Magnetic resonance image artifact early warning method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a magnetic resonance image artifact early warning method and device, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a historical magnetic resonance image and a current magnetic resonance image of a target user based on a preset image acquisition interval; based on the historical magnetic resonance image, identifying a historical head posture of the target user; recognizing a current head posture of the target user based on the current magnetic resonance image; performing head posture difference comparison based on the historical head posture and the current head posture to obtain head posture change data; performing expression recognition on the current magnetic resonance image to obtain a user test expression; based on the head posture change data and the user test expression, artifact early warning evaluation is carried out to obtain artifact early warning evaluation information, and the artifact early warning evaluation information comprises early warning information; and performing magnetic resonance image artifact early warning based on the early warning information. According to the embodiment of the invention, the accuracy of the magnetic resonance image can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a magnetic resonance image artifact warning method and device, an electronic device, and a storage medium. Background Art

[0002] Artifact warning refers to a prompt issued when possible artifacts are detected in the image during the imaging process, which reminds the operator or user to pay attention to avoid the artifact affecting the accuracy of the image. For example, artifact warning for magnetic resonance images can improve the accuracy of magnetic resonance images, thereby improving the accuracy of diagnostic results.

[0003] Currently, a common method for reducing artifacts in MRI images is to physically immobilize the subject's head to reduce the likelihood of artifacts. However, while physical immobilization can reduce large head movements, it cannot eliminate small displacements and can reduce subject comfort, thereby affecting the accuracy of MRI images. Therefore, how to provide early warning when artifacts are about to appear in MRI images to improve their accuracy has become a pressing technical issue. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a magnetic resonance image artifact warning method and device, electronic equipment and storage medium, which are intended to perform warning processing when artifacts are about to appear in the magnetic resonance image, so as to improve the accuracy of the magnetic resonance image.

[0005] To achieve the above-mentioned objectives, a first aspect of an embodiment of the present application provides a magnetic resonance image artifact warning method, the method comprising:

[0006] Based on a preset image acquisition interval, acquiring historical magnetic resonance images and current magnetic resonance images of the target user;

[0007] Based on the historical magnetic resonance images, identifying a historical head posture of the target user;

[0008] identifying a current head posture of the target user based on the current magnetic resonance image;

[0009] Comparing head posture differences based on the historical head posture and the current head posture to obtain head posture change data;

[0010] Performing facial expression recognition on the current magnetic resonance image to obtain a test expression of the user;

[0011] Performing an artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information, wherein the artifact warning assessment information includes warning information;

[0012] Based on the warning information, a magnetic resonance image artifact warning is performed.

[0013] In some embodiments, performing artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information includes:

[0014] Based on the preset warning change data, performing a data size assessment on the head posture change data to obtain data size assessment information;

[0015] Perform expression matching based on the preset warning expression information and the user's test expression to obtain expression matching information;

[0016] The artifact warning assessment information is determined based on the data size assessment information and the expression matching information.

[0017] In some embodiments, performing data size evaluation on the head posture change data based on the preset warning change data to obtain data size evaluation information includes:

[0018] Performing data alignment on the preset warning change data and the head posture change data to obtain a data alignment relationship;

[0019] Based on the data alignment relationship, the preset warning change data and the head posture change data are compared in numerical value to obtain the data size evaluation information.

[0020] In some embodiments, determining the artifact warning assessment information based on the data size assessment information and the expression matching information includes:

[0021] parsing the data size assessment information to obtain head posture maximum value information and head posture minimum value information, wherein the head posture maximum value information indicates that the head posture change data is greater than or equal to the preset warning change data, and the head posture minimum value information indicates that the head posture change data is less than the preset warning change data;

[0022] Analyzing the expression matching information to obtain matching success information and matching failure information;

[0023] When the data size evaluation information is the head posture minimum value information and the expression matching information is the matching failure information, generating artifact-free data, and performing data encapsulation on the artifact-free data to obtain the artifact warning evaluation information;

[0024] When the data size evaluation information is the head posture maximum value information, or the expression matching information is the matching success information, generating artifact pre-formation data, and performing data encapsulation on the artifact pre-formation data to obtain the artifact warning evaluation information;

[0025] When the data size evaluation information is the head posture maximum value information and the expression matching information is the matching success information, artifact pre-formation data is generated, and the artifact pre-formation data is data packaged to obtain the artifact warning evaluation information.

[0026] In some embodiments, identifying the user's historical head posture based on the historical magnetic resonance images includes:

[0027] Performing key point detection on the historical magnetic resonance image to obtain historical facial key points;

[0028] Perform spatial position perception on the historical facial key points to obtain the historical head posture.

[0029] In some embodiments, performing spatial position perception on the historical facial key points to obtain the historical head posture includes:

[0030] Selecting the origin of the historical facial key points to obtain target key points;

[0031] Based on the target key points, construct a head posture space coordinate system;

[0032] Based on the head posture space coordinate system, coordinate calculation is performed on the historical facial key points to obtain the key point space coordinates;

[0033] The historical head posture is determined based on the key point spatial coordinates.

[0034] In some embodiments, performing facial expression recognition on the current magnetic resonance image to obtain the user's facial expression includes:

[0035] Performing face detection on the current magnetic resonance image to obtain a user face image;

[0036] Performing key part detection on the user's face image to obtain position information of key facial parts;

[0037] Expression classification is performed based on the position information of the key facial parts to obtain the user's test expression.

[0038] To achieve the above-mentioned objectives, a second aspect of an embodiment of the present application provides a magnetic resonance image artifact warning device, the device comprising:

[0039] A magnetic resonance image acquisition module, configured to acquire historical magnetic resonance images and current magnetic resonance images of a target user based on a preset image acquisition interval;

[0040] a historical image recognition module, configured to recognize the historical head posture of the target user based on the historical magnetic resonance images;

[0041] a current image recognition module, configured to recognize a current head posture of the target user based on the current magnetic resonance image;

[0042] a head posture comparison module, configured to compare head posture differences based on the historical head posture and the current head posture to obtain head posture change data;

[0043] An image expression recognition module, configured to perform expression recognition on the current magnetic resonance image to obtain a test expression of the user;

[0044] An artifact warning assessment module is configured to perform an artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information, wherein the artifact warning assessment information includes warning information;

[0045] The image artifact warning module is used to provide a magnetic resonance image artifact warning based on the warning information.

[0046] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the method of the above-mentioned first aspect when executing the computer program.

[0047] To achieve the above-mentioned purpose, the fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the method of the above-mentioned first aspect.

[0048] The magnetic resonance image artifact warning method and device, electronic device and storage medium proposed in the present application obtain the historical magnetic resonance images of the target user and the current magnetic resonance image with a time interval of image acquisition interval from the historical magnetic resonance images, and identify the historical head posture of the target user based on the historical magnetic resonance images, identify the current head posture of the target user based on the current magnetic resonance image, perform head posture difference comparison based on the historical head posture and the current head posture, and obtain head posture change data, which can realize real-time monitoring of the target user's head posture changes, thereby improving the real-time performance of magnetic resonance image artifact warning. Secondly, facial expression recognition is performed on the current magnetic resonance image to obtain the user's facial expression. The subject's expression can understand the target user's emotional state during the magnetic resonance imaging process in real time, facilitate real-time analysis of the target user's emotional state, and further improve the real-time nature of the magnetic resonance image artifact warning. Finally, based on the head posture change data and the user's expression, an artifact warning evaluation is performed to obtain artifact warning evaluation information, making the evaluation of the magnetic resonance image more comprehensive, thereby improving the accuracy of the magnetic resonance image artifact warning. When the artifact warning evaluation information includes warning information, a magnetic resonance image artifact warning is performed, which can promptly remind the target user to reduce head posture changes or control emotions, thereby reducing the probability of artifacts in the magnetic resonance image and improving the accuracy of the magnetic resonance image. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of a magnetic resonance image artifact warning method provided by an embodiment of the present application;

[0050] Figure 2 yes Figure 1 Flowchart of step S102 in FIG.

[0051] Figure 3 yes Figure 2 Flowchart of step S202 in FIG.

[0052] Figure 4 yes Figure 1 Flowchart of step S105 in FIG.

[0053] Figure 5 yes Figure 1 Flowchart of step S106 in FIG.

[0054] Figure 6 yes Figure 5 Flowchart of step S501 in FIG.

[0055] Figure 7 yes Figure 5 Flowchart of step S503 in FIG.

[0056] Figure 8Schematic diagram of the structure of the magnetic resonance image artifact warning device provided in an embodiment of the present application;

[0057] Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0061] First, let’s analyze some of the terms used in this application:

[0062] Image artifacts: Image artifacts refer to false structures or deformations that appear in the image due to various factors during the imaging process and do not correspond to the actual object. In the field of medical imaging, such as magnetic resonance imaging and computed tomography, image artifacts can be caused by a variety of reasons, including subject movement, equipment limitations, and improper setting of imaging parameters. For example, in magnetic resonance imaging, slight head movements of the subject may cause blurred images or ghosting, thereby affecting the doctor's accurate diagnosis of the lesion. In addition, problems such as uneven magnetic field of the equipment and radio frequency interference may also cause image artifacts. These artifacts will reduce image quality and diagnostic accuracy, so various measures need to be taken during the imaging process to minimize or avoid their occurrence.

[0063] Artificial intelligence (AI) is a new technical discipline that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. A branch of computer science, AI seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. AI can simulate the information processes of human consciousness and thinking. It also encompasses the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0064] Artifact warning refers to a prompt issued when possible artifacts are detected in the image during the imaging process, which reminds the operator or user to pay attention to avoid the artifact affecting the accuracy of the image. For example, artifact warning for magnetic resonance images can improve the accuracy of magnetic resonance images, thereby improving the accuracy of diagnostic results.

[0065] Currently, a common method for reducing artifacts in MRI images is to physically immobilize the subject's head to reduce the likelihood of artifacts. However, while physical immobilization can reduce large head movements, it cannot eliminate small displacements and can reduce subject comfort, thereby affecting the accuracy of MRI images. Therefore, how to provide early warning when artifacts are about to appear in MRI images to improve their accuracy has become a pressing technical issue.

[0066] Based on this, the embodiments of the present application provide a magnetic resonance image artifact warning method and device, electronic equipment and storage medium, which are intended to perform warning processing when artifacts are about to appear in the magnetic resonance image, so as to improve the accuracy of the magnetic resonance image.

[0067] The magnetic resonance image artifact warning method and device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the magnetic resonance image artifact warning method in the embodiments of the present application is described.

[0068] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0069] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0070] The magnetic resonance image artifact warning method provided in the embodiment of the present application relates to the field of image processing technology. The magnetic resonance image artifact warning method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the magnetic resonance image artifact warning method, etc., but is not limited to the above forms.

[0071] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0072] Figure 1 This is an optional flowchart of the magnetic resonance image artifact warning method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S107.

[0073] Step S101, acquiring historical magnetic resonance images and current magnetic resonance images of a target user based on a preset image acquisition interval;

[0074] Step S102, identifying the target user's historical head posture based on the historical magnetic resonance images;

[0075] Step S103, identifying the current head posture of the target user based on the current magnetic resonance image;

[0076] Step S104, performing head posture difference comparison based on historical head posture and current head posture to obtain head posture change data;

[0077] Step S105, performing facial expression recognition on the current magnetic resonance image to obtain the user's facial expression;

[0078] Step S106, performing an artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information, wherein the artifact warning assessment information includes warning information;

[0079] Step S107: Performing a magnetic resonance image artifact warning based on the warning information.

[0080] Steps S101 to S107 shown in the embodiment of the present application are as follows: by acquiring the historical magnetic resonance images of the target user and the current magnetic resonance images with a time interval equal to the image acquisition interval from the historical magnetic resonance images, and identifying the historical head posture of the target user based on the historical magnetic resonance images, identifying the current head posture of the target user based on the current magnetic resonance images, performing head posture difference comparison based on the historical head posture and the current head posture, obtaining head posture change data, and being able to monitor the head posture changes of the target user in real time, thereby improving the real-time nature of magnetic resonance image artifact warning; secondly, performing facial expression recognition on the current magnetic resonance image to obtain the user's facial expression , it can understand the emotional state of the target user during the magnetic resonance imaging process in real time, facilitate real-time analysis of the emotional state of the target user, and further improve the real-time nature of the magnetic resonance image artifact warning. Finally, based on the head posture change data and the user's expression, an artifact warning evaluation is performed to obtain artifact warning evaluation information, making the evaluation of the magnetic resonance image more comprehensive, thereby improving the accuracy of the magnetic resonance image artifact warning. When the artifact warning evaluation information includes warning information, a magnetic resonance image artifact warning is performed, which can promptly remind the target user to reduce head posture changes or control emotions, thereby reducing the probability of artifacts in the magnetic resonance image and improving the accuracy of the magnetic resonance image.

[0081] In step S101 of some embodiments, the image acquisition interval refers to the length of time used to monitor and evaluate head movements and facial expressions that may cause artifacts during the magnetic resonance imaging process. The target user refers to a subject undergoing an MRI examination, where the subject can be a child or an adult, etc. The historical MRI image refers to a MRI image of the target user acquired at a moment before the current moment during the MRI imaging process. The current MRI image refers to a MRI image of the target user acquired at the current moment during the MRI imaging process. It should be noted that the length of time between the previous moment and the current moment is the image acquisition interval.

[0082] In an embodiment of the present application, when undergoing an MRI examination, the target user will be guided into the MRI machine and lie on a flat MRI examination bed. Then, the MRI examination bed will slowly slide into the MRI machine. Furthermore, the MRI machine can photograph the target user through a MRI imaging device, thereby obtaining an MRI examination video of the target user. Finally, by extracting video frames from the MRI examination video, the current MRI image of the target user can be obtained, and then historical MRI images can be extracted from the MRI examination video according to a pre-set image acquisition interval.

[0083] It should be noted that the magnetic resonance imaging device can be a camera fixed outside the magnetic resonance imaging machine or a reflective lens arranged on the top of the magnetic resonance imaging machine.

[0084] In step S102 of some embodiments, the historical head posture refers to the head posture of the target user in the historical magnetic resonance image, that is, the head posture of the target user at the beginning of the magnetic resonance examination process, wherein the head posture refers to the spatial position information between various parts of the target user's head.

[0085] In an embodiment of the present application, by capturing key points in historical magnetic resonance images, historical facial key points can be determined, and then the coordinate information of all historical facial key points can be queried to obtain the spatial position information of the target user's head in the historical magnetic resonance images, that is, the historical head posture.

[0086] For details, see Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S202:

[0087] Step S201, performing key point detection on historical magnetic resonance images to obtain historical facial key points;

[0088] Step S202: Perform spatial position perception on historical facial key points to obtain historical head posture.

[0089] In step S201 of some embodiments, historical facial key points refer to facial key points of the target user in the historical magnetic resonance image, wherein facial key points refer to specific points used to describe facial features, such as the tip of the nose, the center of the forehead, the center of the left eye, the left side of the mouth, the chin, the center of the right eye, the right side of the mouth, etc.

[0090] In an embodiment of the present application, edge detection, corner detection and other methods can be used to identify the contours and key points of the eyes, nose and other parts in historical magnetic resonance images, thereby obtaining historical facial key points. Alternatively, a trained key point recognition model can be used to perform key point recognition on historical magnetic resonance images to obtain historical facial key points, wherein the key point recognition model can be a deep learning model such as a convolutional neural network.

[0091] In step S202 of some embodiments, after obtaining the historical facial key points in the historical magnetic resonance image, any historical facial key point can be used as the target key point, and the head posture space coordinate system is constructed with the target key point as the coordinate origin. Furthermore, based on the constructed head posture space coordinate system, the spatial coordinate information of all historical facial key points can be obtained, and the historical head posture of the target user can be confirmed.

[0092] For details, see Figure 3 In some embodiments, step S202 may include but is not limited to steps S301 to S304:

[0093] Step S301, selecting the origin of historical facial key points to obtain target key points;

[0094] Step S302: constructing a head posture space coordinate system based on the target key points;

[0095] Step S303, calculating the coordinates of the historical facial key points based on the head posture space coordinate system to obtain the key point space coordinates;

[0096] Step S304: Determine the historical head posture based on the key point spatial coordinates.

[0097] In step S301 of some embodiments, the target key point refers to a point in the historical facial key points that serves as the coordinate origin.

[0098] In an embodiment of the present application, any point can be selected from the historical facial key points as the target key point. It should be noted that in order to facilitate the coordinate generation of the historical facial key points and reduce the complexity of calculation using the coordinate information of the historical facial key points, a historical facial key point in the middle position can be selected from multiple historical facial key points as the target key point.

[0099] In step S302 of some embodiments, the head posture space coordinate system refers to a three-dimensional rectangular space coordinate system used for facial posture positioning.

[0100] In an embodiment of the present application, a rectangular coordinate system that can represent three-dimensional space, namely, a head posture space coordinate system, can be constructed by drawing three mutually perpendicular straight lines and making these three straight lines intersect at the above-mentioned target key points.

[0101] In step S303 of some embodiments, the key point spatial coordinates refer to the coordinate information of the historical facial key points in the head posture space coordinate system.

[0102] In an embodiment of the present application, based on the above-constructed head posture spatial coordinate system, the horizontal distance, vertical distance and vertical distance between each historical facial key point and the above-mentioned target key point are calculated, and then the horizontal distance, vertical distance and vertical distance are used as the coordinate information of the historical facial key point, that is, the key point spatial coordinates.

[0103] In step S304 of some embodiments, after obtaining the key point spatial coordinates of each historical facial key point, the spatial distance between each historical facial key point can be calculated, thereby determining the spatial position relationship between various parts of the target user's head, that is, the historical head posture.

[0104] In steps S301 to S304 shown in this embodiment, any point among the historical facial key points is used as the target key point to construct a head posture space coordinate system, and then the key point space coordinates of each historical facial key point are calculated based on the constructed head posture space coordinate system. The spatial position relationship between various parts of the target user's head can be clearly and accurately obtained, making the acquired historical head posture more accurate.

[0105] In steps S201 to S202 shown in this embodiment, by performing key point detection on historical magnetic resonance images, historical facial key points are obtained, and the basic shape of the target user's head in the historical magnetic resonance images can be obtained. Then, based on the historical facial key points, key point coordinates are queried, and the historical head posture of the target user can be accurately obtained, thereby improving the accuracy of the historical head posture.

[0106] In step S103 of some embodiments, the current head posture refers to the head posture of the target user in the current magnetic resonance image, that is, the head posture of the target user during the magnetic resonance examination.

[0107] In an embodiment of the present application, the current head posture in the current magnetic resonance image can be identified by methods such as key point detection and spatial position perception. The process of performing key point detection on the current magnetic resonance image is the same as the above-mentioned process of performing key point detection on the historical magnetic resonance image, so it will not be repeated. In addition, the process of performing spatial position perception on the key points of the subject's face in the current magnetic resonance image is also the same as the above-mentioned process of performing spatial position perception on the key points of the historical face, so it will not be repeated.

[0108] In step S104 of some embodiments, the head posture change data refers to the difference data between the current head posture of the target user and the historical head posture. It should be noted that the head posture change data includes pitch angle, roll angle, yaw angle, displacement of facial key points in the head posture space coordinate system, etc., wherein the pitch angle refers to the rotation angle of the head around the horizontal axis in the head posture space coordinate system, indicating the up and down movement of the head. For example, when the target user raises his head upward, the pitch angle is a positive value, and when the target user lowers his head, the pitch angle is a negative value. The roll angle refers to the rotation angle of the head around the front and back axes in the head posture space coordinate system, indicating the left and right tilting movement of the head. For example, when the target user's head tilts to the right, the roll angle is a positive value, and when the target user's head tilts to the left, the roll angle is a negative value. The yaw angle refers to the rotation angle of the head around the vertical axis in the head posture space coordinate system, indicating the left and right rotation of the head. For example, when the target user turns his head to the right, the yaw angle is a positive value, and when the target user turns his head to the left, the yaw angle is a negative value.

[0109] In an embodiment of the present application, based on the historical head posture, the starting position of the target user's head in the head posture space coordinate system can be determined, and then based on the current head posture, the final position of the target user's head in the head posture space coordinate system can be determined. Furthermore, by comparing the difference between the starting position and the final position of the target user's head, the pitch angle, roll angle, yaw angle of the target user's head and the displacement of facial key points in the head posture space coordinate system and other data can be calculated respectively. Finally, the above-mentioned pitch angle, roll angle, yaw angle and displacement of facial key points in the head posture space coordinate system of the target user's head are summarized to obtain the head posture change data of the target user during the magnetic resonance examination.

[0110] It should be noted that in order to intuitively and accurately represent the head posture changes between the target user's current head posture and historical head posture, this application can establish a 3D digital head model of the target user before the target user undergoes an MRI examination, and then use the 3D digital head model to simulate the historical head posture and current head posture, thereby providing more accurate head posture change data for magnetic resonance image artifact warning.

[0111] In step S105 of some embodiments, the user test expression refers to the facial expression displayed by the target user during the magnetic resonance imaging process, such as anger, disgust, fear, happiness, sadness, surprise, neutrality, etc.

[0112] In an embodiment of the present application, facial expression information of the target user, that is, the user's test expression, can be obtained by performing expression recognition on the face image in the current magnetic resonance image.

[0113] For details, see Figure 4 In some embodiments, step S105 may include but is not limited to steps S401 to S403:

[0114] Step S401, performing face detection on the current magnetic resonance image to obtain a user face image;

[0115] Step S402: Detect key parts of the user's face image to obtain position information of key facial parts;

[0116] Step S403: performing expression classification based on the position information of key facial parts to obtain the user's test expression.

[0117] In step S401 of some embodiments, the user face image refers to an image region containing a face in the current magnetic resonance image.

[0118] In an embodiment of the present application, the Haar feature can be used to describe the local features of the current magnetic resonance image. The local features can reflect information such as edges and lines in the current magnetic resonance image. Furthermore, the eigenvalue of the Haar feature is calculated through the integral graph, thereby greatly improving the calculation efficiency. Secondly, an adaptive enhancement algorithm is used to train a cascade structure. Finally, the above-mentioned eigenvalue and the current magnetic resonance image are input into the cascade structure, which can gradually eliminate non-face areas, thereby obtaining the face area image in the current magnetic resonance image, that is, the user's face image.

[0119] In another embodiment of the present application, a trained convolutional neural network can be used to detect facial information in the current magnetic resonance image, thereby outputting a facial bounding box and generating a user facial image based on the facial bounding box, wherein the convolutional neural network can be SSD, YOLO, etc.

[0120] In step S402 of some embodiments, the facial key part position information refers to the position information of the facial key points, where the facial key points may be eyes, nose, mouth, etc.

[0121] In an embodiment of the present application, facial key points in the user's face image can be located by edge detection or corner detection methods to obtain the position information of key facial parts. In addition, a trained convolutional neural network can be used to extract key point features of the user's face image to achieve accurate positioning of facial key points, wherein the convolutional neural network can be an OpenFace or Hourglass network, etc.

[0122] In step S403 of some embodiments, after determining the position information of key facial parts in the user's facial image, the geometric features of the face can be calculated based on the position information of key facial parts, such as the degree of eye opening, eyebrow lift, angle of upturned or downturned corners of the mouth, etc. Furthermore, texture features can be extracted in the local area around the above-mentioned facial key points to obtain features such as texture changes of the facial skin and muscle tension. Secondly, methods such as local binary patterns can be used to further capture subtle differences in facial expressions. Finally, the above-mentioned geometric features, texture features and subtle differences of the face are input into a pre-trained expression classification model to determine the expression information displayed in the user's facial image, thereby obtaining the user's test expression.

[0123] In steps S401 to S403 shown in this embodiment, face detection is performed on the current magnetic resonance image to obtain a user face image, and then key parts detection is performed on the user face image to obtain position information of key facial parts. Expression classification is performed based on the position information of key facial parts to obtain the user's test expression, thereby improving the accuracy of expression recognition and making the user's test expression more accurate.

[0124] In step S106 of some embodiments, artifact warning assessment information refers to the results of a comprehensive analysis of head posture change data and the user's facial expressions during the magnetic resonance imaging process. It should be noted that the artifact warning assessment information is used to indicate whether artifacts are likely to occur and whether a warning is necessary. It should be noted that the artifact warning assessment information includes warning-capable information, which indicates that artifacts are likely to occur during the magnetic resonance imaging process and that a warning is necessary.

[0125] In an embodiment of the present application, the head posture change data and the user's expression can be evaluated separately, and then the evaluation results of the two can be combined for comprehensive analysis to generate artifact warning evaluation information.

[0126] For details, see Figure 5 In some embodiments, step S106 may include but is not limited to steps S501 to S503:

[0127] Step S501, based on the preset warning change data, performing a data size evaluation on the head posture change data to obtain data size evaluation information;

[0128] Step S502, performing expression matching based on the preset warning expression information and the user's test expression to obtain expression matching information;

[0129] Step S503 : Determine artifact warning assessment information based on the data size assessment information and the expression matching information.

[0130] In step S501 of some embodiments, the preset warning change data refers to a pre-set threshold of head posture change that requires a warning, wherein the head posture change threshold is used to measure whether the head posture change data has reached a level that requires a warning. The data size assessment information refers to the result of a numerical comparison between the head posture change data and the preset warning change data, and the data size assessment information is used to indicate whether the head posture change data is greater than, equal to, or less than the preset warning change data.

[0131] In an embodiment of the present application, by comparing the numerical value of the head posture change data with the numerical value of the preset warning change data, data size evaluation information indicating whether the head posture change data is smaller than the preset warning change data can be obtained.

[0132] For details, see Figure 6 In some embodiments, step S501 may include but is not limited to steps S601 to S602:

[0133] Step S601, aligning the preset warning change data and the head posture change data to obtain a data alignment relationship;

[0134] Step S602 : Based on the data alignment relationship, the preset warning change data and the head posture change data are compared in numerical value to obtain data size evaluation information.

[0135] In step S601 of some embodiments, the data alignment relationship refers to the correspondence between each item of data in the head posture change data and each item of data in the preset warning change data.

[0136] In an embodiment of the present application, the head posture change data includes pitch angle, roll angle, yaw angle, displacement of facial key points in the head posture space coordinate system, etc. Therefore, before comparing the head posture change data with the preset warning change data, it is necessary to align the various data in the head posture change data with the various data in the preset warning change data to obtain a data alignment relationship to avoid data comparison errors. For example, the head posture change data includes pitch angle, roll angle and yaw angle, then it is necessary to search for the pitch angle, roll angle and yaw angle in the preset warning change data accordingly, and align the pitch angle in the head posture change data with the pitch angle in the preset warning change data, align the roll angle in the head posture change data with the roll angle in the preset warning change data, and align the yaw angle in the head posture change data with the yaw angle in the preset warning change data.

[0137] In step S602 of some embodiments, after obtaining the data alignment relationship between each data in the head posture change data and each data in the preset warning change data, the numerical size of each data in the head posture change data is compared with the corresponding data in the preset warning change data, and the size comparison result of each data in the head posture change data and the corresponding data in the preset warning change data can be obtained, and then data size evaluation information is generated based on the size comparison result. It should be noted that the size comparison result can be the result that the head posture change data is greater than or equal to the preset warning change data, or the result that the head posture change data is less than the preset warning change data, wherein the result that the head posture change data is greater than or equal to the preset warning change data indicates that any one or more data in the head posture change data is greater than or equal to the corresponding one or more data in the preset warning change data, and the result that the head posture change data is less than the preset warning change data indicates that any one of the head posture change data is less than the corresponding data in the preset warning change data.

[0138] In steps S601 to S602 shown in this embodiment, the preset warning change data and the head posture change data are aligned to obtain a data alignment relationship, and then the preset warning change data and the head posture change data are compared in numerical value based on the data alignment relationship to obtain data size evaluation information. This can improve the accuracy of the numerical size comparison, make the data size evaluation information more accurate, avoid artifact warning errors caused by data comparison errors, and thus improve the accuracy of magnetic resonance image artifact warnings.

[0139] In step S502 of some embodiments, the preset warning expression information refers to a pre-set facial expression that can trigger an artifact warning, such as anger or disgust. The expression matching information refers to the matching result between the user's test expression and each facial expression in the preset warning expression information. The expression matching information is used to indicate whether the user's test expression is a facial expression that requires an artifact warning.

[0140] In an embodiment of the present application, by traversing the preset warning expression information, each facial expression that can trigger the artifact warning can be confirmed, and then the user's test expression can be matched with each facial expression type, and a matching result of the user's test expression and each facial expression can be generated to obtain expression matching information.

[0141] In step S503 of some embodiments, after obtaining the data size assessment information and the expression matching information, a comprehensive analysis can be performed on the data size assessment information and the expression matching information to determine whether an artifact warning is needed, and artifact warning assessment information can be generated based on the comprehensive analysis results.

[0142] For details, see Figure 7 In some embodiments, step S503 may include but is not limited to steps S701 to S705:

[0143] Step S701: parsing the data size evaluation information to obtain head posture maximum value information and head posture minimum value information, wherein the head posture maximum value information indicates that the head posture change data is greater than or equal to the preset warning change data, and the head posture minimum value information indicates that the head posture change data is less than the preset warning change data;

[0144] Step S702: parse the expression matching information to obtain matching success information and matching failure information;

[0145] Step S703: When the data size evaluation information is head posture small value information and the expression matching information is matching failure information, artifact-free data is generated and the artifact-free data is data-encapsulated to obtain artifact warning evaluation information;

[0146] Step S704: When the data size evaluation information indicates a large head posture value or the expression matching information indicates successful matching, artifact pre-formation data is generated and the artifact pre-formation data is data packaged to obtain artifact warning evaluation information.

[0147] Step S705 , when the data size evaluation information is head posture large value information and the expression matching information is matching success information, artifact pre-formation data is generated and the artifact pre-formation data is data packaged to obtain artifact warning evaluation information.

[0148] In steps S701 and S702 of some embodiments, by parsing the content contained in the data size evaluation information, the data comparison result represented by the data size evaluation information can be obtained. Specifically, the data comparison result can be head posture maximum value information indicating that the head posture change data is greater than or equal to the preset warning change data, or head posture minimum value information indicating that the head posture change data is less than the preset warning change data. Furthermore, by parsing the content contained in the expression matching information, matching success information indicating that the user's test expression successfully matches the preset warning expression information, or matching failure information indicating that the user's test expression fails to match the preset warning expression information can be obtained, wherein the matching success information indicates that the preset warning expression information contains a facial expression of the same type as the user's test expression, and the matching failure information indicates that the preset warning expression information does not contain a facial expression of the same type as the user's test expression.

[0149] In some embodiments, in steps S703 to S705, by comprehensively analyzing the data size evaluation information and the expression matching information after information parsing, it is possible to determine whether the current magnetic resonance image has a risk of artifacts, and based on this, generate artifact-free data indicating that the current magnetic resonance image has no risk of artifacts, and artifact-preformed data indicating that the current magnetic resonance image has a risk of artifacts. Further, the artifact-free data or the artifact-preformed data are data-encapsulated to obtain corresponding artifact warning evaluation information. Specifically, when the data size evaluation information is head posture small value information and the expression matching information is matching failure information, artifact warning evaluation information indicating that artifacts are unlikely to occur and no warning is required is generated; when the data size evaluation information is head posture large value information or the expression matching information is matching success information, artifact warning evaluation information indicating that artifacts may occur and a warning is required is generated; when the data size evaluation information is head posture large value information and the expression matching information is matching success information, artifact warning evaluation information indicating that artifacts may occur and a warning is required is generated.

[0150] In steps S701 to S705 shown in this embodiment, by performing information analysis on the data size evaluation information to obtain the maximum value information and the minimum value information of the head posture, and by performing information analysis on the expression matching information to obtain the matching success information and the matching failure information, the information expressed by the data size evaluation information and the expression matching information can be clarified. Furthermore, by performing a comprehensive analysis on the parsed data size evaluation information and the expression matching information, artifact warning evaluation information is generated, which improves the accuracy of the artifact evaluation, makes the generated artifact warning evaluation information more accurate and reliable, and thus improves the accuracy of the artifact warning of the magnetic resonance image.

[0151] In steps S501 to S503 shown in this embodiment, by performing a comprehensive analysis of the head posture change data and the user's facial expressions, it is possible to implement artifact warnings for magnetic resonance images in combination with the target user's head posture changes and current expressions. Compared with performing artifact warnings based solely on the target user's head posture changes, the accuracy of magnetic resonance image artifact warnings is improved. In addition, through the head posture change data, it is possible to monitor in real time whether artifacts will appear in the magnetic resonance image, thereby improving the real-time nature of the magnetic resonance image artifact warnings.

[0152] In step S107 of some embodiments, when artifact warning evaluation information is obtained and the artifact warning evaluation information is warning-capable information, a warning operation is performed on the target user who is in the magnetic resonance imaging process to reduce the target user's head posture changes and help the target user control his or her expression, thereby reducing the probability of artifacts appearing in the magnetic resonance image.

[0153] The present application obtains the historical magnetic resonance images of the target user and the current magnetic resonance images with the time interval between the historical magnetic resonance images and the historical magnetic resonance images as the image acquisition interval, and identifies the historical head posture of the target user based on the historical magnetic resonance images, identifies the current head posture of the target user based on the current magnetic resonance image, compares the head posture differences based on the historical head posture and the current head posture, and obtains the head posture change data, which can realize real-time monitoring of the head posture changes of the target user, thereby improving the real-time nature of the magnetic resonance image artifact warning. Secondly, the expression recognition is performed on the current magnetic resonance image to obtain the user's expression, which can understand the target user in real time. The emotional state during the magnetic resonance imaging process facilitates real-time analysis of the emotional state of the target user, further improving the real-time nature of magnetic resonance image artifact warning. Finally, based on the head posture change data and the user's facial expression, an artifact warning evaluation is performed to obtain artifact warning evaluation information, making the evaluation of the magnetic resonance image more comprehensive, thereby improving the accuracy of magnetic resonance image artifact warning. When the artifact warning evaluation information includes warning information, a magnetic resonance image artifact warning is performed, which can promptly remind the target user to reduce head posture changes or control emotions, thereby reducing the probability of artifacts in the magnetic resonance image and improving the accuracy of the magnetic resonance image.

[0154] See also Figure 8 The present application also provides a magnetic resonance image artifact warning device, which can implement the above-mentioned magnetic resonance image artifact warning method. The device includes:

[0155] The magnetic resonance image acquisition module 801 is used to acquire historical magnetic resonance images and current magnetic resonance images of a target user based on a preset image acquisition interval;

[0156] A historical image recognition module 802 is configured to recognize the target user's historical head posture based on historical magnetic resonance images;

[0157] A current image recognition module 803 is used to recognize the current head posture of the target user based on the current magnetic resonance image;

[0158] A head posture comparison module 804 is used to compare head posture differences based on historical head postures and current head postures to obtain head posture change data;

[0159] The image expression recognition module 805 is used to perform expression recognition on the current magnetic resonance image to obtain the user's expression;

[0160] An artifact warning evaluation module 806 is configured to perform an artifact warning evaluation based on the head posture change data and the user's expression, and obtain artifact warning evaluation information, wherein the artifact warning evaluation information includes warning information;

[0161] The image artifact warning module 807 is used to provide a warning of magnetic resonance image artifacts based on the warning information.

[0162] The specific implementation of the magnetic resonance image artifact warning device is basically the same as the specific embodiment of the magnetic resonance image artifact warning method described above, and will not be repeated here.

[0163] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the aforementioned magnetic resonance image artifact warning method. The electronic device can be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0164] See also Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0165] The processor 901 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0166] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called by the processor 901 to execute the magnetic resonance image artifact warning method of the embodiments of this application;

[0167] Input / output interface 903, used to implement information input and output;

[0168] Communication interface 904, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0169] Bus 905 , which transmits information between various components of the device (e.g., processor 901 , memory 902 , input / output interface 903 , and communication interface 904 );

[0170] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0171] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned magnetic resonance image artifact warning method is implemented.

[0172] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] The embodiments of the present application provide a magnetic resonance image artifact warning method, a magnetic resonance image artifact warning device, an electronic device, and a storage medium. Based on a preset image acquisition interval, the method obtains historical magnetic resonance images and a current magnetic resonance image of a target user, and then identifies the head posture of the historical magnetic resonance image to obtain the historical head posture of the target user. The method further identifies the head posture of the current magnetic resonance image to obtain the current head posture of the target user. Furthermore, based on the historical head posture and the current head posture, a head posture difference comparison is performed to obtain head posture change data. Secondly, facial expression recognition is performed on the above-mentioned current magnetic resonance image to obtain the user's test expression. Finally, based on the head posture change data and the user's test expression, an artifact warning evaluation is performed to obtain artifact warning evaluation information. When the artifact warning evaluation information contains warningable information, a magnetic resonance image artifact warning is performed to reduce the amplitude of the target user's head movement.

[0174] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0175] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0176] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0177] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0178] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0179] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0180] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0183] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0184] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A magnetic resonance image artifact warning method, characterized in that: The method comprises: Acquire historical magnetic resonance images and current magnetic resonance images of the target user based on a preset image acquisition interval; Based on the historical magnetic resonance images, identifying a historical head posture of the target user; identifying a current head posture of the target user based on the current magnetic resonance image; Comparing head posture differences based on the historical head posture and the current head posture to obtain head posture change data; Performing facial expression recognition on the current magnetic resonance image to obtain a test expression of the user; Performing an artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information, wherein the artifact warning assessment information includes warning information; Based on the warning information, a magnetic resonance image artifact warning is performed.

2. The method according to claim 1, characterized in that The performing of artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information includes: Based on the preset warning change data, performing a data size assessment on the head posture change data to obtain data size assessment information; Perform expression matching based on the preset warning expression information and the user's test expression to obtain expression matching information; The artifact warning assessment information is determined based on the data size assessment information and the expression matching information.

3. The method according to claim 2, characterized in that The step of performing data size evaluation on the head posture change data based on the preset warning change data to obtain data size evaluation information includes: Performing data alignment on the preset warning change data and the head posture change data to obtain a data alignment relationship; Based on the data alignment relationship, the preset warning change data and the head posture change data are compared in numerical value to obtain the data size evaluation information.

4. The method according to claim 2, characterized in that The determining the artifact warning assessment information based on the data size assessment information and the expression matching information includes: parsing the data size assessment information to obtain head posture maximum value information and head posture minimum value information, wherein the head posture maximum value information indicates that the head posture change data is greater than or equal to the preset warning change data, and the head posture minimum value information indicates that the head posture change data is less than the preset warning change data; Analyzing the expression matching information to obtain matching success information and matching failure information; When the data size evaluation information is the head posture minimum value information and the expression matching information is the matching failure information, generating artifact-free data, and performing data encapsulation on the artifact-free data to obtain the artifact warning evaluation information; When the data size evaluation information is the head posture maximum value information, or the expression matching information is the matching success information, generating artifact pre-formation data, and performing data encapsulation on the artifact pre-formation data to obtain the artifact warning evaluation information; When the data size evaluation information is the head posture maximum value information and the expression matching information is the matching success information, artifact pre-formation data is generated, and the artifact pre-formation data is data packaged to obtain the artifact warning evaluation information.

5. The method according to claim 1, wherein The identifying the historical head posture of the user based on the historical magnetic resonance image includes: Performing key point detection on the historical magnetic resonance image to obtain historical facial key points; Perform spatial position perception on the historical facial key points to obtain the historical head posture.

6. The method according to claim 5, characterized in that The performing spatial position perception on the historical facial key points to obtain the historical head posture includes: Selecting the origin of the historical facial key points to obtain target key points; Based on the target key points, construct a head posture space coordinate system; Based on the head posture space coordinate system, coordinate calculation is performed on the historical facial key points to obtain the key point space coordinates; The historical head posture is determined based on the key point spatial coordinates.

7. The method according to claim 6, characterized in that The performing expression recognition on the current magnetic resonance image to obtain the user's expression includes: Performing face detection on the current magnetic resonance image to obtain a user face image; Performing key part detection on the user's face image to obtain position information of key facial parts; Expression classification is performed based on the position information of the key facial parts to obtain the user's test expression.

8. A magnetic resonance image artifact warning device, characterized in that: The device comprises: A magnetic resonance image acquisition module, configured to acquire historical magnetic resonance images and current magnetic resonance images of a target user based on a preset image acquisition interval; a historical image recognition module, configured to recognize the historical head posture of the target user based on the historical magnetic resonance images; a current image recognition module, configured to recognize a current head posture of the target user based on the current magnetic resonance image; a head posture comparison module, configured to compare head posture differences based on the historical head posture and the current head posture to obtain head posture change data; An image expression recognition module, configured to perform expression recognition on the current magnetic resonance image to obtain a test expression of the user; An artifact warning assessment module is configured to perform an artifact warning assessment based on the head posture change data and the user's expression to obtain artifact warning assessment information, wherein the artifact warning assessment information includes warning information; The image artifact warning module is used to provide a magnetic resonance image artifact warning based on the warning information.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the data table partitioning method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the data table partitioning method according to any one of claims 1 to 7 is implemented.

Images