Real-time monitoring system in magnetic resonance scanning magnet cavity

Abstract

The invention discloses a real-time monitoring system in a magnetic resonance scanning magnet cavity, and relates to the technical field of medical instruments, the system comprises a data acquisition and transmission module, a data processing optimization module, a magnetic field early warning modeling module and an abnormity early warning processing module; through highly-integrated module design, real-time synchronous acquisition and processing of physiological data and magnetic resonance image data of a patient are realized, specifically, a data acquisition and transmission module utilizes flexible diamagnetic sensors including an optical fiber sensor and a non-metal piezoelectric material sensor to accurately capture body surface pressure and temperature changes of the patient, and the pressure and temperature changes of the body surface of the patient are accurately acquired; and meanwhile, an internal structure image acquired by magnetic resonance imaging equipment is rapidly uploaded to a cloud data center through a wireless transmission technology, so that the accuracy and timeliness of data acquisition are improved, and interference and limitation possibly brought by a traditional wired transmission mode are greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, in particular to a real-time monitoring system in a magnetic resonance scanning magnet cavity. Background Art

[0002] With the continuous advancement of medical technology, magnetic resonance imaging (MRI), as a non-invasive, radiation-free medical imaging technology, is playing an increasingly important role in clinical diagnosis. MRI uses a strong magnetic field and radio frequency pulses to cause hydrogen nuclei in the human body to resonate, thereby generating signals. These signals are processed by a computer to form detailed images, providing doctors with rich diagnostic information. However, during the MRI scan process, the patient needs to be in a strong magnetic field environment for a long time, which may lead to some potential safety risks. For example, changes in the patient's physiological state may be affected by the magnetic field, and may even cause discomfort or emergency situations. At the same time, the quality of MRI scans is also affected by many factors, including the patient's body position, physiological state, and the setting of scanning parameters. Therefore, how to ensure the safety and quality of the MRI scanning process has become an urgent problem to be solved in the current field of medical technology.

[0003] Traditional MRI scanning monitoring technology mainly relies on regular inspections and manual adjustments by medical staff. This method has obvious limitations. First, since medical staff cannot monitor the patient's physiological status and scan images in real time and continuously, it is difficult to promptly detect and deal with potential safety hazards. Second, manual adjustment of scanning parameters is not only inefficient but also easily affected by human factors, resulting in fluctuations in scan quality. In addition, traditional technology lacks the ability to comprehensively analyze patient physiological data and scan images, and cannot accurately assess the patient's condition and scan quality, thus limiting the application effect of MRI technology in clinical diagnosis.

[0004] Therefore, the development of a real-time monitoring system inside the MRI scanning magnet cavity will greatly improve the safety and accuracy of the MRI scanning process, provide doctors with more comprehensive and accurate diagnostic information, and thus promote the further development of medical imaging technology. Summary of the Invention

[0005] The present invention aims to address the shortcomings of existing technologies by providing a real-time monitoring system within the magnetic resonance imaging (MRI) magnet cavity. By integrating four modules: data acquisition and transmission, processing optimization, magnetic field warning modeling, and abnormality warning and disposal, the system enables real-time monitoring and analysis of the patient's physiological status and scanned images. The system uses flexible antimagnetic sensors to collect data, combined with cloud-based processing technology, to accurately assess the patient's condition. In the event of an abnormality, it provides timely warnings, automatically adjusts scanning parameters, or activates emergency equipment. This invention effectively improves the safety and diagnostic efficiency of MRI scans, providing a highly efficient and accurate solution for medical institutions.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring system for the interior of a magnetic resonance scanning magnet cavity, the system comprising: a data acquisition and transmission module, a data processing and optimization module, an image enhancement module, a magnetic field early warning modeling module, and an abnormality early warning and disposal module;

[0007] The data acquisition and transmission module collects the patient's physiological data of contact pressure and body surface temperature in real time through a flexible anti-magnetic sensor, collects image data of the patient's internal structure using a magnetic resonance imaging device, and synchronously transmits the physiological data and image data in real time to a cloud data center through wireless transmission technology;

[0008] The data processing optimization module receives data from the cloud data center, filters out abnormal values and calibrates deviation data for physiological data, and eliminates image offset and performs denoising for magnetic resonance images.

[0009] The magnetic field warning modeling module uses a magnetic field strength sensor to monitor the magnetic field strength, builds an evaluation and prediction model based on the patient's physiological data, calculates the patient's status evaluation value through an algorithm formula, and compares it with the warning threshold to determine whether the patient's status is abnormal;

[0010] The abnormal warning and handling module: once an abnormal signal is received, it notifies medical staff through sound and light alarms and wireless communication, and automatically adjusts scanning parameters or activates emergency equipment according to preset rules.

[0011] Furthermore, the installation position and acquisition frequency of the physiological data acquisition equipment in the data acquisition and transmission module, the flexible anti-magnetic sensor is an optical fiber sensor and a non-metallic piezoelectric material sensor, wherein the optical fiber sensor is distributed at the contact point between the cavity wall and the patient, and is used to collect the patient's surface pressure data in real time, and the acquisition frequency is 10-20 times / minute; the non-metallic piezoelectric material sensor is attached to the inner layer of the cavity wall, and is located in a non-contact area 1-3 cm away from the patient's body surface, and indirectly obtains the surface temperature data by detecting the deformation signal of the inner layer of the cavity wall caused by the patient's body temperature change, and the acquisition frequency is 3-5 times / minute.

[0012] Furthermore, in the data processing optimization module, for physiological data, the 3σ principle based on statistical analysis is used to filter out abnormal values. Assume that the physiological data sequence is X={x1,x2,…,x n}, calculate the mean of the series And standard deviation σ, the formulas are: If a data point x j satisfy It is judged as an abnormal value and marked for removal; the linear regression calibration algorithm is used to calibrate the deviation data. Assuming that there is a linear relationship between the physiological parameter y and the time t, the normal physiological data samples {(t1,y1), (t2,y2),…, (t m ,y m )}, t is time, y is physiological parameter, and the coefficients a and b in the linear regression equation are determined using the least squares method. The regression equation is: y = at + b, and the calculation formulas for the coefficients a and b are: in For the physiological data point y with deviation k , according to the corresponding time t k , calibrate using the calibrated equation, the calibrated equation is: corrected =at k +b, where y corrected is the calibrated data.

[0013] Furthermore, the data processing optimization module eliminates the offset of the magnetic resonance image through a linear transformation formula. Let the original image be I(A, B), and the offset vector (ΔA, ΔB) is calculated according to the difference between the ideal position and the actual position of the image feature point. The corrected image is I corrected (A, B), the calculation formula is: corrected (A, B) = I(A + ΔA, B + ΔB), where (A, B) is the coordinate of the original image; a denoising preprocessing method based on local neighborhood averaging is used. For each pixel I(A, B) in the image, a neighborhood window of size c × c is selected with c = 3 at the center, and the average value of all pixels in the neighborhood is calculated. The formula is: The original pixel value is replaced by the neighborhood average value to obtain the denoised image I denoised (A,B), the formula is

[0014] Furthermore, in the construction of the patient status assessment and prediction model in the magnetic field warning modeling module, the patient's physiological parameter set is P = {p1, p2, ..., p n}, the corresponding weight set is and The enhanced image is denoted as I f , the weight set of image features for patient status evaluation is and The calculation formula of the patient status assessment value S is: Among them, f j is the contribution of image features to the patient status, μ iis the physiological parameter p i The mean of i is the standard deviation, and α is the adjustment coefficient with a value range of [0,1]. It is used to balance the proportion of physiological data and image features in the assessment of patient status and is adjusted according to specific diagnostic needs.

[0015] Furthermore, the magnetic field warning modeling module uses the warning trigger formula to judge the patient's status, and the patient status evaluation value is S, and the warning threshold is S th , the trigger warning formula is: Wherein τ is a preset percentage threshold, 0<τ≤0.3.

[0016] Furthermore, the warning threshold S in the magnetic field warning modeling module th Calculation, assuming the magnetic field strength is Q, the upper limit of the normal fluctuation range of physiological parameters in a non-magnetic field environment is R 0max , the lower limit is R 0min The influence coefficient of magnetic field intensity on the upper limit of physiological parameters is ξ, the nonlinear adjustment index of magnetic field intensity is η, the attenuation coefficient of magnetic field intensity on the lower limit of physiological parameters is ζ, the exponential decay rate of magnetic field intensity is ρ, and the warning threshold S th The calculation formula is:

[0017] Furthermore, the preset rules in the abnormal warning and handling module are:

[0018] Physiological parameter abnormality rules: trigger an alarm when the heart rate exceeds 120 beats / minute or is lower than 50 beats / minute; the image abnormality rules include: automatic rescan when the image signal-to-noise ratio is lower than 20dB;

[0019] Image anomaly rules: When the monitoring system identifies an anomaly in the MRI or visible light image, it takes appropriate measures based on the type and severity of the anomaly;

[0020] Equipment operating status rules: operating parameter settings for the magnetic resonance scanning equipment itself.

[0021] Compared with the existing technology, the real-time monitoring system for magnetic resonance scanning magnet cavity has the following beneficial effects:

[0022] 1. The present invention realizes real-time synchronous acquisition and processing of patient physiological data and magnetic resonance image data through a highly integrated module design. Specifically, the data acquisition and transmission module uses flexible anti-magnetic sensors, including optical fiber sensors and non-metallic piezoelectric material sensors, to accurately capture changes in patient surface pressure and temperature. At the same time, combined with the internal structure images obtained by the magnetic resonance imaging equipment, they are quickly uploaded to the cloud data center through wireless transmission technology. This not only improves the accuracy and timeliness of data acquisition, but also greatly reduces the interference and limitations that may be caused by traditional wired transmission methods. In the data processing optimization module, the system uses advanced statistical analysis methods to screen outliers and uses linear regression calibration algorithms to accurately correct deviation data, ensuring the reliability of subsequent analysis. In addition, the offset correction and denoising processing of magnetic resonance images further improve the image quality, providing doctors with a clearer and more accurate diagnostic basis, which not only optimizes the magnetic resonance scanning process, but also significantly improves the accuracy and efficiency of diagnosis.

[0023] 2. The present invention constructs a refined assessment and prediction model by real-time monitoring of magnetic field strength and combining it with the patient's physiological data. The model can dynamically calculate the patient's status assessment value and compare it with the preset warning threshold in real time. Once an abnormality is found, the warning mechanism is immediately triggered. This intelligent early warning system can not only effectively prevent the potential risks to patients caused by magnetic field changes, but also detect abnormal conditions in equipment operation in advance to avoid accidents. The abnormal warning and disposal module further enhances the system's emergency response capability. Through sound and light alarms and wireless communication technology, it quickly notifies medical staff to take corresponding measures. At the same time, the system can also automatically adjust scanning parameters or start emergency equipment according to preset rules to ensure that the normal operation of the equipment can be quickly restored in an emergency and protect the safety and health of patients.

[0024] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0026] Figure 1 A flow chart of a real-time monitoring system for magnetic resonance scanning magnets;

[0027] Figure 2 This is a framework diagram of the real-time monitoring system inside the magnetic resonance scanning magnet cavity. DETAILED DESCRIPTION

[0028] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0029] Example 1:

[0030] Hospital clinical diagnosis scenario.

[0031] In the magnetic resonance imaging examination room of a large general hospital, a patient who came to the hospital with symptoms of headache and blurred vision was arranged to undergo a brain magnetic resonance imaging scan to rule out the possibility of brain lesions.

[0032] Data acquisition and transmission: In the magnetic cavity, the fiber optic sensors are closely distributed at the contact point between the cavity wall and the patient's head. According to the set acquisition frequency, the surface pressure data of the patient's head is collected in real time at a rhythm of 10-20 times / minute. At the same time, the non-metallic piezoelectric material sensor is attached to the inner layer of the cavity wall. In the non-contact area 1-3 cm away from the patient's body surface, the deformation signal of the inner layer of the cavity wall caused by the patient's body temperature change is detected at a frequency of 3-5 times / minute to indirectly obtain the patient's head surface temperature data. While collecting physiological data, the magnetic resonance imaging equipment starts working, performs a full-scale scan of the patient's brain, and obtains image data of the patient's internal brain structure. Subsequently, these physiological data and image data are synchronously transmitted to the cloud data center in real time using wireless transmission technology. Figure 2 for subsequent processing and analysis.

[0033] Data processing optimization: The cloud data center transmits the received data to the data processing optimization module. Figure 1 As shown, for the collected physiological data sequence, let X = x1, x2, ..., x n , according to the 3σ principle based on statistical analysis to filter outliers, first calculate the mean of the series The formula is: Then calculate the standard deviation σ, the formula is If a data point x j satisfy It is determined to be an abnormal value and marked for removal. For the deviation data, the linear regression calibration algorithm is used for calibration. Assuming that there is a linear relationship between the physiological parameter y and the time t, the normal physiological data samples (t1, y1), (t2, y2), ..., (t m ,y m), use the least squares method to determine the coefficients a and b in the linear regression equation y = at + b. The calculation formula for coefficient a is: The calculation formula of coefficient b is: in For the physiological data point y with deviation k , according to the corresponding time t k , calibrate using the calibrated equation, the equation is: y corrected =at k +b.

[0034] For magnetic resonance images, the linear transformation formula is used to eliminate the offset. Let the original image be I(A, B). According to the difference between the ideal position and the actual position of the image feature points, the offset vector (ΔA, ΔB) is calculated. The corrected image is I corrected (A, B), the calculation formula is: I corrected (A, B) = I(A + ΔA, B + ΔB), a denoising preprocessing method based on local neighborhood average is used. For each pixel I(A, B) in the image, a neighborhood window of size c×c (here c=3) is selected with the center, and the average value of all pixels in the neighborhood is calculated. The formula is: The original pixel value is replaced by the neighborhood average value to obtain the denoised image I denoised (A,B), the formula is:

[0035] Magnetic field warning modeling: The magnetic field strength sensor monitors the magnetic field strength in real time, and combines the patient's physiological data (such as body surface pressure and body surface temperature) to build an evaluation and prediction model. The patient's physiological parameter set is P = p1, p2, ..., p n , the corresponding weight set is and The enhanced image is denoted as I f , the weight set of image features for patient status evaluation is and The calculation formula of the patient status assessment value S is: Among them, f j is the contribution of image features to the patient status, μ i is the physiological parameter p i The mean of i is the standard deviation, α is the adjustment coefficient, and its value range is [0, 1]. It is adjusted according to the specific diagnostic needs. The patient status is judged by the early warning trigger formula. The patient status evaluation value is S, and the early warning threshold is S th, the trigger warning formula is: Where τ is the preset percentage threshold, 0<τ≤0.3, and the warning threshold S t h According to the magnetic field intensity Q, the upper limit of the normal fluctuation range of physiological parameters in the non-magnetic field environment R 0max , lower limit R 0min The calculation formulas for the influence coefficient ξ of magnetic field intensity on the upper limit of physiological parameters, the nonlinear adjustment index η of magnetic field intensity, the attenuation coefficient ζ of magnetic field intensity on the lower limit of physiological parameters, and the exponential decay rate ρ of magnetic field intensity are as follows:

[0036] Abnormal warning and disposal: If the abnormal warning and disposal module receives an abnormal signal, such as an abnormality in the patient's brain magnetic resonance image (the suspected lesion area is not clearly displayed), the system will notify medical staff through sound and light alarms, and automatically adjust the scanning parameters according to the image abnormality rules, such as increasing the number of scanning layers or changing the scanning sequence to obtain more accurate images; if the physiological parameters (such as excessively high body surface temperature) are abnormal, emergency equipment, such as cooling equipment, will also be activated to ensure patient safety.

[0037] In summary, in the hospital clinical diagnosis scenario, the real-time monitoring system inside the magnetic resonance scanning magnet cavity plays an important role. Through the data acquisition and transmission module, it comprehensively collects the patient's physiological data and image data and transmits them in a timely manner. The data processing and optimization module uses specific algorithms to process data to ensure that the data is accurate and clear. The image enhancement module uses convolutional neural networks to enhance images to assist doctors in diagnosis. The magnetic field warning modeling module combines multiple factors to build a model to effectively evaluate the patient's status. The abnormal warning and disposal module can respond quickly when an abnormality is found. The entire system improves the safety and diagnostic accuracy of magnetic resonance examinations, and provides strong support for patients' accurate diagnosis and safety.

[0038] Example 2:

[0039] A professional medical research institution is conducting a cutting-edge research project on biomarkers for the early diagnosis of neurodegenerative diseases. The project has selected a group of volunteers with a family history of neurological diseases. The project hopes to conduct in-depth analysis of brain structural changes through regular magnetic resonance imaging scans, thereby exploring potential disease biomarkers.

[0040] Data acquisition and transmission: Inside the magnet cavity of a magnetic resonance imaging device used for scientific research, fiber optic sensors are distributed at the contact points between the cavity wall and the volunteer's body at a set acquisition frequency of 10-20 times / minute, collecting real-time pressure data of the contact points between the volunteer's body and the magnet cavity wall. At the same time, non-metallic piezoelectric material sensors are attached to the inner layer of the cavity wall. In a non-contact area 1-3 cm away from the volunteer's body surface, they detect deformation signals of the inner layer of the cavity wall caused by changes in the volunteer's body temperature at a frequency of 3-5 times / minute, thereby indirectly acquiring surface temperature data. The magnetic resonance imaging equipment is started simultaneously to perform a full-scale, high-resolution scan of the volunteer's brain and related parts of the nervous system to obtain detailed image data. Subsequently, with the help of wireless transmission technology, these physiological and image data are transmitted to the cloud data center in real time, providing original data for subsequent in-depth analysis.

[0041] Data processing optimization: The cloud data center transmits the collected data to the data processing optimization module. For physiological data, the sequence is X = x1, x2, ..., x n , use the Зσ principle based on statistical analysis to filter out outliers, first calculate the mean The formula is: Then calculate the standard deviation σ, the formula is: If a data point x j satisfy It is judged as an abnormal value and marked for removal. For the deviation data, the linear regression calibration algorithm is used for calibration. Assuming that there is a linear relationship between the physiological parameter y and the time t, the normal physiological data samples (t1, y1), (t2, y2), ..., (t m ,y m ), use the least squares method to determine the coefficients a and b in the linear regression equation. The linear regression equation is: y = at + b, and the calculation formula for the coefficient a is: The calculation formula of coefficient b is: in For the physiological data point y with deviation k , according to the corresponding time t k , using the calibrated equation y corrected =at k +b for calibration.

[0042] For magnetic resonance images, the linear transformation formula is used to eliminate the offset. Let the original image be I(A, B). According to the difference between the ideal position and the actual position of the image feature points, the offset vector (ΔA, ΔB) is calculated. The corrected image is I corrected (A, B), the calculation formula is: I corrected(A, B) = I(A + ΔA, B + ΔB), a denoising preprocessing method based on local neighborhood average is used. For each pixel I(A, B) in the image, a neighborhood window of size c×c (here c=3) is selected with the center, and the average value of all pixels in the neighborhood is calculated. The formula is: The original pixel value is replaced by the neighborhood average value to obtain the denoised image I denoised (A,B), the formula is:

[0043] Magnetic field warning modeling: The magnetic field strength sensor monitors the magnetic field strength in real time, and combines the volunteers' physiological data (such as body surface pressure and body surface temperature) to build an evaluation and prediction model. The set of volunteers' physiological parameters is P = p1, p2, ..., p n , the corresponding weight set is and The enhanced image is denoted as I f , the weight set of image features for patient status evaluation is and The calculation formula for the volunteer status assessment value S is: Among them, f j is the contribution of image features to the volunteer state, μ i is the physiological parameter p i The mean of i is the standard deviation, α is the adjustment coefficient, and its value range is [0, 1]. It is adjusted according to the research focus. The early warning trigger formula is used to judge the volunteer status. The volunteer status evaluation value is S, and the early warning threshold is S th , the trigger warning formula is: Where τ is the preset percentage threshold, 0<τ≤0.3, and the warning threshold S th According to the magnetic field intensity Q, the upper limit of the normal fluctuation range of physiological parameters in the non-magnetic field environment R 0max , lower limit R 0min , the influence coefficient of magnetic field intensity on the upper limit of physiological parameters ξ, the nonlinear adjustment index η of magnetic field intensity, the attenuation coefficient ζ of magnetic field intensity on the lower limit of physiological parameters, and the exponential decay rate ρ of magnetic field intensity are calculated as follows:

[0044] Abnormal warning and disposal: When the abnormal warning and disposal module receives an abnormal signal, such as an abnormality in the equipment operating status parameters (such as the magnetic field stability index), the system immediately notifies the scientific researchers through sound and light alarms and wireless communications. According to the equipment operating status rules, the system automatically pauses the scan and starts the equipment troubleshooting program to ensure the normal operation of the equipment, the accuracy of the scientific research data and the safety of the volunteers. After the equipment returns to normal, it will continue to scan according to the research plan, continuously provide high-quality data support for scientific research projects, and promote the research progress of biomarkers for early diagnosis of neurodegenerative diseases.

[0045] In summary, in the research scenarios of scientific research institutions, this real-time monitoring system provides key technical support for the study of neurological diseases. The data acquisition and transmission module stably obtains the physiological and image data of volunteers, the data processing and optimization module processes the data to ensure data quality, the magnetic field warning modeling module monitors risks in real time to ensure the smooth progress of research, and the abnormal warning and disposal module handles abnormalities in a timely manner. The system helps scientific researchers to conduct in-depth research on neurological diseases and provides an effective research tool for discovering potential biomarkers, exploring disease mechanisms and early diagnosis methods.

[0046] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A real-time monitoring system for magnetic resonance scanning magnet cavity, characterized in that: The system includes: data acquisition and transmission module, data processing and optimization module, magnetic field warning modeling module and abnormal warning and disposal module; The data acquisition and transmission module collects the patient's physiological data of contact pressure and body surface temperature in real time through a flexible anti-magnetic sensor, collects image data of the patient's internal structure using a magnetic resonance imaging device, and synchronously transmits the physiological data and image data in real time to a cloud data center through wireless transmission technology; The data processing optimization module receives data from the cloud data center, filters out abnormal values and calibrates deviation data for physiological data, and eliminates image offset and performs denoising for magnetic resonance images. The magnetic field warning modeling module uses a magnetic field strength sensor to monitor the magnetic field strength, builds an evaluation and prediction model based on the patient's physiological data, calculates the patient's status evaluation value through an algorithm formula, and compares it with the warning threshold to determine whether the patient's status is abnormal; The abnormal warning and handling module: once an abnormal signal is received, it notifies medical staff through sound and light alarms and wireless communication, and automatically adjusts scanning parameters or activates emergency equipment according to preset rules.

2. The real-time monitoring system for the magnetic resonance scanning magnet cavity according to claim 1, characterized in that: The installation position and acquisition frequency of the physiological data acquisition equipment in the data acquisition and transmission module, the flexible anti-magnetic sensor is an optical fiber sensor and a non-metallic piezoelectric material sensor, wherein the optical fiber sensor is distributed at the contact part between the cavity wall and the patient, and is used to collect the patient's surface pressure data in real time, and the acquisition frequency is 10-20 times / minute; the non-metallic piezoelectric material sensor is attached to the inner layer of the cavity wall, and is located in a non-contact area 1-3 cm away from the patient's body surface, and indirectly obtains the surface temperature data by detecting the deformation signal of the inner layer of the cavity wall caused by the patient's body temperature change, and the acquisition frequency is 3-5 times / minute.

3. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 1, characterized in that: In the data processing optimization module, for physiological data, the 3σ principle based on statistical analysis is used to filter out abnormal values. Assume that the physiological data sequence is X={x1,x2,…,x n }, calculate the mean of the series And standard deviation σ, the formulas are: If a data point x j satisfy It is judged as an abnormal value and marked for removal; the linear regression calibration algorithm is used to calibrate the deviation data. Assuming that there is a linear relationship between the physiological parameter y and time t, the normal physiological data samples {(t1,y1), (t2,y2), ..., (t m ,y m )}, t is time, y is physiological parameter, and the coefficients a and b in the linear regression equation are determined using the least squares method. The regression equation is: y = at + b, and the calculation formulas for the coefficients a and b are: in For the physiological data point y with deviation k , according to the corresponding time t k , calibrate using the calibrated equation, the calibrated equation is: corrected =at k +b, where y corrected is the calibrated data.

4. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 1, characterized in that: In the data processing optimization module, the linear transformation formula is used to eliminate the offset of the magnetic resonance image. Assuming the original image is I(A, B), the offset vector (ΔA, ΔB) is calculated based on the difference between the ideal position and the actual position of the image feature point. The corrected image is I corrected (A, B), the calculation formula is: corrected (A, B) = I(A + ΔA, B + ΔB), where (A, B) is the coordinate of the original image; a denoising preprocessing method based on local neighborhood averaging is used. For each pixel I(A, B) in the image, a neighborhood window of size c × c is selected with c = 3 at the center, and the average value of all pixels in the neighborhood is calculated. The formula is: The original pixel value is replaced by the neighborhood average value to obtain the denoised image I denoised (A,B), the formula is:

5. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 1, characterized in that: The construction of the patient status assessment and prediction model in the magnetic field warning modeling module is as follows: the patient's physiological parameter set is P = {p1, p2, ..., p n }, the corresponding weight set is and The enhanced image is denoted as I f , the weight set of image features for patient status evaluation is and The calculation formula of the patient status assessment value S is: Among them, f j is the contribution of image features to the patient status, μ i is the physiological parameter p i The mean of i is the standard deviation, and α is the adjustment coefficient with a value range of [0,1]. It is used to balance the proportion of physiological data and image features in the assessment of patient status and is adjusted according to specific diagnostic needs.

6. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 6, characterized in that: The magnetic field warning modeling module uses the warning trigger formula to judge the patient's status. The patient status evaluation value is S, and the warning threshold is S. th , the trigger warning formula is: Wherein τ is a preset percentage threshold, 0<τ≤0.

3.

7. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 7, characterized in that: The warning threshold S in the magnetic field warning modeling module th Calculation, assuming the magnetic field strength is Q, the upper limit of the normal fluctuation range of physiological parameters in a non-magnetic field environment is R 0max , the lower limit is R 0min The influence coefficient of magnetic field intensity on the upper limit of physiological parameters is ξ, the nonlinear adjustment index of magnetic field intensity is η, the attenuation coefficient of magnetic field intensity on the lower limit of physiological parameters is ζ, the exponential decay rate of magnetic field intensity is ρ, and the warning threshold S th The calculation formula is:

8. The real-time monitoring system in the magnetic resonance scanning magnet cavity according to claim 1, characterized in that: The preset rules in the abnormal warning and handling module are: Physiological parameter abnormality rules: trigger an alarm when the heart rate exceeds 120 beats / minute or is lower than 50 beats / minute; the image abnormality rules include: automatic rescan when the image signal-to-noise ratio is lower than 20dB; Image anomaly rules: When the monitoring system identifies an anomaly in the MRI or visible light image, it takes appropriate measures based on the type and severity of the anomaly; Equipment operating status rules: operating parameter settings for the magnetic resonance scanning equipment itself.

Images