Magnetic resonance scan protocol determination method and magnetic resonance imaging method

Abstract

The application relates to a magnetic resonance scanning protocol determination method and a magnetic resonance imaging method. In response to a user input operation instruction, a task type corresponding to the operation instruction is obtained, when the task type is identified as an image scanning task in a medical task, an initial scanning protocol corresponding to the image scanning task is acquired, and a target scanning protocol for a scanning object is determined according to the initial scanning protocol; the task type includes a medical task and a non-medical task. In the embodiment of the application, when the task type of the operation instruction is an image scanning task, the corresponding initial scanning protocol is acquired, and the target scanning protocol for the scanning object is determined based on the initial scanning protocol, so that the user does not need to manually select a specific scanning protocol in a protocol package according to a scanning part described on a paper scanning sheet or an electronic scanning sheet, problems caused by incorrect manual selection of the scanning protocol can be greatly reduced, and the efficiency and accuracy of magnetic resonance scanning protocol determination are improved.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a method for determining magnetic resonance scanning protocol and a magnetic resonance imaging method. Background Technology

[0002] Scanning patients using Magnetic Resonance Imaging (MRI) protocols can yield magnetic resonance medical images. These images can be used to observe lesions and tissues, providing important information for subsequent treatment and efficacy evaluation.

[0003] Currently, technicians manually select the appropriate scanning protocol package from the protocol packages based on the scanning areas described on paper or electronic scanning forms. This process relies on the technician's experience and judgment, resulting in low efficiency and low accuracy in determining the scanning protocol. Summary of the Invention

[0004] Therefore, it is necessary to provide a magnetic resonance scanning protocol determination method and a magnetic resonance imaging method that can improve the accuracy and efficiency of magnetic resonance scanning protocol determination, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for determining magnetic resonance scanning protocols, including:

[0006] In response to a user-inputted operation command, the task type corresponding to the operation command is obtained; the task type includes medical tasks and non-medical tasks.

[0007] When the task type is identified as an image scanning task in medical tasks, the initial scanning protocol corresponding to the image scanning task is obtained;

[0008] The target scanning protocol for the object to be scanned is determined based on the initial scanning protocol.

[0009] In one embodiment, obtaining the initial scanning protocol corresponding to the image scanning task includes:

[0010] Obtain the matching results between the image scanning task and multiple candidate scanning protocols in a preset operation library;

[0011] If the matching result indicates the existence of a candidate scanning protocol that matches the image scanning task, reference information is obtained, including the status information of the scanning device and / or the feature information of the scanning object;

[0012] The candidate scanning protocol matching the image scanning task is adjusted based on the reference information to obtain the initial scanning protocol.

[0013] In one embodiment, determining the target scanning protocol for the scanned object based on the initial scanning protocol includes:

[0014] Output the initial scan protocol;

[0015] In response to the user's interactive operation command regarding the initial scanning protocol, the target scanning protocol is obtained.

[0016] In one embodiment, obtaining the reference information includes:

[0017] Obtain the real-time operating data of the scanning device corresponding to the image scanning task;

[0018] The real-time operating data is processed to identify the device status, thereby obtaining the status information of the scanning device.

[0019] In one embodiment, the medical task further includes an image processing task, and the method further includes:

[0020] When the operation instruction is recognized as an image processing task, the image processing method corresponding to the image processing task is obtained;

[0021] The image is processed based on the image processing method described above.

[0022] In one embodiment, the method for obtaining the image processing corresponding to the image processing task includes:

[0023] The corresponding detection model is invoked according to the operation instructions;

[0024] The image is detected based on the detection model to obtain analysis results;

[0025] The image processing method is matched based on the analysis results.

[0026] In one embodiment, the method further includes:

[0027] When the operation instruction is identified as a non-medical task, or when the matching result indicates that there is no candidate scanning protocol corresponding to the image scanning task, the user is interacted with through a pre-established interaction model.

[0028] In one embodiment, the method further includes:

[0029] Upon receiving the user's input operation command, the system acquires the user's operation log in real time to update the preset operation library based on the operation log.

[0030] In one embodiment, the method further includes:

[0031] When the task type is the image scanning task, output scanning precautions information corresponding to the image scanning task to the scanning object.

[0032] Secondly, this application also provides a magnetic resonance scanning protocol determination device, comprising:

[0033] The first response module is used to respond to the operation command input by the user and obtain the task type corresponding to the operation command; the task type includes medical tasks and non-medical tasks.

[0034] The first acquisition module is used to acquire the initial scanning protocol corresponding to the image scanning task when the task type is identified as an image scanning task in medical tasks.

[0035] The determination module is used to determine the target scanning protocol for the scanned object based on the initial scanning protocol.

[0036] Thirdly, this application also provides a magnetic resonance imaging method, the method comprising:

[0037] In response to a first operation command input by the user, the task type corresponding to the first operation command is obtained; the task type includes medical tasks and non-medical tasks.

[0038] When the task type is identified as an image scanning task in medical tasks, the initial scanning protocol corresponding to the image scanning task is obtained;

[0039] The target scanning protocol for the object to be scanned is determined based on the initial scanning protocol.

[0040] The target scanning protocol based on the invoked preset operation library is used to perform magnetic resonance scanning on the scanning object to obtain an initial magnetic resonance image;

[0041] In response to the second operation command input by the user, the task type corresponding to the second operation command is obtained;

[0042] When the second operation instruction is recognized as an image processing task, the initial magnetic resonance image is processed based on the image processing method corresponding to the image processing task to obtain the target magnetic resonance image.

[0043] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps provided in the first and third aspects.

[0044] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps provided in the first and third aspects.

[0045] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps provided in the first and third aspects.

[0046] The aforementioned magnetic resonance imaging (MRI) method and method for determining the MRI scanning protocol respond to user-inputted operation commands, obtain the task type corresponding to the operation command, and when the task type is identified as an image scanning task within medical tasks, acquire the initial scanning protocol corresponding to the image scanning task, and determine the target scanning protocol for the scanned object based on the initial scanning protocol. Task types include medical tasks and non-medical tasks. In this embodiment, when the task type of the operation command is an image scanning task, the corresponding initial scanning protocol is acquired, and the target scanning protocol for the scanned object is determined based on the initial scanning protocol. This eliminates the need for the user to manually select a specific scanning protocol from the protocol package based on the scanned area described on a paper or electronic scan sheet, significantly reducing problems caused by manually selecting an incorrect scanning protocol and improving the efficiency and accuracy of MRI scanning protocol determination. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a diagram illustrating the application environment of a magnetic resonance scanning protocol determination method in one embodiment.

[0049] Figure 2 This is a flowchart illustrating a method for determining a magnetic resonance scanning protocol in one embodiment;

[0050] Figure 3 This is a flowchart illustrating the magnetic resonance scanning protocol determination method in another embodiment;

[0051] Figure 4 This is a flowchart illustrating an initial scanning protocol determination method in one embodiment;

[0052] Figure 5 This is a flowchart illustrating a target scanning protocol determination method in one embodiment;

[0053] Figure 6 This is a schematic diagram of a magnetic resonance scanning system in one embodiment;

[0054] Figure 7 This is a structural block diagram of a magnetic resonance scanning protocol determination device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] Radiology departments typically prepare pre-defined "protocol packages" for various common scanning needs. These packages are optimized and validated multiple times to reduce errors and improve efficiency. Currently, the common procedure for selecting a scanning protocol is as follows: The patient arrives at the scanning room and provides a paper scan appointment form to the scanning technician, or provides a scan form including the scan area and precautions through the hospital's electronic system (Picture Archiving and Communication Systems, PACS). The scanning technician reads the scan form or reviews the scan form sent from the PACS system. For the scan area and sub-area described on the scan form, the technician selects the appropriate scanning protocol from the protocol package. Alternatively, the outpatient physician may consult in detail with the radiology department's scanning technician before the scan to establish various scan areas and corresponding scanning protocols. However, this approach may encounter the following problems:

[0057] Manual selection of scanning protocols: Scanners need to manually select the appropriate scanning protocol from the protocol package based on information on paper or electronic scan forms. This process relies on the technician's experience and judgment, which may lead to human error. Information transmission efficiency: If the hospital uses paper appointment forms, there may be risks of poor information transmission, loss or damage of paper forms. Even with electronic PACS systems, scanners need to spend time reviewing and interpreting them. Variability and complexity: Different cases may require different types or combinations of scanning protocols, which increases the complexity of selecting the correct scanning protocol. Patient waiting time: If multiple patients are involved, patient waiting time is increased. Information consistency issues: Since the information on the scan forms is manually entered and matched, there is a risk of inconsistencies in information or interpretation. Technician fatigue and distraction: Under high traffic or emergency conditions, scanners may face stress, which may affect the accuracy and efficiency of their determination of MRI scan protocols. Updates and training: Protocol packages and scanning equipment are frequently updated, and scanners need to continuously receive new training and guidance to ensure they can select the most appropriate scanning protocol. Personalized needs: To reduce error rates and improve efficiency, scanning procedures are usually standardized. This means that there is a standard operating procedure for specific conditions and scanning needs, while special medical conditions or cases may require personalized scanning settings, which further increases the variables that technicians need to consider when selecting scanning protocols; Error costs: A small mistake or inappropriate selection may lead to the need for rescanning, which not only increases costs but may also cause unnecessary trouble for patients; Communication barriers: Sometimes, there may be communication barriers between technicians and doctors or patients, resulting in scan requirements or precautions not being accurately conveyed, further increasing the risk of errors; Quality control and auditing: In order to ensure the highest level of medical quality, radiology departments usually conduct regular quality control and auditing.

[0058] As can be seen, the aforementioned methods heavily rely on human resources when selecting scanning protocols, lack highly personalized scanning solutions, and have a high risk of error in high-volume or complex cases. Therefore, to address these technical problems and further improve the accuracy and efficiency of scanning, this application proposes a method for determining magnetic resonance scanning protocols and a magnetic resonance imaging method.

[0059] The magnetic resonance scanning protocol determination method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown includes a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 1As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data for determining magnetic resonance imaging (MRI) scanning protocols in medical scans. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining MRI scanning protocols. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0060] Those skilled in the art will understand that Figure 1 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.

[0061] In one exemplary embodiment, such as Figure 2 As shown, a method for determining magnetic resonance scanning protocol is provided, which is applied to... Figure 1 The following explanation uses computer equipment as an example, including the following steps S201 to S203. Wherein:

[0062] S201, in response to the user's input operation command, obtain the task type corresponding to the operation command; the task type includes medical tasks and non-medical tasks.

[0063] In this embodiment, after obtaining the user-inputted operation instructions, keywords in the operation instructions can be identified to determine the task type corresponding to the operation instructions. For example, the operation instructions may include: performing a head MRI scan on the object being scanned, i.e., the operation instruction is a medical task; acquiring an MRI medical image of the object being scanned and performing noise reduction processing on the MRI medical image, i.e., the operation instruction is a medical task; reconstructing the projection data of the object being scanned to obtain a reconstructed image, i.e., the operation instruction is a medical task; maintenance of the MRI equipment, i.e., a medical knowledge query instruction; and identifying the symptoms of a cold, i.e., the operation instruction is a non-medical task.

[0064] In one possible implementation, a mapping between operation instructions and task types can be pre-established, and the user's operation instructions can be matched with the mapping to obtain the task type corresponding to the operation instructions.

[0065] In one possible implementation, keyword recognition can be performed on the operation command to obtain the corresponding imaging domain, such as magnetic resonance imaging (MRI) or computed tomography (CT). If the operation command falls within the imaging domain, further analysis can be performed to determine the corresponding task type within that domain. Combined with... Figure 3 As shown, keyword recognition is performed on the operation instructions. If the operation instructions are related to magnetic resonance imaging, the task type corresponding to the operation instructions is further determined.

[0066] Optionally, the operation commands can be voice commands, text commands, or key-triggered commands, and can process image, text, and voice data simultaneously.

[0067] S202, when the task type is identified as an image scanning task in medical tasks, obtain the initial scanning protocol corresponding to the image scanning task.

[0068] In this embodiment, the computer device stores multiple candidate scanning protocols for each imaging domain, as well as a correspondence between task types and candidate scanning protocols. When the task type is an image scanning task, the matching result between the image scanning task and multiple candidate scanning protocols can be obtained based on the correspondence, and the matched candidate scanning protocol can be used as the initial scanning protocol.

[0069] In one possible implementation, reference information can also be obtained, and the matched candidate scanning protocols can be adjusted based on the reference information to obtain an initial scanning protocol; the reference information includes the status information of the scanning device and / or the feature information of the scanning object.

[0070] In one possible implementation, if the matching result indicates that there is no candidate scanning protocol corresponding to the image scanning task, then the user-created scanning protocol is received and used as the initial scanning protocol for the scanning object; or, based on the image scanning task, a more similar scanning protocol is recommended to the user, while outputting a prompt message informing the user that there is no candidate scanning protocol matching the image scanning task, and the user needs to modify the recommended scanning protocol.

[0071] S203, determine the target scanning protocol for the object to be scanned based on the initial scanning protocol.

[0072] In the embodiments of this application, the following continues... Figure 3As shown, the initial scanning protocol can be used as the target scanning protocol for the scanned object. The computer device automatically controls the scanning equipment to perform scanning according to the target scanning protocol. For example, the operation command is: "Please perform scalp removal on Time-of-Flight (TOF) scans." The initial scanning protocol is three TOF protocols, and the scalp removal operation will be performed automatically. The user confirms. After confirmation, the three TOF protocols are used as the target scanning protocol, and mouse events from the preset operation library are automatically invoked to control the scanning equipment to perform the scanning operation based on the target scanning protocol.

[0073] In one possible implementation, the target scanning protocol could be the one modified by the user from the initial scanning protocol.

[0074] In the aforementioned magnetic resonance imaging (MRI) scan protocol determination method, in response to a user-inputted operation command, the task type corresponding to the operation command is obtained. When the task type is identified as an image scanning task within medical tasks, the initial scan protocol corresponding to the image scanning task is acquired, and the target scan protocol for the scanned object is determined based on the initial scan protocol. Task types include medical tasks and non-medical tasks. In this embodiment, when the task type of the operation command is an image scanning task, the corresponding initial scan protocol is acquired, and the target scan protocol for the scanned object is determined based on the initial scan protocol. This eliminates the need for the user to manually select a specific scan protocol from the protocol package based on the scanned area described on a paper or electronic scan sheet. This significantly reduces problems caused by manually selecting an incorrect scan protocol, improving the efficiency and accuracy of MRI scan protocol determination.

[0075] Figure 4 This is a flowchart illustrating an initial scanning protocol determination method in one embodiment, as shown below. Figure 4 As shown, this application embodiment relates to a possible implementation of how to obtain the initial scanning protocol corresponding to an image scanning task, including the following steps:

[0076] S401, Obtain the matching results of the image scanning task with multiple candidate scanning protocols in the preset operation library.

[0077] In this embodiment of the application, a preset operation library in the computer device stores multiple candidate scanning protocols for each imaging domain, as well as the correspondence between task types and candidate scanning protocols. In the case of an image scanning task within a medical task, the matching result between the image scanning task and multiple candidate scanning protocols can be obtained based on the correspondence. The matching result may indicate the existence of a candidate scanning protocol that matches the image scanning task, or it may indicate the absence of a candidate scanning protocol that matches the image scanning task.

[0078] S402, if the matching result indicates the existence of a candidate scanning protocol that matches the image scanning task, obtain reference information, which includes the status information of the scanning device and / or the feature information of the scanned object.

[0079] S403, adjust the candidate scanning protocol that matches the image scanning task according to the reference information to obtain the initial scanning protocol.

[0080] In this embodiment, candidate scanning protocols matching the image scanning task are adjusted based on reference information. For example, a user may want to speed up the scanning of an object by asking through an interactive model, "What methods can speed up the scan?" The computer device automatically detects the "speed up scanning" request in the question and triggers a preset acceleration optimization module. Based on system configuration and historical data, the current load of the scanning device, the scanning area, and the patient's specific conditions are determined, and a recommended acceleration scheme is automatically generated, such as automatically adjusting the scanning sequence (e.g., compressed sensing, parallel imaging technology) and providing optimized parameter suggestions. Based on the scanning site and clinical needs, the optimal scanning parameters are automatically selected without sacrificing image quality.

[0081] Optionally, multiple initial scan protocols can be generated for the operator to choose from, or multiple optimized optimal scan protocols can be provided directly as the initial scan protocols.

[0082] In this embodiment, the matching results between the image scanning task and multiple candidate scanning protocols in a preset operation library are obtained. If the matching result indicates the existence of a candidate scanning protocol matching the image scanning task, reference information is obtained. Based on the reference information, the candidate scanning protocol matching the image scanning task is adjusted to obtain an initial scanning protocol. Compared to simply providing "parameter suggestions" or "acceleration methods," this embodiment can automatically generate and execute an initial scanning protocol that meets specific requirements based on the specific conditions of the scanned object, the scanned area, and the status information of the scanning device, thus improving the real-time performance and personalization of the initial scanning protocol determination.

[0083] Figure 5 This is a flowchart illustrating a target scanning protocol determination method in one embodiment, as shown below. Figure 5 As shown, this application embodiment relates to a possible implementation of how to determine the target scanning protocol for the scanning object based on the initial scanning protocol, including the following steps:

[0084] S501, outputs the initial scan protocol.

[0085] S502, in response to the user's interactive operation command for the initial scanning protocol, obtains the target scanning protocol.

[0086] Optionally, the interactive operation command can be an editing command, a confirmation command, etc. Different interactive operation commands can be used to interact with each other. For example, if the interactive operation command is an editing command, it can be edited by voice operation, text box input, etc.; if the interactive operation command is a confirmation command, it can be confirmed by voice operation, button click, etc.

[0087] In this embodiment, the initial scanning protocol is displayed on the computer device's display interface in a combination of text and graphics, such as in text boxes, tables, or drop-down menus. For example, scanning angles and scanning ranges can be displayed in tables, and the body position of the scanned object can be displayed as images. For instance, if multiple initial scanning protocols are obtained, the user can select a target scanning protocol from them; alternatively, the optimal initial scanning protocol can be obtained, and the user can confirm it; or, if the optimal initial scanning protocol is obtained, the user can edit and modify it to obtain the target scanning protocol.

[0088] In this embodiment, an initial scanning protocol is output. In response to the user's interactive operation command for the initial scanning protocol, a target scanning protocol is obtained. The computer device recommends scanning protocols to the user based on the scanning task. The user determines the target scanning protocol for the target object based on the recommended candidate scanning protocols, thereby improving the efficiency and accuracy of target scanning protocol determination.

[0089] In one embodiment, obtaining reference information includes: obtaining real-time operating data of the scanning device corresponding to the image scanning task; and performing device status identification processing on the real-time operating data to obtain the status information of the scanning device.

[0090] Optionally, the real-time operating data varies depending on the scanning device. For example, for magnetic resonance imaging (MRI) devices, the real-time operating data can include radio frequency power, radio frequency pulse sequence, magnetic field strength, gradient field strength, gradient switching rate, and gradient linearity.

[0091] In this embodiment, during the operation of the scanning device, sensors continuously collect real-time operating data, which is then stored in a storage medium. If a candidate scanning protocol matching the image scanning task is found, the corresponding real-time operating data is retrieved from the storage medium, and the scanning device's status information is obtained based on this data. For example, a temperature sensor can be used to monitor the scanning device's temperature in real time, obtaining temperature data. This collected data is then sent to a computer, which performs device status identification processing on the real-time operating data to obtain the scanning device's status information.

[0092] In one possible implementation, real-time operational data could be acquired only during the scanning process of the scanning device.

[0093] like Figure 6 As shown, the status recognition processing of real-time operating data can be performed by using a preset status recognition network at the business layer to analyze and process the real-time operating data, or by using image processing algorithms to extract feature information from the real-time operating data and perform fault prediction based on the feature information to obtain the status information of the scanning device.

[0094] Furthermore, after obtaining the status information of the scanning device, the candidate scanning protocol that matches the image scanning task can be adjusted based on the status information and / or the feature information of the scanned object to obtain the initial scanning protocol.

[0095] Optionally, appropriate measures can be further determined based on the status information. For example, if the status information indicates that the MRI bed is difficult to move, possibly due to wear, blockage, or electronic malfunction, the user is advised to regularly inspect and lubricate mechanical components and remove any possible obstructions.

[0096] In this embodiment, real-time operating data of the scanning device corresponding to the image scanning task is acquired, and device status identification processing is performed on the real-time operating data to obtain the status information of the scanning device. This lays the foundation for determining the initial scanning protocol based on the status information and / or the feature information of the scanned object. Furthermore, it can automatically identify the status of the scanning device, predict malfunctions in advance, and has multiple security protection mechanisms to effectively prevent various potential risks.

[0097] In one embodiment, when the operation instruction is identified as an image processing task, the image processing method corresponding to the image processing task is obtained; and the image is processed based on the image processing method.

[0098] Optionally, the image processing method can be a post-processing algorithm for the scanned image, or it can be adjusting the parameters of the target scanning protocol to rescan, or it can be a combination of the post-processing algorithm and adjusting the parameters of the target scanning protocol.

[0099] In this embodiment of the application, taking post-processing algorithms as an example, the image processing task may include image preprocessing such as denoising, enhancement, and filtering. Denoising is used to eliminate random noise in the image, enhancement is used to adjust the image contrast and brightness to improve the visual effect, and filtering algorithms are used to highlight or weaken certain features in the image so that lesions and tissue boundaries that are not easy to observe can be clearly displayed from the processed image.

[0100] Image processing tasks can also include image segmentation, in which specific structures in an image are identified and located by dividing the image into multiple regions or objects. Image processing algorithms for image segmentation tasks can include thresholding (dividing regions based on pixel intensity), region growing (expanding regions from an initial point based on predetermined criteria), and edge detection (identifying the boundaries of tissue structures). Image segmentation is crucial for subsequent quantitative analysis and 3D reconstruction.

[0101] Image processing tasks can also include feature extraction, which extracts features such as shape, size, and texture from images. This is crucial for disease classification and diagnosis. For example, in tumor detection, feature extraction can help distinguish between benign and malignant tumors.

[0102] Image processing tasks can also include image registration, which aligns two or more images acquired at different times, using different devices, or under different conditions. The image registration algorithms used can be feature-based registration, intensity-based registration, etc.

[0103] Image processing tasks can also include image fusion, which combines images from different scanning devices (such as MRI and computed tomography (CT)) into a single image to integrate their respective strengths. For example, MRI provides better soft tissue contrast, while CT provides higher spatial resolution and bone detail. By fusing images from different modalities, more comprehensive information can be obtained, leading to a more accurate diagnosis.

[0104] Image processing tasks can also include quantitative analysis and visualization, performing quantitative analysis and advanced visualization of images. Quantitative analysis can involve volume measurement, density measurement, or calculation of other physiological parameters. Visualization techniques such as 3D reconstruction and virtual endoscopy can help doctors better understand complex anatomical structures and lesion morphologies.

[0105] In this embodiment, when the task type is medical image processing, an image processing algorithm corresponding to the medical image processing task is obtained, and the input medical image is processed based on the image processing algorithm. While processing medical scanning tasks, other types of tasks can also be processed, realizing multi-task processing. It integrates all the functions needed in the medical field and greatly improves the efficiency and accuracy of multi-task processing.

[0106] In one embodiment, obtaining an image processing method corresponding to an image processing task includes: invoking a corresponding detection model according to an operation instruction; performing detection on the image based on the detection model to obtain analysis results; and matching an image processing method based on the analysis results.

[0107] In this embodiment, for example, when a user discovers artifacts on a scanned image and the operation command is "What is the cause of the stripes on the image?", the system determines whether the user's operation command involves the "artifact recognition" module and identifies the keyword "stripes" artifact. A preset detection model is automatically invoked to identify the artifact type of the image and determine whether it conforms to known artifact patterns (e.g., motion artifacts, metallic artifacts).

[0108] Given known artifact patterns, automated correction suggestions are provided, recommending appropriate parameter adjustments to the target scanning protocol (such as increasing the number of scans or adjusting the trigger time).

[0109] If a user wishes to perform artifact correction, the computer equipment can automatically modify these parameters based on the analysis structure without further user intervention.

[0110] In this embodiment, the corresponding detection model is invoked according to the operation instruction; the image is detected based on the detection model to obtain the analysis result; and the image processing method is matched according to the analysis result. This embodiment can perform automated detection and correction operations on images through the built-in detection model, simplifying and automating the traditional manual operation steps. This not only speeds up image processing but also reduces the possibility of human error.

[0111] In one embodiment, when the operation instruction is identified as a non-medical task, or when the matching result shows that there is no candidate scanning protocol corresponding to the image scanning task, the user is interacted with through a pre-established interaction model.

[0112] In this embodiment, when the operation instruction is a non-medical task, interaction with the user is conducted through a pre-established interaction model. For example, the task type of the operation instruction may be a consultation task, such as obtaining maintenance knowledge of an MRI machine or suggesting medication for a cough; the task type of the operation instruction may be building a knowledge graph based on the operation instruction or creating a database, etc.

[0113] If the matching result indicates that no candidate scanning protocol exists for the image scanning task, a prompt message can be output through the interactive model to inform the user that no candidate scanning protocol exists and the user needs to manually create a scanning protocol. Alternatively, the user can be prompted with specific information about creating a scanning protocol during the interaction with the interactive model.

[0114] Optional, as described above Figure 3 As shown, the interaction model can be a large language model. When the task type is a non-medical task, or when the matching result does not have a candidate scanning protocol corresponding to the image scanning task, the corresponding sub-model is called to interact with the user.

[0115] Operation command samples can be input into the interaction model, and the prediction results output by the interaction model can be compared with the gold standard corresponding to the operation command samples. The interaction model can be trained based on the comparison results.

[0116] In this embodiment of the application, when the operation instruction is identified as a non-medical task, or when the matching result is that there is no candidate scanning protocol corresponding to the image scanning task, the user is interacted with through a pre-established interaction model. Through continuous interaction with the user and collection of data, the candidate scanning protocol can be continuously updated and optimized.

[0117] In one embodiment, upon receiving an operation command input from a user, the user's operation log is acquired in real time to update the preset operation library based on the operation log.

[0118] In this embodiment, the process continues as described above. Figure 6 As shown, upon receiving user input commands, the system acquires the user's operation log in real time. The operation log data is processed at the business layer. If the user modifies a candidate scanning protocol matched for an image scanning task, the candidate scanning protocol can be updated based on the operation log. If no candidate scanning protocol is matched for the image scanning task, and the user manually creates a scanning protocol, the user-created scanning protocol is retrieved from the operation log and used as a candidate scanning protocol for that task to update the preset operation library.

[0119] In this embodiment, upon receiving an operation command input by the user, the user's operation log is acquired in real time to update the preset operation library based on the operation log, thereby improving the candidate scanning protocol database and enhancing the accuracy and efficiency of target scanning protocol determination.

[0120] In one embodiment, when the task type is an image scanning task, scanning precautions information corresponding to the image scanning task is output to the scanning object.

[0121] In this embodiment, the process continues as described above. Figure 6 As shown, when the task type is medical imaging scanning, scanning precautions information can be output to the scanning object through voice messages, text boxes, virtual avatars, etc. The scanning precautions information is then output to the intelligent central interface of the interaction layer through the intelligent central gateway to interact with the scanning object.

[0122] Optionally, image data of the scanned object can be acquired during the scanning process, and dialogue can be conducted with the scanned object to identify the current state of the scanned object based on the image data or dialogue content.

[0123] Furthermore, if the scanned subject is detected to be in a state of tension, music, lighting, or voice commands can be used to help the subject relax.

[0124] In this embodiment of the application, when the task type is an image scanning task, scanning precautions information corresponding to the image scanning task is output to the scanning object. This can provide more refined services based on the individuality and scanning needs of each scanning object, thereby improving the user experience.

[0125] In one embodiment, a magnetic resonance imaging method is provided, the method comprising: responding to a first operation instruction input by a user, obtaining a task type corresponding to the first operation instruction; the task type including medical tasks and non-medical tasks; when the task type is identified as an image scanning task in medical tasks, obtaining an initial scanning protocol corresponding to the image scanning task; determining a target scanning protocol for the scanned object according to the initial scanning protocol; performing magnetic resonance scanning on the scanned object based on the target scanning protocol of a pre-defined operation library to obtain an initial magnetic resonance image; responding to a second operation instruction input by a user, obtaining a task type corresponding to the second operation instruction; when the second operation instruction is identified as an image processing task, processing the initial magnetic resonance image based on an image processing method corresponding to the image processing task to obtain a target magnetic resonance image.

[0126] In this embodiment, after obtaining the target scanning protocol, it can be invoked from a preset operation library. The object to be scanned is then scanned based on the invoked target scanning protocol to obtain an initial magnetic resonance image. The initial magnetic resonance image is then processed based on a second operation command input by the user to obtain the target magnetic resonance image. The task type of the second operation command can be a preprocessing task in medical procedures, such as noise reduction or contrast enhancement of the initial magnetic resonance image.

[0127] In this embodiment, when the task type of the operation instruction is an image scanning task, the corresponding initial scanning protocol is obtained. Based on the initial scanning protocol, the target scanning protocol for the scanned object is determined. This eliminates the need for the user to manually select a specific scanning protocol from the protocol package based on the scanned area described on a paper or electronic scanning form. This significantly reduces problems caused by manually selecting an incorrect scanning protocol, improving the efficiency and accuracy of magnetic resonance scanning protocol determination. Furthermore, scanning the object based on the target scanning protocol further improves the efficiency of magnetic resonance scanning.

[0128] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0129] Based on the same inventive concept, this application also provides a magnetic resonance scanning protocol determination apparatus for implementing the magnetic resonance scanning protocol determination method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the magnetic resonance scanning protocol determination apparatus provided below can be found in the limitations of the magnetic resonance scanning protocol determination method described above, and will not be repeated here.

[0130] In one exemplary embodiment, such as Figure 7 As shown, a magnetic resonance scanning protocol determination device is provided, comprising: a first response module 11, a first acquisition module 12, and a determination module 13, wherein:

[0131] The first response module 11 is used to respond to the operation command input by the user and obtain the task type corresponding to the operation command; the task type includes medical tasks and non-medical tasks.

[0132] The first acquisition module 12 is used to acquire the initial scanning protocol corresponding to the image scanning task when the task type is identified as an image scanning task in medical tasks.

[0133] The determination module 13 is used to determine the target scanning protocol for the scanned object based on the initial scanning protocol.

[0134] In one embodiment, the first acquisition module 12 is specifically used to acquire the matching results of the image scanning task with multiple candidate scanning protocols in a preset operation library; if the matching result indicates that there is a candidate scanning protocol that matches the image scanning task, it acquires reference information, which includes the status information of the scanning device and / or the feature information of the scanning object; and adjusts the candidate scanning protocol that matches the image scanning task according to the reference information to obtain an initial scanning protocol.

[0135] In one embodiment, the determining module 13 is specifically used to output the initial scanning protocol; and to obtain the target scanning protocol in response to the user's interactive operation command for the initial scanning protocol.

[0136] In one embodiment, the first acquisition module 12 is specifically used to acquire real-time operating data of the scanning device corresponding to the image scanning task; and to perform device status recognition processing on the real-time operating data to obtain the status information of the scanning device.

[0137] In one embodiment, the magnetic resonance scanning protocol determination device includes:

[0138] The second acquisition module is used to acquire the image processing method corresponding to the image processing task when the operation instruction is identified as an image processing task.

[0139] The first processing module is used to process images based on image processing methods.

[0140] In one embodiment, the second acquisition module is specifically used to call the corresponding detection model according to the operation instruction; to detect the image based on the detection model and obtain the analysis result; and to match the image processing method according to the analysis result.

[0141] In one embodiment, the magnetic resonance scanning protocol determination device includes:

[0142] The interaction module is used to interact with the user through a pre-established interaction model when the operation command is identified as a non-medical task, or when the matching result is that there is no candidate scanning protocol corresponding to the image scanning task.

[0143] In one embodiment, the magnetic resonance scanning protocol determination device includes:

[0144] The receiving module is used to obtain the user's operation log in real time when the user inputs an operation command, so as to update the preset operation library based on the operation log.

[0145] In one embodiment, the magnetic resonance scanning protocol determination device includes:

[0146] The output module is used to output scanning precautions information corresponding to the image scanning task to the scanning object when the task type is image scanning task.

[0147] In one exemplary embodiment, a magnetic resonance imaging apparatus is also provided, comprising:

[0148] The first response module is used to respond to the first operation command input by the user and obtain the task type corresponding to the operation command;

[0149] The first acquisition module is used to acquire the initial scanning protocol corresponding to the image scanning task when the task type is identified as an image scanning task in medical tasks.

[0150] The determination module is used to determine the target scanning protocol for the scanned object based on the initial scanning protocol;

[0151] The scanning module is used to perform magnetic resonance scanning on the object to be scanned based on the target scanning protocol of the preset operation library and obtain an initial magnetic resonance image.

[0152] The second response module is used to respond to the second operation command input by the user and obtain the task type corresponding to the second operation command;

[0153] The second processing module is used to process the initial magnetic resonance image based on the image processing method corresponding to the image processing task when the second operation instruction is identified as an image processing task, so as to obtain the target magnetic resonance image.

[0154] The modules in the aforementioned magnetic resonance scanning protocol determination device and magnetic resonance imaging device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware within or independently of the processor in a computer device, or stored in software within the memory of a computer device, so that the processor can call and execute the operations corresponding to each module.

[0155] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above method embodiments.

[0156] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above method embodiments.

[0157] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of any of the above method embodiments.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0159] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0161] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. 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 application should be determined by the appended claims.

Claims

1. A method for determining magnetic resonance scanning protocol, characterized in that, The method includes: In response to a user-inputted operation command, the task type corresponding to the operation command is obtained; the task type includes medical tasks and non-medical tasks. When the task type is identified as an image scanning task in medical tasks, the initial scanning protocol corresponding to the image scanning task is obtained; The target scanning protocol for the object to be scanned is determined based on the initial scanning protocol.

2. The method according to claim 1, characterized in that, The step of obtaining the initial scanning protocol corresponding to the image scanning task includes: Obtain the matching results between the image scanning task and multiple candidate scanning protocols in a preset operation library; If the matching result indicates the existence of a candidate scanning protocol that matches the image scanning task, reference information is obtained, including the status information of the scanning device and / or the feature information of the scanning object; The candidate scanning protocol matching the image scanning task is adjusted based on the reference information to obtain the initial scanning protocol.

3. The method according to claim 2, characterized in that, The step of determining the target scanning protocol for the scanned object based on the initial scanning protocol includes: Output the initial scan protocol; In response to the user's interactive operation command regarding the initial scanning protocol, the target scanning protocol is obtained.

4. The method according to claim 2, characterized in that, The obtained reference information includes: Obtain the real-time operating data of the scanning device corresponding to the image scanning task; The real-time operating data is processed to identify the device status, thereby obtaining the status information of the scanning device.

5. The method according to claim 1, characterized in that, The medical task also includes image processing tasks, and the method further includes: When the operation instruction is recognized as an image processing task, the image processing method corresponding to the image processing task is obtained; The image is processed based on the image processing method described above.

6. The method according to claim 5, characterized in that, The method for obtaining the image processing corresponding to the image processing task includes: The corresponding detection model is invoked according to the operation instructions; The image is detected based on the detection model to obtain analysis results; The image processing method is matched based on the analysis results.

7. The method according to claim 2, characterized in that, The method further includes: When the operation instruction is identified as a non-medical task, or when the matching result indicates that there is no candidate scanning protocol corresponding to the image scanning task, the user is interacted with through a pre-established interaction model.

8. The method according to any one of claims 2-4, 6 and 7, characterized in that, The method further includes: Upon receiving the user's input operation command, the system acquires the user's operation log in real time to update the preset operation library based on the operation log.

9. The method according to claim 1, characterized in that, The method further includes: When the task type is the image scanning task, output scanning precautions information corresponding to the image scanning task to the scanning object.

10. A magnetic resonance imaging method, characterized in that, The method includes: In response to a first operation command input by the user, the task type corresponding to the first operation command is obtained; the task type includes medical tasks and non-medical tasks. When the task type is identified as an image scanning task in medical tasks, the initial scanning protocol corresponding to the image scanning task is obtained; The target scanning protocol for the object to be scanned is determined based on the initial scanning protocol. The target scanning protocol based on the invoked preset operation library is used to perform magnetic resonance scanning on the scanning object to obtain an initial magnetic resonance image; In response to the second operation command input by the user, the task type corresponding to the second operation command is obtained; When the second operation instruction is recognized as an image processing task, the initial magnetic resonance image is processed based on the image processing method corresponding to the image processing task to obtain the target magnetic resonance image.

Images