," "second," "third," etc., used in this application are merely to distinguish similar objects and do not represent a specific ordering of objects.

[0043] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed description. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, apparatus, means, elements, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0044] Please see Figure 1 , Figure 1This is a schematic diagram of an application scenario provided by an embodiment of this application. This application scenario may include a client 101, a data acquisition device 103, and a scanning protocol adjustment device 105. The client 101 can receive user-configured scanning parameters and generate an initial scanning protocol accordingly. The client 101 and the data acquisition device 103 can communicate to send the generated initial scanning protocol to the data acquisition device 103, which then scans the target object according to the initial scanning protocol to obtain an initial medical image. For example, the data acquisition device 103 can scan the target object according to the initial scanning protocol to obtain corresponding raw data, which can then be reconstructed to obtain the initial medical image. The data acquisition device 103 can be an electronic device with data acquisition and data transmission / reception capabilities. For example, the acquisition device 103 may include electronic devices capable of acquiring medical images, such as computed tomography (CT) equipment, magnetic resonance imaging (MRI) equipment, positron emission tomography (PET) equipment, etc., or it may be a multimodal imaging device composed of a combination of the above-mentioned electronic devices, such as PET-CT equipment, PET-MRI equipment, etc. Correspondingly, the medical images acquired by the acquisition device 103 may be computed tomography images, magnetic resonance images, or positron emission tomography images, etc. The acquisition device 103 and the scanning protocol adjustment device 105 can communicate to send the acquired initial medical image to the scanning protocol adjustment device 105, which then adjusts the scanning protocol based on the initial medical image to determine a target scanning protocol that meets the requirements.

[0045] The client 101 can be various electronic devices with a display screen and a configuration interface, including but not limited to smartphones, computers (including laptops and desktops), tablet computers, personal digital assistants (PDAs), etc. The scanning protocol adjustment device 105 can be an electronic device with data processing and data transmission / reception capabilities. The electronic device can be a physical device or a cluster of physical devices, such as a server or a server cluster. Of course, the electronic device can also be a virtualized cloud device, such as at least one cloud computing device in a cloud computing cluster. This application does not limit the form of the electronic device.

[0046] The scanning protocol adjustment method described in this application will be explained in detail below with reference to the accompanying drawings. Figure 2This is a flowchart illustrating one embodiment of the scanning protocol adjustment method provided in this application. While this application provides method operation steps as shown in the following embodiments or figures, the method may include more or fewer operation steps based on conventional or non-inventive methods. For steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application. In actual scanning protocol adjustment processes or method execution, the method may be executed in the order shown in the embodiments or figures, or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0047] Specifically, one implementation of the scanning protocol adjustment method provided in this application is, for example... Figure 2 As shown, the method may include:

[0048] S201: Acquire the initial medical image based on the initial scanning protocol.

[0049] In this embodiment, the scanning protocol is a protocol for controlling the operation of medical devices, such as the acquisition device 103, when scanning a target object. Various medical devices have their corresponding scanning protocols. For example, the scanning protocol may include the step logic of the scanning operation of the medical device 101, scanning parameters, bed information, etc. The scanning parameters may include scanning range, scanning voltage, scanning current, scanning time, scanning start position, scanning end position, scanning mode, etc. The scanning mode may include conventional scanning such as plain scan and contrast-enhanced scanning. Contrast-enhanced scanning may include dynamic contrast enhancement, specific contrast agent enhanced scanning, etc. The scanning range may include the size and position of the scanning field of view, as well as parameters of the overlapping area between adjacent scanning ranges, such as the overlap ratio and the upper and lower edge coordinates of the overlapping area. In other embodiments of this application, the scanning parameters may also include the system parameters of the medical device. It is understood that different medical devices have different system parameters. For example, when the imaging system is an MRI system or a PET-MRI system, the system parameters may include the main magnetic field parameter B0, the radio frequency magnetic field parameter B1, and the gradient field parameter, etc. The bed information may include the number of beds required for scanning and the position information of each bed (bed center coordinates). In one embodiment of this application, the initial scan protocol can be generated in real time. For example, a user can set different scan parameters based on their own experience, and the client 101 can generate the corresponding initial scan protocol in real time after receiving the user's instruction. The user can be a doctor, nurse, clinical pathologist, medical imaging expert, radiologist, sonographer, etc. In other embodiments of this application, the initial scan protocol can also be obtained from other terminals or other medical devices; this application does not impose any restrictions on this.

[0050] In this embodiment, after obtaining the initial scanning protocol, a corresponding initial medical image can be determined according to the initial scanning protocol. For example, the medical device can scan the corresponding part of the target object according to the initial scanning protocol to obtain the initial medical image. The target object can be a living organism, such as a human or animal. Alternatively, digital image processing technology can be used to simulate imaging on a human digital model according to the initial scanning protocol to generate a preview image corresponding to the initial scanning protocol. The human digital model can be an XCAT model or a standard human digital model commonly used in the medical field, simulated using GATE software. The imaging part of the preview image can correspond to the part of the target object to be scanned, and the preview image can be approximated as the initial medical image obtained by scanning the target object according to the initial scanning protocol. It is understood that the initial medical image can be displayed on a display device such as a screen for user observation and judgment.

[0051] S203: Select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model.

[0052] In practical applications, image quality depends on many influencing factors, such as spatial resolution, tissue contrast, and signal-to-noise ratio. Different influencing factors can lead to different quality defects in medical images. Using the same image quality detection model cannot yield quality assessment results under different influencing factors. In other words, the quality assessment results are not comprehensive. Furthermore, different users are concerned with different influencing factors when judging image quality, and a fixed image quality detection model cannot obtain quality assessment results under different influencing factors. Therefore, in this embodiment, multiple image quality detection models corresponding to different quality influencing factors can be pre-constructed. This allows different image quality detection models to be selected according to actual application needs to evaluate the image quality of the initial medical image, obtaining quality assessment results under different quality influencing factors. In one embodiment of this application, the pre-constructed quality influencing factors include one or more of the following: image artifact degree, image spatial resolution, image contrast, image signal-to-noise ratio, image background noise, image uniformity, and fat suppression degree. The image contrast can be the contrast between bright and dark areas in the initial medical image, such as the contrast between different brightness levels between the brightest white area and the darkest black area, or it can be understood as the magnitude of grayscale contrast in an image. The uniformity of the image can be the degree of uniformity of the image signal acquired when the medical device scans the target object. For example, during an MRI scan, it refers to the uniformity of the magnetic resonance signal generated by hydrogen nuclei in the tissues, organs, and / or lesions of the target object under the influence of an external strong magnetic field. The image background noise can be the proportion of unwanted or redundant interference information present in the initial medical image. For example, isolated noise points may exist in certain areas of the image. The degree of image artifacts can be the extent to which artifacts in the initial medical image are eliminated or suppressed.

[0053] In one embodiment of this application, the preset quality factors can be set by the user according to their own needs. Specifically, the preset quality influencing factors can be determined in response to an input command. For example, the scanning protocol adjustment device 105 can provide an interactive interface, which may include an input box, a selection box, a confirmation button, etc. The user can input the preset quality influencing factors in the input box by manual input, voice input, etc., and trigger the confirmation button to generate an input command after the input is completed. The scanning protocol adjustment device 105 can determine the corresponding preset quality influencing factors in response to the input command. The selection box may include radio buttons, drop-down boxes, etc. The user can also select the corresponding preset quality influencing factors according to their needs.

[0054] In practical applications, when scanning a target object using medical equipment, the target object's characteristic data, such as height, weight, and age, can affect scanning parameters such as the number of scanning layers and scanning thickness, thus impacting the image quality of the initial medical image acquired. Therefore, in another embodiment of this application, preset quality-influencing factors can be determined based on the target object's characteristic data; wherein, the image obtained by scanning the target object is the initial medical image. The characteristic data can be determined based on the target object's profile information or obtained from a third party, such as a health application. The characteristic data may include basic information about the target object, such as height, weight, gender, and age, and may also include the target object's respiratory rate, heart rate, etc.

[0055] In this embodiment, after determining the preset quality influencing factors, a target image quality detection model matching the preset quality influencing factors can be selected from multiple image quality detection models. The image quality detection module can be trained using multiple medical image samples. The image quality detection model can include a model trained using machine learning methods. In some examples, the machine learning methods can include K-nearest neighbor algorithm, perceptron algorithm, decision tree, support vector machine, logistic regression, maximum entropy, deep learning algorithms, etc. The deep learning algorithms can include convolutional neural networks (CNN), recurrent neural networks (RNN), etc., and this application does not impose limitations. Each image quality detection model can be trained using different medical image samples. Different medical image samples may contain different types of quality defects. In one embodiment of this application, after determining the target image quality detection model, the initial medical image can be input into the target image quality detection model. After the target image quality detection model extracts features, judges quality, and outputs the target quality assessment result corresponding to the initial medical image, it outputs the target quality assessment result. The quality assessment results can be specific numerical values ​​or grades, such as high fat suppression or low fat suppression. Correspondingly, the quality assessment results can be presented in various forms, such as graphical representations or index-based methods. Through the above embodiments, different image quality detection models can be used to determine quality assessment results for different defect types, increasing the readability of medical image information and facilitating users' efficient judgment and understanding of the overall scan image quality.

[0056] S205: Adjust the replica scanning protocol accordingly based on the target quality assessment results to determine the target scanning protocol; wherein the replica scanning protocol is created and generated according to the initial scanning protocol.

[0057] In practical applications, typical image quality inspection processes only go as far as outputting quality assessment results. If the user lacks medical experience or has limited experience, they cannot provide suggestions for subsequent imaging processes or perform other follow-up work based on the quality assessment results. Therefore, in this embodiment, the scanning protocol can be adjusted accordingly based on the target quality assessment results to determine the target scanning protocol. After determining the target scanning protocol, target medical images that meet both image quality requirements and clinical diagnostic requirements can be acquired based on the target scanning protocol, facilitating user observation and providing reasonable diagnostic results. In one embodiment of this application, to retain the initial scanning protocol for subsequent comparison of the two scanning protocols, a copy of the initial scanning protocol can be created. Thus, during the scanning protocol adjustment process, only the copy scanning protocol can be adjusted, while the original initial scanning protocol is preserved.

[0058] The scanning protocol adjustment method provided in this application can acquire an initial medical image corresponding to an initial scanning protocol and determine preset quality influencing factors based on actual diagnostic needs. Then, a target image quality detection model corresponding to the preset quality influencing factors can be selected from multiple image quality detection models, and the target image quality detection model outputs a target quality assessment result corresponding to the initial medical image. Finally, the copy scanning protocol can be adjusted based on the target quality assessment result to determine the target scanning protocol. In this method, multiple image quality detection models can meet the detection needs under various dimensions of image quality defects, making the application scenarios of scanning protocol adjustment more diversified. Users can also select different preset quality influencing factors according to actual needs, allowing them to focus on observing the image quality defects they need to observe, achieving efficient monitoring of image quality. Furthermore, the scanning protocol can be automatically adjusted based on the target quality assessment result, thereby greatly improving the quality of the obtained medical images. Finally, since the adjusted scanning protocol is a copy scanning protocol, no changes are made to the initial scanning protocol, thus preserving the initial scanning protocol for easy subsequent image comparison.

[0059] In practical applications, each quality-influencing factor has its corresponding parameter adjustment rules. For example, insufficient fat suppression can be addressed by improving the fat suppression coefficient to optimize image quality. Therefore, in one embodiment of this application, after determining the target quality assessment result, the copy scanning protocol can be adjusted based on the parameter adjustment rules. Specifically, adjusting the copy scanning protocol based on the target quality assessment result to determine the target scanning protocol includes:

[0060] S301: Determine the preset parameter adjustment rules corresponding to the preset quality influencing factors;

[0061] S303: Adjust the copy scanning protocol accordingly based on the target quality assessment results and the preset parameter adjustment rules to determine the target scanning protocol.

[0062] In this embodiment, the preset parameter adjustment rule may include the correspondence between image quality and scanning protocol. The preset parameter adjustment rule can be derived from experimental results or calculated based on theoretical foundations. The preset parameter adjustment rule can take various forms, such as image form, function form, or tabular form. Different preset quality influencing factors result in different preset parameter adjustment rules. Specifically, when the preset quality influencing factor is image resolution, the preset parameter adjustment rule may include the correspondence between the image resolution and scanning parameters such as scan layer thickness and field of view (FOV). For example, the image resolution may be negatively correlated with the scan layer thickness and positively correlated with the FOV. The negative correlation may include a negative correlation coefficient between the image resolution and the scan layer thickness, while the positive correlation may include a positive correlation coefficient between the image resolution and the FOV. When the preset quality influencing factor is image signal-to-noise ratio (SNR), the preset parameter adjustment rule may include the correspondence between the image SNR and scanning parameters such as echo time, repetition time, and receiving bandwidth. The receiving bandwidth is the frequency range of the readout gradient sampling. For example, the image signal-to-noise ratio (SNR) is negatively correlated with both the echo time and the receiving bandwidth, while it is positively correlated with the repetition time. In one embodiment of this application, after determining the preset parameter adjustment rule, the copy scanning protocol can be adjusted based on the target quality assessment result output by the target image quality detection model and the preset parameter adjustment rule to determine a target scanning protocol that can obtain better image quality and meet user needs. For example, if the target quality assessment result indicates low spatial resolution, the scanning layer thickness can be reduced and the field of view (FOV) increased to improve spatial resolution; if the target quality assessment result indicates low image SNR, the echo time and receiving bandwidth can be reduced, or the repetition time can be increased.

[0063] Through the above embodiments, the copy scanning protocol can be accurately adjusted using the preset parameter adjustment rules to ensure that the adjusted scanning protocol can obtain medical images with better image quality, so that users can make more accurate diagnostic results based on the medical images.

[0064] Furthermore, in one embodiment of this application, the optimal medical image corresponding to each quality influencing factor type can be obtained. The image quality of the optimal medical image is superior to that of other medical images. Then, the copy protocol can be adjusted based on a comparison between the image quality of the optimal medical image and the target quality assessment result. Specifically, the adjustment of the copy scanning protocol based on the target quality assessment result includes:

[0065] S401: Obtain the benchmark evaluation results corresponding to the preset quality influencing factors;

[0066] S403: Adjust the copy scanning protocol accordingly based on the comparison between the target quality assessment result and the benchmark assessment result.

[0067] In this embodiment, the benchmark evaluation result can be determined based on the quality evaluation result of the benchmark image corresponding to the preset quality influencing factors. The benchmark image may include a medical image that does not contain a defect type corresponding to the preset quality influencing factors. The benchmark image can be obtained from image libraries of multiple hospital radiology departments or from other third-party devices. After obtaining the benchmark image, it can be input into the target image quality detection model, which outputs the benchmark evaluation result. Alternatively, other image quality detection models can be used to determine the benchmark evaluation result; this application does not impose any limitations on this. In one embodiment, after determining the benchmark evaluation result, the copy scanning protocol can be adjusted accordingly based on the comparison between the benchmark evaluation result and the target quality evaluation result. For example, when the quality evaluation result is a specific numerical value, the degree of adjustment of the scanning parameters can be determined based on the difference between the benchmark evaluation result and the target quality evaluation result. In another embodiment, the copy scanning protocol can also be adjusted based on the benchmark scanning protocol corresponding to the benchmark image. For example, the parameter values ​​of each scanning parameter included in the copy scanning protocol can be adjusted to values ​​corresponding to the parameter values ​​of each scanning parameter included in the basic scanning protocol. The above embodiments provide a simpler and more direct way to determine the adjustment direction of the copy scanning protocol.

[0068] Specifically, in one embodiment of this application, the image quality detection model is trained in the following manner:

[0069] S501: Acquire multiple medical image samples, wherein the medical image samples are labeled with reference image quality;

[0070] S503: Construct an image quality detection model, wherein training parameters are set in the image quality detection model;

[0071] S505: Input the multiple medical image samples into the image quality detection model respectively to generate prediction results;

[0072] S507: Based on the difference between the prediction result and the quality of the reference image, the training parameters are iteratively adjusted until the difference meets the preset requirements.

[0073] In this embodiment, after acquiring the medical image samples, an image quality detection model can be constructed, and the image quality detection model is equipped with training parameters. Then, the multiple medical image samples can be input into the image quality detection model to generate prediction results. In one embodiment of this application, the prediction results may include the quality assessment results corresponding to the input medical image samples. Finally, based on the difference between the prediction results and the quality of the reference image, the training parameters are iteratively adjusted until the difference meets a preset requirement. In some examples, the preset requirement may include that the difference between the prediction results and the quality of the labeled reference image is less than a difference threshold. The preset requirement may also include that the number of iterative adjustments is greater than a preset number threshold, which may be set to, for example, 50 times, 60 times, etc.

[0074] Furthermore, in one embodiment of this application, the image quality detection model is trained using various medical image samples of different quality defect types, and the various medical image samples are labeled with corresponding quality assessment results.

[0075] In this embodiment, to enable the trained image quality detection models to perform image quality assessments across multiple dimensions, different image quality detection models can be trained using different categories of medical image samples. Each category of medical image sample is labeled with quality assessment results for different defect types. These multiple medical image samples can be actual medical images with reference value, such as images obtained from the image libraries of multiple hospital radiology departments, or from the medical records of multiple patients who underwent medical image acquisition collected from multiple hospitals. Of course, relatively realistic medical image samples can also be obtained through other channels such as health check centers; this application does not impose any limitations on this. In one example, the medical image quality detection model can be an image contrast quality detection model, and the corresponding medical image samples can be labeled with different image contrasts. For positive samples, the image contrast is high, indicating high imaging quality.

[0076] In one embodiment of this application, an initial medical image and a medical image corresponding to the target scanning protocol can be displayed on an interactive interface, facilitating user comparison and providing a clear and intuitive display of the effect of scanning protocol adjustment. Specifically, after adjusting the copy scanning protocol based on the target quality assessment result to determine the target scanning protocol, the method further includes:

[0077] S601: Obtain the medical image corresponding to the target scanning protocol;

[0078] S603: Display the comparison results of the medical image and the initial medical image on the interactive interface.

[0079] In this embodiment, the scanning protocol adjustment device 105 can provide an interactive interface, which may include a command interface, a menu interface, a graphical user interface, etc. The interactive interface may include multiple display components, which can be used to display the initial medical image and the medical image corresponding to the target scanning protocol. In one embodiment of this application, the medical image and the initial medical image can be displayed in 2D or 3D view. Correspondingly, the medical image and the initial medical image can be two-dimensional images or three-dimensional images. After displaying the medical image and the initial medical image on the interactive interface, the medical image and the initial medical image can also be stored in the medical images of a Picture Archiving and Communication Systems (PACS) system, or in a database corresponding to the medical images.

[0080] The scanning protocol adjustment method provided in this application has been described in detail above. The following section will refer to the appendix... Figure 3 The present application describes a scanning protocol adjustment device 105, which includes:

[0081] The medical image acquisition module 1051 is used to acquire an initial medical image based on an initial scanning protocol.

[0082] The quality assessment result determination module 1053 is used to select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model;

[0083] The scanning protocol adjustment module 1055 is used to adjust the replica scanning protocol accordingly based on the target quality assessment result to determine the target scanning protocol; wherein the replica scanning protocol is created and generated according to the initial scanning protocol.

[0084] Optionally, in one embodiment of this application, the preset quality influencing factors are determined in at least one of the following ways:

[0085] In response to input commands, determine preset quality influencing factors;

[0086] Based on the characteristic data of the target object, preset quality influencing factors are determined; wherein, the image obtained by scanning the target object is the initial medical image.

[0087] Optionally, in one embodiment of this application, adjusting the copy scanning protocol based on the target quality assessment result to determine the target scanning protocol includes:

[0088] Determine the preset parameter adjustment rules corresponding to the preset quality influencing factors;

[0089] The copy scanning protocol is adjusted accordingly based on the target quality assessment results and the preset parameter adjustment rules to determine the target scanning protocol.

[0090] Optionally, in one embodiment of this application, adjusting the copy scanning protocol based on the target quality assessment result includes:

[0091] Obtain the benchmark evaluation results corresponding to the preset quality influencing factors;

[0092] Based on the comparison between the target quality assessment results and the benchmark assessment results, the copy scanning protocol is adjusted accordingly.

[0093] Optionally, in one embodiment of this application, after adjusting the copy scanning protocol accordingly based on the target quality assessment result to determine the target scanning protocol, the apparatus further includes:

[0094] Acquire the medical image corresponding to the target scanning protocol;

[0095] The comparison results between the medical image and the initial medical image are displayed on the interactive interface.

[0096] Optionally, in one embodiment of this application, the preset quality influencing factors include one or more of the following: image artifact degree, image spatial resolution, image contrast, image signal-to-noise ratio, image background noise, image uniformity, and fat suppression degree.

[0097] Optionally, in one embodiment of this application, the image quality detection model is trained using various medical image samples of different quality defect types, and the various medical image samples are labeled with corresponding quality assessment results.

[0098] Optionally, in one embodiment of this application, the image quality detection model is trained in the following manner:

[0099] Multiple medical image samples are acquired, and the medical image samples are labeled with reference image quality;

[0100] An image quality detection model is constructed, wherein training parameters are set in the image quality detection model;

[0101] The multiple medical image samples are input into the image quality detection model to generate prediction results;

[0102] Based on the difference between the prediction result and the quality of the reference image, the training parameters are iteratively adjusted until the difference meets the preset requirements.

[0103] According to the embodiments of this application, the scanning protocol adjustment device 105 can be used to execute the methods described in the embodiments of this application. The above and other operations and / or functions of each module in the scanning protocol adjustment device 105 are respectively for implementing the corresponding processes of the methods provided in the above embodiments. For the sake of brevity, they will not be described again here.

[0104] It should also be noted that the embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the accompanying drawings of the device embodiments provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0105] This application also provides a processing device, including a memory and a processor, wherein the memory stores computer program instructions, and the processor is configured to execute the computer program instructions to perform the methods described in the above embodiments.

[0106] The processing device can be a physical device or a cluster of physical devices, or it can be a virtualized cloud device, such as at least one cloud computing device in a cloud computing cluster. For ease of understanding, this application illustrates the structure of the processing device as an independent physical device.

[0107] like Figure 4As shown, the processing device 400 includes a processor and a memory for storing computer program instructions for the processor; wherein the processor is configured to implement the above-described apparatus when executing the computer program instructions. The electronic device 400 includes a memory 401, a processor 403, a bus 405, and a communication interface 407. The memory 401, processor 403, and communication interface 407 communicate via the bus 405. The bus 405 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 4 The symbol is represented by only one thick line, but this does not indicate that there is only one bus or one type of bus. Communication interface 407 is used for communication with external devices.

[0108] The processor 403 can be a central processing unit (CPU). The memory 401 can include volatile memory, such as random access memory (RAM). The memory 401 can also include non-volatile memory, such as read-only memory (ROM), flash memory, HDD or SSD, etc.

[0109] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0110] This application also provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the methods described in the above embodiments.

[0111] A computer-readable storage medium can be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), electrically programmable read-only memory (EPROM or flash memory), static random-access memory (SRAM), compact disc read-only memory (CD-ROM), digital video disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof.

[0112] The computer program instructions described herein can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer program instructions from the network and forwards them to a computer-readable storage medium within the respective computing / processing device.

[0113] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as "C" or similar languages. The computer program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state information from computer program instructions. These electronic circuits can execute computer program instructions to implement various aspects of this application.

[0114] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods and apparatus according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0115] These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0116] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other equipment to perform the functions / actions specified in one or more blocks of a flowchart and / or block diagram.

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.

[0118] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A scan protocol adjustment method, characterized by, The method includes: Acquire initial medical images based on the initial scanning protocol; Select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model; Determine the benchmark evaluation result corresponding to the preset quality influencing factor; wherein, the benchmark evaluation result is the quality evaluation result of the benchmark image corresponding to the preset quality influencing factor, and the benchmark image includes medical images that do not have the defect type corresponding to the preset quality influencing factor; Based on the comparison between the target quality assessment results and the benchmark assessment results, the replica scanning protocol is adjusted accordingly to obtain the target scanning protocol; the replica scanning protocol is created and generated based on the initial scanning protocol. The step of adjusting the copy scanning protocol based on the comparison between the target quality assessment result and the benchmark assessment result includes: When the evaluation result is a numerical value, the degree of adjustment of each scanning parameter in the copy scanning protocol is determined based on the difference between the benchmark evaluation result and the target quality evaluation result, and each scanning parameter is adjusted according to the degree of adjustment of each scanning parameter.

2. The method according to claim 1, characterized in that, The preset quality influencing factors are determined according to at least one of the following methods: In response to input commands, determine preset quality influencing factors; Based on the characteristic data of the target object, preset quality influencing factors are determined; wherein, the image obtained by scanning the target object is the initial medical image.

3. The method of claim 1, wherein, After adjusting the replica scanning protocol accordingly based on the target quality assessment results to determine the target scanning protocol, the method further includes: Acquire the medical image corresponding to the target scanning protocol; The comparison results between the medical image and the initial medical image are displayed on the interactive interface.

4. The method of claim 1, wherein, The preset quality influencing factors include one or more of the following: image artifact degree, image spatial resolution, image contrast, image signal-to-noise ratio, image background noise, image uniformity, and fat suppression degree.

5. The method of claim 1, wherein, The image quality detection model is trained using various medical image samples of different quality defect types, and each type of medical image sample is labeled with a corresponding quality assessment result.

6. The method of claim 1, wherein, The image quality detection model is trained as follows: Multiple medical image samples are acquired, and the medical image samples are labeled with reference image quality; An image quality detection model is constructed, wherein training parameters are set in the image quality detection model; The multiple medical image samples are input into the image quality detection model to generate prediction results; Based on the difference between the prediction result and the quality of the reference image, the training parameters are iteratively adjusted until the difference meets the preset requirements.

7. A scanning protocol adjustment apparatus characterized by, The device includes: The medical image acquisition module is used to acquire initial medical images based on the initial scanning protocol. The quality assessment result determination module is used to select a target image quality detection model that matches the preset quality influencing factors from multiple image quality detection models; input the initial medical image into the target image quality detection model, and output the target quality assessment result corresponding to the initial medical image through the target image quality detection model; A scanning protocol adjustment module is used to determine the benchmark evaluation result corresponding to the preset quality influencing factor; wherein, the benchmark evaluation result is the quality evaluation result of the benchmark image corresponding to the preset quality influencing factor, and the benchmark image includes medical images that do not have the defect type corresponding to the preset quality influencing factor; The scanning protocol adjustment module is further configured to adjust the replica scanning protocol accordingly based on the comparison between the target quality assessment result and the benchmark assessment result to obtain the target scanning protocol; the replica scanning protocol is created and generated based on the initial scanning protocol. The step of adjusting the copy scanning protocol based on the comparison between the target quality assessment result and the benchmark assessment result includes: When the evaluation result is a numerical value, the degree of adjustment of each scanning parameter in the copy scanning protocol is determined based on the difference between the benchmark evaluation result and the target quality evaluation result, and each scanning parameter is adjusted according to the degree of adjustment of each scanning parameter.

8. A computer-readable storage medium having stored thereon computer program instructions, wherein, When the computer program instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

Images