Intelligent auxiliary method for magnetic resonance imaging examination and related equipment

Abstract

The invention discloses an intelligent auxiliary method for magnetic resonance imaging examination and related equipment. The method comprises the following steps: extracting real-time imaging data obtained by examination in a magnetic resonance imaging examination process of a patient; performing motion artifact recognition on the real-time imaging data through a magnetic resonance imaging motion artifact recognition model obtained through pre-training; in a case where it is determined that the identified imaging motion artifacts reach a degree affecting the diagnosis, scanning is suspended and a patient cooperation prompt message is generated. The problems that in the traditional magnetic resonance imaging examination process, in the examination process, the patient cooperation is poor, and voice prompts such as the remaining examination duration are often manually prompted, and prompting is not timely can be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of smart medical care, and more specifically, the present invention relates to an intelligent auxiliary method for magnetic resonance imaging examination and related equipment. Background Art

[0002] During traditional magnetic resonance imaging examinations, voice prompts, including poor patient cooperation during the examination and the remaining examination time, are often given manually, and there are problems such as delayed prompts. In addition, the noise that may exist in the operating room during the manual prompt process will interfere with the patient's understanding. In the past, there was a lack of voice prompts before the injection of contrast agent, which easily caused the patient to be nervous during the injection, resulting in displacement and poor cooperation. In the past, when the patient's breath-holding scan was not effective, it was often judged by the examination technician, which required certain technical experience and there was also the problem of delayed prompts. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In order to solve the problems in the traditional magnetic resonance imaging examination process, including poor patient cooperation during the examination, the remaining examination time, etc., the voice prompts are often manually prompted, and the prompts are not timely. In a first aspect, the present invention proposes an intelligent auxiliary method for magnetic resonance imaging examination, the above method comprising:

[0005] Extracting real-time imaging data obtained during a patient's magnetic resonance imaging examination;

[0006] Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model;

[0007] If it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis, the scan is suspended and a patient cooperation prompting message is generated.

[0008] Optionally, also include:

[0009] When a patient undergoes a magnetic resonance imaging examination, recording the start time of the patient's examination and extracting the patient's examination item type;

[0010] Calculating the remaining duration of the magnetic resonance imaging examination based on the examination start time of the patient and the examination item type;

[0011] The remaining time is displayed to the patient.

[0012] Optionally, also include:

[0013] In the case where the examination item type includes at least one of the chest, abdomen and heart, generating a breath-holding cooperation prompt message for the patient, wherein the breath-holding cooperation prompt message includes a breath-holding prompt and a breath-holding stop prompt;

[0014] Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model;

[0015] When it is determined that the identified imaging motion artifact is a motion artifact caused by breathing, the scanning is suspended and a message prompting the patient to hold his breath is generated.

[0016] Optionally, also include:

[0017] Generate a patient cooperation reminder message before drug injection for user enhanced imaging.

[0018] Optionally, also include:

[0019] Collect video image information of the patient in the examination equipment;

[0020] identifying motion image information of the patient according to the video image information;

[0021] The identified imaging motion artifacts are corrected based on the motion image information.

[0022] Optionally, also include:

[0023] Determine the type and timing information of the working sound of the equipment in the examination equipment based on the start time of the examination of the patient and the type of the examination item;

[0024] A patient comfort prompt message is generated, wherein the comfort prompt message includes the type and timing information of the device working sound in the inspection device.

[0025] Optionally, also include:

[0026] Collect audio data of the patient in the examination equipment;

[0027] In the case where the audio data matches the working sound of the device in the examination device, a patient comfort prompt message is generated to prompt that the current noise is a normal working sound of the device in the examination device;

[0028] During the period when there is working sound of the equipment in the examination device, a cooperation prompt message is displayed to the patient and the doctor is reminded that there is communication interference in the current period to avoid the doctor from communicating with the patient in the current period.

[0029] In a second aspect, the present invention further provides an intelligent auxiliary device for magnetic resonance imaging examination, comprising:

[0030] An extraction unit, used for extracting real-time imaging data obtained during a magnetic resonance imaging examination of a patient;

[0031] An identification unit, configured to perform motion artifact identification on the real-time imaging data by using a pre-trained magnetic resonance imaging motion artifact identification model;

[0032] The auxiliary unit is used to terminate the scan and generate a patient cooperation prompt message when it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis.

[0033] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the intelligent auxiliary method for magnetic resonance imaging examination as described in any one of the first aspects above when executing the computer program stored in the memory.

[0034] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the intelligent auxiliary method for magnetic resonance imaging examination according to any one of the above items in the first aspect is implemented.

[0035] In summary, the intelligent auxiliary method for magnetic resonance imaging examination proposed in this application extracts real-time imaging data obtained during the patient's magnetic resonance imaging examination; uses a pre-trained magnetic resonance imaging motion artifact recognition model to identify motion artifacts on the real-time imaging data; when it is determined that the identified imaging motion artifacts have reached a level that affects the diagnosis, the scan is terminated and a patient cooperation prompt message is generated. As a result, real-time feedback and clear voice prompts can effectively reduce the patient's nervousness and help them better understand the examination process, thereby improving their cooperation. By terminating the scan in a timely manner and providing guidance, the occurrence of motion artifacts can be significantly reduced, thereby improving the quality of the image. Due to the improvement in image quality, doctors can make diagnoses more accurately and reduce the possibility of misdiagnosis or missed diagnosis.

[0036] The intelligent auxiliary method for magnetic resonance imaging examination of the present invention, and other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A schematic diagram of a flow chart of an intelligent auxiliary method for magnetic resonance imaging examination provided in an embodiment of the present application;

[0039] Figure 2 A schematic diagram of the structure of an intelligent auxiliary device for magnetic resonance imaging examination provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of the structure of an intelligent auxiliary electronic device for magnetic resonance imaging examination provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims 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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] In order to solve the problems in traditional MRI examinations, including poor patient cooperation during the examination, voice prompts for the remaining examination time, etc., which are often prompted manually and are not timely, please refer to Figure 1 , is a flow chart of an intelligent auxiliary method for magnetic resonance imaging examination provided in an embodiment of the present application, which may specifically include: steps S110 to S130.

[0043] S110, extracting real-time imaging data obtained during the magnetic resonance imaging examination of the patient.

[0044] S120, performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model.

[0045] S130: When it is determined that the identified imaging motion artifact reaches a level that affects the diagnosis, the scan is terminated and a patient cooperation prompt message is generated.

[0046] It is understandable that during the MRI examination, the device will continue to generate image data. The method first extracts this real-time data for subsequent analysis. The real-time imaging data is analyzed using a pre-trained motion artifact recognition model. Motion artifacts are usually caused by the patient moving during the scan, which will affect the clarity of the image and the accuracy of the diagnosis. Once a motion artifact is identified and it is determined that the degree of its impact on the diagnosis reaches a certain standard (such as affecting the key area of ​​the image), the system will automatically terminate the scan and generate a prompt message to remind the patient to remain still or make other necessary cooperation.

[0047] Exemplarily, a data extraction module is embedded in the MRI device to acquire imaging data in real time. Model training: A large number of training samples with motion artifacts are used to train the motion artifact recognition model to ensure that it can accurately identify different types of motion artifacts. During each scan, the image data is fed into the motion artifact recognition model for analysis in real time. A threshold for the impact of motion artifacts on image diagnosis is set, and once the threshold is exceeded, subsequent steps are triggered. Patients are informed of their current status through sound prompts or visual prompts (such as screen information) and are instructed on how to cooperate, such as keeping still, taking deep breaths, or adjusting their posture.

[0048] In summary, the intelligent auxiliary method for magnetic resonance imaging examination provided in the embodiment of the present application extracts real-time imaging data obtained during the magnetic resonance imaging examination of the patient; the real-time imaging data is subjected to motion artifact recognition through a pre-trained magnetic resonance imaging motion artifact recognition model; when it is determined that the recognized imaging motion artifact has reached a level that affects the diagnosis, the scan is terminated and a patient cooperation prompt message is generated. As a result, real-time feedback and clear voice prompts can effectively reduce the patient's nervousness and help them better understand the examination process, thereby improving their cooperation. By timely terminating the scan and providing guidance, the occurrence of motion artifacts can be significantly reduced, thereby improving the quality of the image. Due to the improvement in image quality, doctors can make diagnoses more accurately and reduce the possibility of misdiagnosis or missed diagnosis.

[0049] For example, when performing an abdominal MRI scan, the system extracts imaging data in real time and monitors motion artifacts. If the patient moves slightly during the scan, the system immediately stops the scan and prompts the patient to remain still through voice. After receiving the prompt, the patient was able to adjust his posture and finally successfully completed the scan, and the image quality was significantly improved. In the joint MRI examination, the model detected motion artifacts in the image, which affected the diagnosis. The system automatically stopped the scan and reminded the patient to take a deep breath and remain still. After adjustment, a clear image was obtained after rescanning, and the doctor was able to accurately judge the condition of the joint injury. In the brain MRI examination, the patient felt uneasy due to environmental noise, which caused movement. The system detected motion artifacts and automatically stopped the scan, prompting the patient to relax through voice. After receiving the instructions, the patient remained still and successfully completed the scan, and the image quality met the diagnostic requirements.

[0050] According to some embodiments, further comprising:

[0051] When a patient undergoes a magnetic resonance imaging examination, recording the start time of the patient's examination and extracting the patient's examination item type;

[0052] Calculating the remaining duration of the magnetic resonance imaging examination based on the examination start time of the patient and the examination item type;

[0053] The remaining time is displayed to the patient.

[0054] It is understandable that by recording the start time of the examination, the system can accurately track the progress of the examination. Combined with the estimated duration of the examination items, the remaining time can be dynamically calculated to help patients understand the progress of the examination. Showing patients the remaining time can help reduce their anxiety about the examination time. After understanding the approximate time of the examination, patients can better adjust their mental state and enhance their willingness to cooperate. Extracting the patient's examination item type enables the system to provide corresponding time prompts based on different types of MRI examinations to ensure the accuracy and relevance of the information. This personalized feedback can enhance the patient experience and make them feel valued.

[0055] Exemplarily, the system automatically records the start time of the examination when the patient enters the scanning room and is ready to start the examination. Based on the patient's appointment information or examination application, the system extracts the current examination item type. Based on the patient's examination start time and the estimated duration of the item, the remaining time is calculated. Remaining time = estimated duration - (current time - examination start time). The remaining time is displayed to the patient through the screen or voice prompt so that they can understand the progress of the examination.

[0056] For example, taking a brain MRI examination as an example, the start time of the examination is recorded as 10:00, and the examination type is extracted as "brain MRI", and the estimated duration is 30 minutes. At 10:10, the remaining time is calculated to be 20 minutes, and the system prompts the patient: "There are still 20 minutes left before the examination is completed, please stay relaxed." Taking an abdominal MRI examination as an example, the start time of the abdominal MRI examination is 14:00, and the system extracts the estimated duration of the project as 25 minutes. At 14:10, the remaining time is calculated to be 15 minutes, and the patient is prompted: "There are still 15 minutes left before the examination is completed, please continue to stay still.".

[0057] Understandably, by displaying the remaining time in real time, patients can clearly understand the progress of the examination, thereby reducing anxiety and uneasiness about time. This transparency of information can make patients more relaxed, thereby improving cooperation. When patients know the remaining examination time, they can better control their movements and reduce motion artifacts caused by tension or uneasiness, thereby improving image quality. By automatically recording the start time and calculating the remaining time, the communication burden between technicians and patients is reduced, and the efficiency of the examination is improved. The smoothness of the examination process is improved, reducing the need for repeated scans. The enhanced sense of care and attention felt by patients during the examination helps to improve the overall medical experience, thereby increasing patients' satisfaction and trust in medical services.

[0058] In some examples, this also includes:

[0059] In the case where the examination item type includes at least one of the chest, abdomen and heart, generating a breath-holding cooperation prompt message for the patient, wherein the breath-holding cooperation prompt message includes a breath-holding prompt and a breath-holding stop prompt;

[0060] Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model;

[0061] When it is determined that the identified imaging motion artifact is a motion artifact caused by breathing, the scanning is suspended and a message prompting the patient to hold his breath is generated.

[0062] Understandably, in chest, abdominal, and cardiac examinations, the patient's breathing has a significant impact on image quality. By generating breath-holding cooperation prompts, patients can be helped to remain still at critical moments, thereby reducing motion artifacts caused by breathing. Imaging data is analyzed in real time using a pre-trained motion artifact recognition model to identify artifacts caused by respiratory motion. This recognition allows for rapid response and automatic termination of scans, avoiding unnecessary repeat examinations. The system promptly communicates breath-holding and breath-stopping instructions to patients through sound and visual prompts to ensure that patients can cooperate to complete the examination, thereby improving the success rate of the examination and image quality.

[0063] Exemplarily, the system checks the type of project for the current patient, and if it includes at least one of the chest, abdomen, or heart, it proceeds to the next step. When it is confirmed that the patient is undergoing an examination for the above-mentioned parts, the system generates a breath-holding cooperation prompt message, including a breath-holding prompt (such as "Please hold your breath") and a breath-stopping prompt (such as "You can breathe"). During the scanning process, the system extracts imaging data in real time and analyzes the data using a trained motion artifact recognition model. If a motion artifact is detected and it is confirmed that the artifact is caused by breathing, the system immediately terminates the scan. After the scan is terminated, the system generates a breath-holding cooperation prompt message to the patient through sound or screen to guide him to cooperate in the next scan.

[0064] For example, in a chest MRI scan, the system identifies that the patient's examination type is "chest". When motion artifacts caused by breathing are detected in the imaging data, the system terminates the scan and prompts the patient: "Please hold your breath and stay still. The scan will be restarted soon." In an abdominal MRI examination, the patient moves due to breathing during the scan, and the system identifies the corresponding motion artifacts. At this time, the system immediately terminates the scan and gives a voice prompt: "Please hold your breath and prepare to rescan." When performing a cardiac MRI, the system analyzes the imaging data in real time and finds that the motion artifact is caused by the patient's breathing. The system terminates the scan and prompts: "Please hold your breath and stay still. It will start again later."

[0065] It is understandable that by generating breath-holding prompts, patients can effectively control their breathing at critical moments and reduce artifacts caused by respiratory movement, thereby improving image clarity and diagnostic accuracy. The mechanism of real-time motion artifact recognition and timely termination of scanning can effectively avoid repeated scans caused by motion artifacts, saving time and resources. Through clear breath-holding prompts and stop breath-holding instructions, patients can better understand and implement cooperation requirements, enhancing their initiative and sense of participation in the examination process. Transparency of information and timely feedback can reduce patients' anxiety, improve the overall medical experience, and make patients feel more cared for and valued during the examination process.

[0066] In some examples, this also includes:

[0067] Generate a patient cooperation reminder message before drug injection for user enhanced imaging.

[0068] In some examples, this also includes:

[0069] Collect video image information of the patient in the examination equipment;

[0070] identifying motion image information of the patient according to the video image information;

[0071] The identified imaging motion artifacts are corrected based on the motion image information.

[0072] It is understandable that when a patient undergoes an MRI scan, the system collects video image information in the examination device in real time to monitor the patient's motion state. By analyzing the collected video image information, the system can identify the patient's motion state and determine whether there are imaging artifacts caused by motion. Based on the motion image information, the system can correct the identified imaging motion artifacts. This correction can improve the quality of the final image, making the image clearer and more accurate.

[0073] Exemplarily, during the MRI scanning process, the system uses a camera or a built-in sensor to collect video image information of the patient in the examination device in real time. By analyzing the collected video, the motion image information generated by the patient during the scanning process, such as body micro-movement, breathing, etc., is identified. During the scanning process, the motion artifact recognition model is used to analyze the imaging data to identify artifacts caused by the patient's movement. According to the identified motion image information, the identified motion artifacts are corrected, and the algorithm is used to recalculate the image data to improve the image quality. The core idea of ​​correcting motion artifacts is to use the identified motion information to adjust the image data so that the final generated image is closer to the real static image. Common methods include image reconstruction, interpolation methods and denoising techniques. Set the following parameters: I (x, y, t) is the image data at time t, where x and y are spatial coordinates. R (x, y) is the reconstructed image data. M (x, y, t) is the identified motion model, which represents the patient's motion at time t. Δt is the scanning time interval. According to the identified motion image information, a motion model M (x, y, t) is constructed. For example, if the patient is displaced, a linear model can be used to represent M(x,y,t)=M0(x,y)+ΔM(x,y,t), where M0(x,y) is the baseline position and ΔM(x,y,t) is the motion offset. Use the motion model to reconstruct the image. Adjust the image data I(x,y,t). R(x,y)=I(xM(x,y,t),yM(x,y,t),t). This means that the original image data is spatially shifted and restored to an image in a static state. In order to better reconstruct the image, an interpolation method can be used to smooth the adjusted data. Common interpolation methods include bilinear interpolation or bicubic interpolation. For example, using the bilinear interpolation formula w i and w j is a weight function, defined as being inversely proportional to the distance to the target location. The image quality is further improved by a denoising algorithm. Median filtering or Gaussian filtering can be used. For example, the formula for Gaussian filtering is: Where σ is the standard deviation of the Gaussian distribution, which controls the degree of smoothness. Therefore, by using the motion model and image reconstruction, the blur and artifacts caused by motion can be effectively eliminated, and the clarity of the image can be improved. After interpolation and denoising, the signal-to-noise ratio of the final image is improved, and the details are clearer, which is conducive to the doctor's accurate diagnosis. The algorithm can achieve real-time or near real-time image correction to meet the rapid needs of MRI scanning. For example, in the case of artifacts caused by respiratory motion, the motion model may be a periodic function that describes the frequency and amplitude of breathing. By dynamically adjusting the image, the algorithm can effectively reduce the image blur caused by breathing. Through the above steps and parameters, the algorithm can effectively correct the motion artifacts in MRI imaging, and ultimately improve the quality and accuracy of the image.

[0074] For example, during a chest MRI scan, the system collects video image information of the patient in real time. Analysis found that the patient had slight respiratory movements during the scan, and the system subsequently identified related motion artifacts. Based on the motion image information, the system corrects the artifacts, and the quality of the final generated image is significantly improved. During the abdominal MRI process, the system records the patient's video information and detects slight movements of the patient due to discomfort during the examination. After identifying the motion artifacts, the system corrects the image based on the motion image information, and finally obtains a clear abdominal image to help doctors make an accurate diagnosis. During a cardiac MRI examination, the system collects video information of the patient and identifies his frequent respiratory movements caused by anxiety. The system corrects imaging artifacts by analyzing motion image information to ensure the clarity and accuracy of the final image, thereby improving the reliability of the diagnosis.

[0075] It is understandable that through the real-time acquisition and analysis of video image information, the system can effectively identify and correct motion artifacts, thereby improving the clarity and accuracy of the final image. The artifact correction mechanism based on motion image information makes image processing more intelligent and precise, which helps to overcome the limitations of traditional methods. The real-time monitoring and feedback mechanism can promptly remind patients to remain still and reduce movements caused by anxiety, thereby improving cooperation. By effectively correcting motion artifacts, the chance of repeated examinations due to poor image quality is reduced, saving medical resources and time. The patient's experience during the examination is improved, and they can feel higher professionalism and care, thereby improving satisfaction.

[0076] In some examples, this also includes:

[0077] Determine the type and timing information of the working sound of the equipment in the examination equipment based on the start time of the examination of the patient and the type of the examination item;

[0078] A patient comfort prompt message is generated, wherein the comfort prompt message includes the type and timing information of the device working sound in the inspection device.

[0079] It is understandable that MRI equipment generates specific audio signals when working, and these signals vary depending on the examination items. By analyzing the type and timing information of the equipment's working sound, patients can be helped to better understand the examination process. When patients are examined, informing them of the equipment's working sound and its timing information in advance can effectively reduce the patient's tension and make them feel more relaxed and safe during the examination. Providing patients with personalized soothing prompts based on different examination item types and equipment working sound characteristics can enhance the patient's overall experience.

[0080] Exemplarily, when the patient enters the MRI scanning room and is ready to begin the examination, the system automatically records the start time of the examination. Based on the patient's appointment information or examination application, the current examination item type (such as brain, abdomen, heart, etc.) is extracted. Based on the type of examination item, the system queries the database to obtain the equipment working sound type and timing information corresponding to the item (such as tone changes, duration, etc.). Combined with the equipment working sound type and timing information, a patient soothing reminder message is generated, which may be: "In the next examination, you will hear some sounds. These sounds are made by the normal operation of the equipment, and the sounds will last for about 10 seconds at each stage. Please stay relaxed and the equipment will automatically complete the examination."

[0081] Exemplarily, during a brain MRI examination, the system records the start time as 10:00, and extracts the examination item type as "brain". According to the database, the system determines that the equipment working sound type is "low-frequency humming" and the timing information is "once every 20 seconds, lasting 5 seconds". The system generates a prompt: "You will hear a low-frequency humming sound during the examination, once every 20 seconds, for about 5 seconds. Rest assured, the equipment is working properly."; In an abdominal MRI examination, the start time is 14:00, and the system extracts the examination type as "abdomen". The working sound type is "high-frequency pulse sound", and the timing information is "once every 15 seconds, lasting 2 seconds". The system prompts: "Please note that you will hear a high-frequency pulse sound, once every 15 seconds, for about 2 seconds. Please try to relax."; In a cardiac MRI examination, the start time is 09:00, and the examination type is "heart". The equipment working sound type is "periodic drum sound", and the timing information is "once every 10 seconds, lasting 3 seconds". System-generated prompt: "During the following inspection, you will hear a periodic drum sound, once every 10 seconds, lasting about 3 seconds. Please remain relaxed and the inspection will proceed smoothly."

[0082] It is understandable that informing patients of the type and timing of the device's working sound in advance can effectively reduce patients' fear of unknown noises and alleviate their anxiety. Through soothing prompts, patients can cooperate with the examination more relaxedly and reduce the incidence of motion artifacts caused by tension. Personalized soothing strategies make patients feel more cared for and valued, improving the overall medical experience. Clear information delivery can enhance patients' trust in the medical process and make them more willing to accept follow-up examinations and treatments.

[0083] In some examples, this also includes:

[0084] Collect audio data of the patient in the examination equipment;

[0085] In the case where the audio data matches the working sound of the device in the examination device, a patient comfort prompt message is generated to prompt that the current noise is a normal working sound of the device in the examination device;

[0086] During the period when there is working sound of the equipment in the examination device, a cooperation prompt message is displayed to the patient and the doctor is reminded that there is communication interference in the current period to avoid the doctor from communicating with the patient in the current period.

[0087] It is understandable that during the MRI examination, the system collects audio data in the device in real time in order to analyze the type and characteristics of noise. By comparing it with the working sound of the device, it is determined whether the current audio data belongs to the normal working sound of the device. This matching mechanism helps to confirm the source of the noise, thereby eliminating the patient's doubts. During the period of confirming the working sound of the device, the system can generate a soothing reminder message and show it to the patient through visual prompts. In addition, it can also prompt doctors to avoid communicating with patients when noise interference occurs to reduce communication misunderstandings and discomfort.

[0088] Exemplarily, during an MRI scan, the system uses a built-in microphone or an external sensor to collect audio data from the patient in the device. The collected audio data is matched with the characteristics of the device's working sound to determine whether the current audio is a normal device working sound. For example, the frequency characteristics and amplitude changes of the audio signal are calculated using audio feature extraction and signal processing algorithms. When it is confirmed that the audio data matches the device's working sound, the system generates a patient-reassuring reminder message, such as: "The current noise is the normal working sound of the device. Please rest assured that it will not affect your examination." During the period when the device's working sound is present, a cooperation reminder message is displayed to the patient through the screen or voice. At the same time, the system prompts the doctor: "There is currently communication interference, please avoid communicating with the patient."

[0089] For example, in a brain MRI scan, the audio data collected by the system matches the low-frequency humming characteristics of the device. The system generates a prompt: "The current noise is the normal working sound of the device, please stay relaxed." At the same time, it prompts the doctor: "There is currently AC interference, please avoid communicating with the patient." During the abdominal MRI process, the system detects high-frequency pulse sounds and confirms that it matches the working sound of the device. The system prompts the patient: "The high-frequency sound you hear is the normal working sound of the device, please don't worry." And remind the doctor: "There is currently AC interference, please avoid communicating with the patient." In a cardiac MRI examination, the audio data captured by the system is consistent with the periodic drum sound characteristics. The system generates a soothing prompt: "The drum sound you hear is the sound of the normal operation of the device, please rest assured." And prompts the doctor: "There is currently AC interference, please suspend communication with the patient.".

[0090] It is understandable that by clearly indicating that the current noise is the normal working sound of the equipment, the patient's fear of unknown noise is reduced, thereby improving their comfort and cooperation. In the case of interference from the working sound of the equipment, the system promptly reminds the doctor to avoid communication, which can effectively reduce communication misunderstandings and improve inspection efficiency. The real-time audio matching and feedback mechanism enables potential interference factors during the inspection process to be identified in a timely manner, reducing motion artifacts caused by patient anxiety. The collaboration of personalized comfort prompts and doctor communication helps to improve patients' trust and satisfaction with medical services.

[0091] See also Figure 2 , an embodiment of the intelligent auxiliary device for magnetic resonance imaging examination in the embodiment of the present application may include:

[0092] An extraction unit 21 is used to extract real-time imaging data obtained during a magnetic resonance imaging examination of a patient;

[0093] An identification unit 22, configured to perform motion artifact identification on the real-time imaging data by using a pre-trained magnetic resonance imaging motion artifact identification model;

[0094] The auxiliary unit 23 is used to terminate the scan and generate a patient cooperation prompt message when it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis.

[0095] In summary, the intelligent auxiliary device for magnetic resonance imaging examination provided in the embodiment of the present application extracts real-time imaging data obtained during the magnetic resonance imaging examination of the patient; uses a pre-trained magnetic resonance imaging motion artifact recognition model to identify motion artifacts on the real-time imaging data; when it is determined that the identified imaging motion artifacts have reached a level that affects the diagnosis, the scan is terminated and a patient cooperation prompt message is generated. As a result, real-time feedback and clear voice prompts can effectively reduce the patient's nervousness and help them better understand the examination process, thereby improving their cooperation. By terminating the scan in a timely manner and providing guidance, the occurrence of motion artifacts can be significantly reduced, thereby improving the quality of the image. Due to the improvement in image quality, doctors can make diagnoses more accurately and reduce the possibility of misdiagnosis or missed diagnosis.

[0096] like Figure 3 As shown, the embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for intelligent assistance in magnetic resonance imaging examination are implemented:

[0097] Extracting real-time imaging data obtained during a patient's magnetic resonance imaging examination;

[0098] Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model;

[0099] If it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis, the scan is suspended and a patient cooperation prompting message is generated.

[0100] Since the electronic device introduced in this embodiment is a device used to implement an intelligent auxiliary device for magnetic resonance imaging examination in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation method of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0101] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiment:

[0102] Extracting real-time imaging data obtained during a patient's magnetic resonance imaging examination;

[0103] Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model;

[0104] If it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis, the scan is suspended and a patient cooperation prompting message is generated.

[0105] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0110] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 The process of intelligent assistance for magnetic resonance imaging examination in the corresponding embodiment.

[0111] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0116] 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 is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0117] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent auxiliary method for magnetic resonance imaging examination, characterized in that: include: Extracting real-time imaging data obtained during a patient's magnetic resonance imaging examination; Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model; If it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis, the scan is suspended and a patient cooperation prompting message is generated.

2. The method according to claim 1, characterized in that Also includes: When a patient undergoes a magnetic resonance imaging examination, recording the start time of the patient's examination and extracting the patient's examination item type; Calculating the remaining duration of the magnetic resonance imaging examination based on the examination start time of the patient and the examination item type; The remaining time is displayed to the patient.

3. The method according to claim 2, characterized in that Also includes: In the case where the examination item type includes at least one of the chest, abdomen and heart, generating a breath-holding cooperation prompt message for the patient, wherein the breath-holding cooperation prompt message includes a breath-holding prompt and a breath-holding stop prompt; Performing motion artifact recognition on the real-time imaging data using a pre-trained magnetic resonance imaging motion artifact recognition model; When it is determined that the identified imaging motion artifact is a motion artifact caused by breathing, the scanning is suspended and a message prompting the patient to hold his breath is generated.

4. The method according to claim 1, characterized in that Also includes: Generate a patient cooperation reminder message before drug injection for user enhanced imaging.

5. The method according to any one of claims 1 to 4, characterized in that Also includes: Collect video image information of the patient in the examination equipment; identifying motion image information of the patient according to the video image information; The identified imaging motion artifacts are corrected based on the motion image information.

6. The method according to any one of claims 2 to 5, characterized in that: Also includes: Determine the type and timing information of the working sound of the equipment in the examination equipment based on the start time of the examination of the patient and the type of the examination item; A patient comfort prompt message is generated, wherein the comfort prompt message includes the type and timing information of the device working sound in the inspection device.

7. The method according to any one of claims 1 to 6, characterized in that Also includes: Collect audio data of the patient in the examination equipment; In the case where the audio data matches the working sound of the device in the examination device, a patient comfort prompt message is generated to prompt that the current noise is a normal working sound of the device in the examination device; During the period when there is working sound of the equipment in the examination device, a cooperation prompt message is displayed to the patient and the doctor is reminded that there is communication interference in the current period to avoid the doctor from communicating with the patient in the current period.

8. An intelligent auxiliary device for magnetic resonance imaging examination, characterized in that: include: An extraction unit, used for extracting real-time imaging data obtained during a magnetic resonance imaging examination of a patient; An identification unit, configured to perform motion artifact identification on the real-time imaging data by using a pre-trained magnetic resonance imaging motion artifact identification model; The auxiliary unit is used to terminate the scan and generate a patient cooperation prompt message when it is determined that the identified imaging motion artifact has reached a level that affects the diagnosis.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the intelligent auxiliary method for magnetic resonance imaging examination as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent auxiliary method for magnetic resonance imaging examination according to any one of claims 1 to 7 is implemented.

Images