Magnetic resonance imaging pulse and breath composite gating method based on breath guidance

Abstract

The invention discloses a magnetic resonance imaging pulse and breath composite gating method based on breath guidance. The method comprises the following steps: acquiring face video data of a subject; carrying out skin region identification to obtain a corresponding region of interest; calculating a pixel mean value to obtain an original IPPG signal; removing head artifacts; determining a respiratory cycle T1 and a pulse cycle T2, and calculating a ratio N of the respiratory cycle T1 to the pulse cycle T2; determining a breathing time interval corresponding to each pulse cycle; the delay time d of the IPPG signal peak relative to the electrocardiosignal R wave peak is determined; calculating a composite gating time interval for magnetic resonance imaging in each pulse cycle; and generating a composite gating signal for triggering the MRI equipment to carry out magnetic resonance imaging. Through skin area recognition, effective head motion artifact removal and fine synchronous control over the pulse and the respiratory cycle, image artifacts are reduced, and the quality and efficiency of MRI imaging are remarkably improved.

Description

Technical Field

[0001] The invention relates to the field of magnetic resonance imaging, and more particularly to a pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance. Background Art

[0002] Magnetic resonance imaging (MRI), as an advanced medical imaging technology, plays a vital role in clinical medical diagnosis. It uses strong magnetic fields and radio frequency waves to perform non-invasive imaging of the human body, providing high-resolution anatomical structure and functional information, which is of great significance for the early detection and diagnosis of diseases and the formulation of treatment plans.

[0003] However, in existing MRI techniques, the use of gating methods is essential to reduce motion artifacts and improve image quality. Traditional gating methods mainly rely on external devices, such as respiratory gating belts or electrocardiogram monitors, but these methods often have problems such as complex operation, discomfort to subjects, and poor signal synchronization. In addition, these methods can usually only monitor respiration or heartbeat alone, and it is difficult to achieve precise synchronization between the two.

[0004] In addition, although some researchers have tried to use image photoplethysmography (IPPG) technology to extract physiological signals from video data in recent years, facial video data is easily affected by various factors such as lighting changes and head movement, resulting in unstable quality of the extracted IPPG signal, which in turn affects the triggering accuracy and imaging effect of magnetic resonance imaging.

[0005] Therefore, how to design a pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance to effectively remove motion artifacts and achieve fine control of the respiration and pulse cycles to improve the quality of MRI images and diagnostic efficiency is an urgent problem that technicians in this field need to solve. Summary of the invention

[0006] In view of this, the present invention provides a pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance, which realizes synchronous control of pulse and respiration cycles through precise facial video analysis and advanced signal processing algorithms, thereby reducing motion artifacts during magnetic resonance imaging and improving image quality and diagnostic accuracy.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A pulse and respiration compound gating method for magnetic resonance imaging based on respiration guidance comprises the following steps:

[0009] S1, obtaining facial video data of the subject;

[0010] S2. Combining the SLICO algorithm and the pre-trained SVM model, performing skin area recognition on each frame of the facial video data to obtain a corresponding region of interest;

[0011] S3, calculating the pixel mean of the region of interest to obtain the original IPPG signal of multiple frames of images;

[0012] S4, removing head artifacts from the original IPPG signal to obtain an IPPG signal after the head artifacts are removed;

[0013] S5, determining the respiratory cycle T1 and the pulse cycle T2 based on the IPPG signal after removing the head artifact, and calculating the ratio N of the respiratory cycle T1 to the pulse cycle T2;

[0014] S6, determining the breathing time interval corresponding to each pulse cycle based on the ratio N of the breathing cycle T1 and the pulse cycle T2;

[0015] S7, combining the subject's ECG signal, and determining the delay time d of the IPPG signal peak relative to the ECG signal R wave apex through a pre-trained regression model;

[0016] S8, calculating a composite gating time interval for performing magnetic resonance imaging in each pulse cycle based on the respiratory time interval corresponding to each pulse cycle and the delay time d;

[0017] S9. Generate a composite gating signal for triggering an MRI device to perform magnetic resonance imaging according to the composite gating time interval.

[0018] Furthermore, the S2 includes:

[0019] S21, segmenting each frame of the image using the SLICO algorithm to obtain multiple super-pixel blocks with similar color and texture features;

[0020] S22, for each superpixel block, using the pre-trained SVM model to classify the skin area and the non-skin area;

[0021] S23. Based on the classification result, determine the skin area as the region of interest.

[0022] Furthermore, the S3 includes:

[0023] S31, calculating the light intensity value of each pixel in the region of interest in the time series t;

[0024] C(x,y)=I×(ρ s (t)+ρ d (t))+V n

[0025] Among them, C(x,y) represents the light intensity value of the pixel with coordinates (x,y), I represents the light intensity of the light source, and ρ s (t) represents the specular reflection coefficient, ρ d (t) represents the specular diffuse reflection coefficient, V n represents the quantization noise of the image sensor;

[0026] S32, quantization noise V n and the specular diffuse reflectance ρ d (t) Remove and calculate the pixel mean ;

[0027]

[0028] in, Indicates the removal of quantization noise V n and the specular diffuse reflectance ρ d (t), the coordinates are the light intensity values ​​of the pixels at (x, y); N represents the number of pixels.

[0029] Furthermore, the S4 includes:

[0030] S41, calculating the change information of the spatial average position of the four corners of the region of interest over time, and obtaining the corresponding time series data;

[0031] S42, extracting feature vector v from the time series data using principal component analysis algorithm i , construct the noise subspace; where the eigenvector v i Indicates the main direction of head movement;

[0032] S43, projecting the original IPPG signal x into the noise subspace to obtain the head artifact noise p;

[0033]

[0034] S44, removing the head artifact noise p to obtain an IPPG signal after the head artifact is removed.

[0035] Furthermore, in S5, determining the respiratory cycle T1 includes:

[0036] S511, inputting the IPPG signal after removing the head artifact into a bandpass filter, removing the high-frequency components higher than 0.45 Hz and the low-frequency components lower than 0.13 Hz through the bandpass filter, and obtaining a filtered respiratory signal;

[0037] S512, performing time series analysis on the filtered respiratory signal to identify respiratory peaks or troughs;

[0038] S513: Determine the respiratory cycle T1 based on the time interval between respiratory peaks or troughs.

[0039] Furthermore, in S5, determining the pulse cycle T2 includes:

[0040] S521, setting the width of the initial sliding window to L; wherein L is an even number greater than 2;

[0041] S522, define the IPPG signal after removing the head artifact as , the discrete signal point sub-interval covered by the initial sliding window is ;

[0042] S523, Select As the starting reference point, the peak feature point or valley feature point identification is performed; the peak feature point or valley feature point identification includes: if ,and

[0043] ,but is the peak feature point; if ,and

[0044] ,but is the valley feature point;

[0045] S524, moving the sliding window to traverse the IPPG signal after removing the head artifacts until all peak feature points or valley feature points in the signal are identified;

[0046] S525. Determine the pulse cycle T2 based on the peak feature point or the valley feature point.

[0047] Furthermore, the S6 includes:

[0048] S61, based on the ratio N of the respiratory cycle T1 to the pulse cycle T2, determine the length of the respiratory time interval corresponding to each pulse cycle T2 as ;

[0049] S62, determining the starting time point of each pulse cycle T2, and dividing the exhalation time interval and the inhalation time interval corresponding to each pulse cycle based on the starting time point and the length of the breathing time interval.

[0050] Further, the S7 includes:

[0051] S71, synchronously acquiring the subject's ECG signal and the IPPG signal after removing the head artifact;

[0052] S72. Input the subject's ECG signal and the IPPG signal after removing the head artifact into the pre-trained regression model, and determine the time difference between the IPPG signal peak and the top of the ECG R wave as the delay time d; wherein the pre-trained regression model uses the least squares method to minimize the prediction error.

[0053] Furthermore, the S8 includes:

[0054] S81, defining the starting time point of the mth pulse cycle as Tm_start and the ending time point as Tm_end;

[0055] S82, based on the starting time point Tm_start, determine the starting time point of the exhalation phase corresponding to the mth pulse cycle as The end time of the exhalation phase is ;

[0056] S83, combining the delay time d, determining the starting time point of the composite gating time window as Tm_start , the end time is .

[0057] Furthermore, the S9 includes:

[0058] S91, determining a time point for triggering an MRI device to perform magnetic resonance imaging based on the composite gating time interval;

[0059] S92, converting the time point into a signal format matching the MRI device according to a preset coding rule, and outputting the signal to the MRI device for magnetic resonance imaging.

[0060] It can be seen from the above technical solution that, compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0061] 1. This method combines the SLICO algorithm with the pre-trained SVM model for skin area recognition, which can more accurately locate the facial area of ​​interest, thereby improving the quality of the original IPPG signal. And by combining superpixel block segmentation and machine learning classification, the skin area can be stably and reliably extracted under different environments, providing more accurate basic data for subsequent signal processing.

[0062] 2. Principal component analysis (PCA) is introduced to construct the noise subspace, and head motion artifacts are removed accordingly, improving the purity of the IPPG signal. By calculating the time series change information of the angular position of the region of interest and using PCA to extract the feature vector, the main direction of the head movement can be accurately captured, and then these artifacts can be effectively separated and removed from the original signal, ensuring the authenticity and accuracy of the obtained breathing and pulse cycles.

[0063] 3. By determining the respiratory time interval corresponding to each pulse cycle and the delay time d of the IPPG wave peak relative to the R wave apex of the ECG signal, the most suitable composite gating time interval for MRI scanning can be accurately calculated. This allows the MRI device to trigger imaging at the best time, reduce image artifacts caused by breathing and heartbeat, improve image quality and diagnostic efficiency, and reduce unnecessary radiation exposure and scanning time, bringing great convenience to clinical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0065] Figure 1 A flow chart of a pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance provided by an embodiment of the present invention;

[0066] Figure 2 A schematic diagram of the process of obtaining facial video data of a subject provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] like Figure 1 As shown, this embodiment provides a pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance, comprising the following steps:

[0069] S1, obtaining facial video data of the subject;

[0070] S2. Combining the SLICO algorithm and the pre-trained SVM model, performing skin area recognition on each frame of the facial video data to obtain a corresponding region of interest;

[0071] S3, calculating the pixel mean of the region of interest to obtain the original IPPG signal of multiple frames of images;

[0072] S4, removing head artifacts from the original IPPG signal to obtain an IPPG signal after the head artifacts are removed;

[0073] S5. Based on the IPPG signal after removing the head artifact, determine the respiratory cycle T1 and the pulse cycle T2, and calculate the ratio N of the respiratory cycle T1 to the pulse cycle T2;

[0074] S6. Based on the ratio N of the respiratory cycle T1 to the pulse cycle T2, determine the respiratory time interval corresponding to each pulse cycle;

[0075] S7. Combine the electrocardiogram signal of the subject, and determine the delay time d of the peak of the IPPG signal relative to the R-wave peak of the electrocardiogram signal through a pre-trained regression model;

[0076] S8. Based on the respiratory time interval corresponding to each pulse cycle and the delay time d, calculate the composite gating time interval for magnetic resonance imaging in each pulse cycle;

[0077] S9. Generate a composite gating signal for triggering the MRI device to perform magnetic resonance imaging according to the composite gating time interval.

[0078] This method not only realizes the accurate recognition of the skin area through advanced algorithms, but also optimizes the signal processing flow, effectively reducing noise interference, thereby ensuring that the extracted physiological signals have higher accuracy. In addition, this method combines the electrocardiogram signal and the IPPG signal, and through precise time synchronization and calculation, greatly enhances the stability during the imaging process. Under the combined action of these comprehensive improvement measures, this method is more reliable in the application of magnetic resonance imaging, providing more accurate medical image support for users.

[0079] The following further elaborates on each step in the above technical solution:

[0080] In step S1 of this embodiment, obtain the facial video data of the subject;

[0081] As Figure 2 shown, in the specific process of obtaining the facial video data of the subject, first use the visible light source 1 to irradiate the facial area of the subject, and reflect the light to the acquisition camera 3 through the reflector 2. The acquisition camera 3 is located outside the MRI device and can capture the facial image reflected by the reflector 2. This setting ensures that the facial video data of the subject is recorded in real time without affecting the MRI imaging quality, providing basic information for subsequent skin area recognition and signal processing.

[0082] In step S2 of this embodiment, combine the SLICO algorithm and the pre-trained SVM model to identify the skin area in each frame of the facial video data, and obtain the corresponding region of interest; including:

[0083] S21, segmenting each frame of the image using the SLICO algorithm to obtain multiple super-pixel blocks with similar color and texture features;

[0084] S22, for each superpixel block, using the pre-trained SVM model to classify the skin area and the non-skin area;

[0085] S23. Based on the classification result, determine the skin area as the region of interest.

[0086] In this embodiment S3, the pixel mean of the region of interest is calculated to obtain the original IPPG signal of multiple frames of images; including:

[0087] S31, calculating the light intensity value of each pixel in the region of interest in the time series t;

[0088] C(x,y)=I×(ρ s (t)+ρ d (t))+V n

[0089] Among them, C(x,y) represents the light intensity value of the pixel with coordinates (x,y), I represents the light intensity of the light source, and ρ s (t) represents the specular reflection coefficient, ρ d (t) represents the specular diffuse reflection coefficient, V n represents the quantization noise of the image sensor;

[0090] S32, quantization noise V n and the specular diffuse reflectance ρ d (t) Remove and calculate the pixel mean ;

[0091]

[0092] in, Indicates the removal of quantization noise V n and the specular diffuse reflectance ρ d (t), the light intensity value of the pixel with coordinate (x, y); N represents the number of pixels. In this embodiment S4, the original IPPG signal is subjected to head artifact removal to obtain the IPPG signal after the head artifact is removed; including:

[0093] S41, calculating the change information of the spatial average position of the four corners of the region of interest over time, and obtaining the corresponding time series data;

[0094] S42, extracting feature vector v from the time series data using principal component analysis algorithm i , construct the noise subspace; where the eigenvector v i Indicates the main direction of head movement;

[0095] S43, projecting the original IPPG signal x into the noise subspace to obtain the head artifact noise p;

[0096]

[0097] S44, removing the head artifact noise p to obtain an IPPG signal after the head artifact is removed.

[0098] In this embodiment S5, based on the IPPG signal after removing the head artifact, the respiratory cycle T1 and the pulse cycle T2 are determined, and the ratio N of the respiratory cycle T1 to the pulse cycle T2 is calculated;

[0099] Specifically, determining the respiratory cycle T1 includes:

[0100] S511, inputting the IPPG signal after removing the head artifact into a bandpass filter, removing the high-frequency components higher than 0.45 Hz and the low-frequency components lower than 0.13 Hz through the bandpass filter, and obtaining a filtered respiratory signal;

[0101] S512, performing time series analysis on the filtered respiratory signal to identify respiratory peaks or troughs;

[0102] S513: Determine the respiratory cycle T1 based on the time interval between respiratory peaks or troughs.

[0103] Further, the pulse cycle T2 is determined, including:

[0104] S521, setting the width of the initial sliding window to L; wherein L is an even number greater than 2;

[0105] S522, define the IPPG signal after removing the head artifact as , the discrete signal point sub-interval covered by the initial sliding window is ;

[0106] S523, Select As the starting reference point, the peak feature point or valley feature point identification is performed; the peak feature point or valley feature point identification includes: if ,and

[0107] ,but is the peak feature point; if ,and

[0108] ,but is the valley feature point;

[0109] S524, moving the sliding window to traverse the IPPG signal after removing the head artifacts until all peak feature points or valley feature points in the signal are identified;

[0110] S525. Determine the pulse cycle T2 based on the peak feature point or the valley feature point.

[0111] In this embodiment S6, based on the ratio N of the respiratory cycle T1 to the pulse cycle T2, the respiratory time interval corresponding to each pulse cycle is determined; including:

[0112] S61, based on the ratio N of the respiratory cycle T1 to the pulse cycle T2, determine the length of the respiratory time interval corresponding to each pulse cycle T2 as ;

[0113] S62, determining the starting time point of each pulse cycle T2, and dividing the exhalation time interval and the inhalation time interval corresponding to each pulse cycle based on the starting time point and the length of the breathing time interval.

[0114] Furthermore, breathing guidance can be performed based on the exhalation time interval and the inhalation time interval corresponding to each pulse cycle, guiding the subject to breathe according to a specific breathing pattern. For example, when N=3, it means that a breathing cycle is three times longer than a pulse cycle. Therefore, in each pulse cycle T2, Time for the exhalation and inhalation process.

[0115] In actual operation, every time a characteristic point (such as a peak or trough) in the pulse waveform is detected, it means that a new pulse cycle has begun, and the breathing guidance program will be started at this time. Taking the indicator light as an example, when the mth pulse characteristic point is detected, the indicator light will turn "green", prompting the subject to start inhaling, and this process will continue After a certain time, the indicator light turns yellow, indicating that the exhalation phase has begun. The subject should follow the instructions to exhale for the same period of time. After completing this cycle, if the scan is not over, the indicator light will turn back to "green" again, guiding the subject to repeat the above process until the entire magnetic resonance imaging process is completed.

[0116] It not only ensures that the subject's breathing rhythm is consistent with the pulse cycle, but also effectively reduces image artifacts caused by the lack of coordination between breathing and heart movement, thereby improving the quality and efficiency of magnetic resonance imaging.

[0117] In this embodiment S7, in combination with the subject's ECG signal, the delay time d of the IPPG signal peak relative to the ECG signal R wave apex is determined by a pre-trained regression model; including:

[0118] S71, synchronously acquiring the subject's ECG signal and the IPPG signal after removing the head artifact;

[0119] S72. Input the subject's ECG signal and the IPPG signal after removing the head artifact into the pre-trained regression model, and determine the time difference between the IPPG signal peak and the top of the ECG R wave as the delay time d; wherein the pre-trained regression model uses the least squares method to minimize the prediction error.

[0120] In this embodiment S8, based on the respiratory time interval corresponding to each pulse cycle and the delay time d, a composite gating time interval for performing magnetic resonance imaging in each pulse cycle is calculated; including:

[0121] S81, defining the starting time point of the mth pulse cycle as Tm_start and the ending time point as Tm_end;

[0122] S82, based on the starting time point Tm_start, determine the starting time point of the exhalation phase corresponding to the mth pulse cycle as The end time of the exhalation phase is ;

[0123] S83, combining the delay time d, determining the starting time point of the composite gating time window as Tm_start , the end time is .

[0124] In this step, the starting time point of the composite gated time window is set to Tm_start , which means starting the magnetic resonance imaging process at a delay time d after the start of the pulse cycle to ensure that the heart is in a relatively stable period. Similarly, the end time point of the composite gating time window is also adjusted accordingly to , thereby avoiding the period when the heart moves most violently and reducing the impact of motion artifacts on image quality.

[0125] In this embodiment S9, a composite gating signal for triggering an MRI device to perform magnetic resonance imaging is generated according to the composite gating time interval; including:

[0126] S91, determining a time point for triggering an MRI device to perform magnetic resonance imaging based on the composite gating time interval;

[0127] S92, converting the time point into a signal format matching the MRI device according to a preset coding rule, and outputting the signal to the MRI device for magnetic resonance imaging.

[0128] This embodiment provides a pulse and respiration composite gating method for magnetic resonance imaging based on breathing guidance, which obtains the facial video data of the subject, combines the SLICO algorithm with the pre-trained SVM model to accurately identify the skin area, and then calculates the original IPPG signal and removes the head artifact, determines the respiration and pulse cycle and their ratio based on the optimization algorithm, and determines the delay time between the IPPG signal peak and the ECG R wave apex in combination with the ECG signal, and finally calculates the composite gating time interval and generates a composite gating signal to trigger the MRI device. This method can accurately monitor pulse and respiration at the same time, effectively reduce noise interference, improve the accuracy of physiological signals, and enhance the imaging stability in combination with the ECG signal, providing more reliable and accurate medical imaging support for magnetic resonance imaging.

[0129] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0130] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance, characterized in that: The following steps are involved: S1, obtaining facial video data of the subject; S2. Combining the SLICO algorithm and the pre-trained SVM model, performing skin area recognition on each frame of the facial video data to obtain a corresponding region of interest; S3, calculating the pixel mean of the region of interest to obtain the original IPPG signal of multiple frames of images; S4, removing head artifacts from the original IPPG signal to obtain an IPPG signal after the head artifacts are removed; S5, determining the respiratory cycle T1 and the pulse cycle T2 based on the IPPG signal after removing the head artifact, and calculating the ratio N of the respiratory cycle T1 to the pulse cycle T2; S6, determining the breathing time interval corresponding to each pulse cycle based on the ratio N of the breathing cycle T1 and the pulse cycle T2; S7, combining the subject's ECG signal, and determining the delay time d of the IPPG signal peak relative to the ECG signal R wave apex through a pre-trained regression model; S8, calculating a composite gating time interval for performing magnetic resonance imaging in each pulse cycle based on the respiratory time interval corresponding to each pulse cycle and the delay time d; S9. Generate a composite gating signal for triggering an MRI device to perform magnetic resonance imaging according to the composite gating time interval.

2. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S2 comprises: S21, segmenting each frame of the image using the SLICO algorithm to obtain multiple super-pixel blocks with similar color and texture features; S22, for each superpixel block, using the pre-trained SVM model to classify the skin area and the non-skin area; S23. Based on the classification result, determine the skin area as the region of interest.

3. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S3 includes: S31, calculating the light intensity value of each pixel in the region of interest in the time series t; C(x,y)=I×(ρ s (t)+ρ d (t))+V n Among them, C(x,y) represents the light intensity value of the pixel with coordinates (x,y), I represents the light intensity of the light source, and ρ s (t) represents the specular reflection coefficient, ρ d (t) represents the specular diffuse reflectance, V n represents the quantization noise of the image sensor; S32, quantization noise V n and the specular diffuse reflectance ρ d (t) Remove and calculate the pixel mean ; ； in, Indicates the removal of quantization noise V n and the specular diffuse reflectance ρ d (t), the coordinates are the light intensity values ​​of the pixels at (x, y); N represents the number of pixels.

4. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S4 comprises: S41, calculating the change information of the spatial average position of the four corners of the region of interest over time, and obtaining the corresponding time series data; S42, extracting feature vector v from the time series data using principal component analysis algorithm i , construct the noise subspace; among them, the eigenvector v i Indicates the main direction of head movement; S43, projecting the original IPPG signal x into the noise subspace to obtain the head artifact noise p; ； S44, removing the head artifact noise p to obtain an IPPG signal after the head artifact is removed.

5. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: In S5, determining the respiratory cycle T1 includes: S511, inputting the IPPG signal after removing the head artifact into a bandpass filter, removing the high-frequency components higher than 0.45 Hz and the low-frequency components lower than 0.13 Hz through the bandpass filter, and obtaining a filtered respiratory signal; S512, performing time series analysis on the filtered respiratory signal to identify respiratory peaks or troughs; S513: Determine the respiratory cycle T1 based on the time interval between respiratory peaks or troughs.

6. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: In S5, determining the pulse cycle T2 includes: S521, setting the width of the initial sliding window to L; wherein L is an even number greater than 2; S522, define the IPPG signal after removing the head artifact as , the discrete signal point sub-interval covered by the initial sliding window is ; S523, Select As the starting reference point, the peak feature point or valley feature point identification is performed; the peak feature point or valley feature point identification includes: if ,and ,but is the peak feature point; if ,and ,but is the valley feature point; S524, moving the sliding window to traverse the IPPG signal after removing the head artifacts until all peak feature points or valley feature points in the signal are identified; S525. Determine the pulse cycle T2 based on the peak feature point or the valley feature point.

7. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S6 comprises: S61, based on the ratio N of the respiratory cycle T1 to the pulse cycle T2, determine the length of the respiratory time interval corresponding to each pulse cycle T2 as ; S62, determining the starting time point of each pulse cycle T2, and dividing the exhalation time interval and the inhalation time interval corresponding to each pulse cycle based on the starting time point and the length of the breathing time interval.

8. The pulse and respiration composite gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S7 comprises: S71, synchronously acquiring the subject's ECG signal and the IPPG signal after removing the head artifact; S72. Input the subject's ECG signal and the IPPG signal after removing the head artifact into the pre-trained regression model, and determine the time difference between the IPPG signal peak and the top of the ECG R wave as the delay time d; wherein the pre-trained regression model uses the least squares method to minimize the prediction error.

9. The pulse and respiration compound gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S8 comprises: S81, defining the starting time point of the mth pulse cycle as Tm_start and the ending time point as Tm_end; S82, based on the starting time point Tm_start, determine the starting time point of the exhalation phase corresponding to the mth pulse cycle as The end time of the exhalation phase is ; S83, combining the delay time d, determining the starting time point of the composite gating time window as Tm_start , the end time is .

10. The pulse and respiration compound gating method for magnetic resonance imaging based on respiration guidance according to claim 1, characterized in that: The S9 comprises: S91, determining a time point for triggering an MRI device to perform magnetic resonance imaging based on the composite gating time interval; S92, converting the time point into a signal format matching the MRI device according to a preset coding rule, and outputting the signal to the MRI device for magnetic resonance imaging.

Images