阅读说明：本技术 确定呼吸阶段的方法及装置、磁共振成像方法及系统 (Method and device for determining respiratory phase and magnetic resonance imaging method and system ) 是由 何金强 翁得河 谢树群 董芳 于 2019-08-21 设计创作，主要内容包括：本公开提供了确定呼吸阶段的方法及装置、磁共振成像方法及系统。确定呼吸阶段的方法包括：从呼吸信号中提取距离特征值、点数特征值以及面积特征值,其中,所述距离特征值、所述点数特征值以及所述面积特征值用于指示所述呼吸信号中相邻的两个波形的波形变化；根据所述距离特征值、所述点数特征值以及所述面积特征值训练呼吸信号模型,以利用所述呼吸信号模型确定呼吸信号的呼吸阶段。本公开解决了相关技术中无法准确地确定呼吸信号的呼吸阶段的问题,具有能够准确地确定呼吸阶段的有益效果。(The present disclosure provides a method and apparatus for determining a respiratory phase, a magnetic resonance imaging method and system. The method for determining the respiratory phase comprises the following steps: extracting a distance characteristic value, a point characteristic value and an area characteristic value from a respiratory signal, wherein the distance characteristic value, the point characteristic value and the area characteristic value are used for indicating waveform changes of two adjacent waveforms in the respiratory signal; and training a respiratory signal model according to the distance characteristic value, the point characteristic value and the area characteristic value so as to determine the respiratory phase of the respiratory signal by using the respiratory signal model. The method and the device solve the problem that the breathing phase of the breathing signal cannot be accurately determined in the related art, and have the advantage that the breathing phase can be accurately determined.)

1. A method of determining a respiratory phase of a respiratory signal, comprising:

extracting a distance characteristic value, a point characteristic value and an area characteristic value from a respiratory signal, wherein the distance characteristic value, the point characteristic value and the area characteristic value are used for indicating waveform changes of two adjacent waveforms in the respiratory signal;

and training a respiratory signal model according to the distance characteristic value, the point characteristic value and the area characteristic value so as to determine the respiratory phase of the respiratory signal by using the respiratory signal model.

2. The method of claim 1, wherein,

the distance characteristic value is a ratio of a width of a second half waveform of a first waveform of the two adjacent waveforms to a width of a first half waveform of a second waveform of the two adjacent waveforms; and/or

The point characteristic value is the ratio of the width of a section of ascending waveform to the peak point of a first waveform in the two adjacent waveforms to the width of a section of descending waveform to the valley point of the first waveform; and/or

The area characteristic value is a ratio of an area formed by two peak points of the two adjacent waveforms and a valley point between the two waveforms to an area formed by the second waveform.

3. The method of claim 1 or 2, wherein prior to extracting distance, point, and area eigenvalues from the respiratory signal, the method further comprises:

acquiring a peak point of a first waveform and a peak point of a second waveform in the two waveforms, and respectively taking the peak points as a first maximum value point and a second maximum value point;

acquiring a valley point between the two waveforms as a first minimum value point, and acquiring a valley point of the second waveform after the second maximum value point as a second minimum value point;

and determining time points corresponding to the first maximum value point, the first minimum value point, the second maximum value point and the second minimum value point respectively as a first maximum value time point, a first minimum value time point, a second maximum value time point and a second minimum value time point.

4. The method of claim 3, wherein extracting distance feature values from the respiratory signal comprises:

calculating a ratio of a difference between the first minimum time point and the first maximum time point to a difference between the second maximum time point and the first minimum time point;

the calculated ratio is taken as the extracted distance feature value.

5. The method of claim 3, wherein extracting point feature values from the respiratory signal comprises:

determining a starting time point of a section of rising waveform of the first waveform to the first maximum point and a starting time point of a section of falling waveform of the first waveform to the first minimum value according to a predetermined amplitude proportion parameter and the first maximum point and the first minimum point, as a first time point and a second time point for determining an end-expiratory starting time point of the respiratory phase respectively;

calculating a ratio of a difference between the first maximum time point and the first time point to a difference between the first minimum time point and the second time point;

the calculated ratio is taken as the extracted point feature value.

6. The method of claim 5, wherein the first and second points in time are determined according to the following two equations:

mag(t_1)＝mag(t_max1)*p+mag(t_min1)*(1-p)；

mag(t_2)＝mag(t_max1)*(1-p)+mag(t_min1)*p；

wherein t _1 is the first time point, t _ max1 is the first maximum time point, p is the amplitude scaling parameter, t _ min1 is the first minimum time point, and mag is an amplitude function.

7. The method of claim 6, wherein the amplitude scaling parameter p is equal to 80%.

8. The method of claim 3, wherein extracting area feature values from the respiration signal comprises:

calculating the ratio of a first polygon area determined by the first maximum value point, the second maximum value point and the first minimum value point to a second polygon area determined by the first minimum value point, the second maximum value point and the second minimum value point;

the calculated ratio is taken as the extracted area feature value.

9. Apparatus for determining a respiratory phase of a respiratory signal, comprising:

an extraction module configured to extract a distance feature value, a point feature value and an area feature value from a respiration signal, wherein the distance feature value, the point feature value and the area feature value are used for indicating waveform changes of two adjacent waveforms in the respiration signal;

a determination module configured to train a respiratory signal model from the distance feature values, the point feature values, and the area feature values to determine a respiratory phase of a respiratory signal using the respiratory signal model.

10. The apparatus of claim 9, wherein the extraction module comprises:

a maximum value point acquisition unit configured to acquire a peak point of a first waveform and a peak point of a second waveform of the two waveforms as a first maximum value point and a second maximum value point, respectively;

a minimum value point acquisition unit configured to acquire a valley point between the two waveforms as a first minimum value point, and acquire a valley point of the second waveform after the second maximum value point as a second minimum value point;

a time point determining unit configured to determine time points corresponding to the first maximum value point, the first minimum value point, the second maximum value point, and the second minimum value point, respectively, as a first maximum value time point, a first minimum value time point, a second maximum value time point, and a second minimum value time point.

11. The apparatus of claim 10, wherein the extraction module comprises:

a distance calculation unit configured to calculate a ratio of a difference between the first minimum time point and the first maximum time point to a difference between the second maximum time point and the first minimum time point;

a distance extraction unit configured to take the calculated ratio as the extracted distance feature value.

12. The apparatus of claim 10, wherein the extraction module comprises:

a feature point determination unit configured to determine, according to a predetermined amplitude scale parameter and the first maximum value point and the first minimum value point, a start time point of a segment of a rising waveform of the first waveform to the first maximum value point and a start time point of a segment of a falling waveform of the first waveform to the first minimum value as a first time point and a second time point for determining an end-expiratory start time point of the respiratory phase, respectively;

a feature point calculation unit configured to calculate a ratio of a difference between the first maximum time point and the first time point to a difference between the first minimum time point and the second time point;

a feature point extraction unit configured to take the calculated ratio as an extracted point feature value.

13. The apparatus of claim 10, wherein the extraction module comprises:

an area calculation unit configured to calculate a ratio of a first polygon area determined by the first maximum point, the second maximum point, and the first minimum point to a second polygon area determined by the first minimum point, the second maximum point, and the second minimum point;

an area feature extraction unit configured to take the calculated ratio as an extracted area feature value.

14. A magnetic resonance imaging method comprising:

determining a respiratory phase of a respiratory signal according to the method of any one of claims 1 to 8;

and magnetic resonance imaging of the examined part of the examined object according to the determined breathing phase.

15. A magnetic resonance imaging system comprising:

the apparatus of any of claims 9 to 13, configured to determine a respiratory phase of a respiratory signal;

an imaging device configured to perform magnetic resonance imaging of the examined part of the examined object according to the determined breathing phase.

16. A non-transitory readable storage medium having stored thereon a program that, when executed, causes a processor to perform the method of any of claims 1-8.

Technical Field

The present disclosure relates to the field of medical Magnetic Resonance Imaging, and in particular, to a method and an apparatus for determining a respiratory phase, a Magnetic Resonance Imaging (MRI) method and system, and a storage medium.

Background

Magnetic resonance imaging is one of tomographic imaging that uses the magnetic resonance phenomenon to acquire electromagnetic signals from an object such as a human body and reconstruct information. Specifically, the magnetic resonance imaging system applies a radio frequency pulse of a specific frequency to a human body in a static magnetic field, so that hydrogen protons in the human body are excited to generate a magnetic resonance phenomenon. After stopping the pulse, the protons produce a Magnetic Resonance (MR) signal during relaxation. Human body information is reconstructed through the processing processes of receiving magnetic resonance signals, space encoding, image reconstruction and the like.

In magnetic resonance imaging, respiratory motion of a subject degrades the quality of magnetic resonance images of a portion of the subject, such as the abdomen, which is affected by respiratory motion. To eliminate motion artifacts in magnetic resonance images caused by respiratory motion, a respiratory sensor is typically used to detect the respiratory motion state of the subject and, when appropriate, to trigger magnetic resonance data acquisition.

However, different coil units in a magnetic resonance imaging system receive inconsistent respiratory motion signals, which results in differential respiratory motion information being obtained for each receiving channel, and the information is different for different positions of different subjects.

Disclosure of Invention

According to an aspect of an embodiment of the present disclosure, a method of determining a respiratory phase of a respiratory signal is provided. The method comprises the following steps: extracting a distance characteristic value, a point characteristic value and an area characteristic value from a respiratory signal, wherein the distance characteristic value, the point characteristic value and the area characteristic value are used for indicating waveform changes of two adjacent waveforms in the respiratory signal; and training a respiratory signal model according to the distance characteristic value, the point characteristic value and the area characteristic value so as to determine the respiratory phase of the respiratory signal by using the respiratory signal model.

By the method, the problem that the breathing phase of the breathing signal cannot be accurately determined in the related technology is solved, and the method has the beneficial effect that the breathing phase can be accurately determined.

In an exemplary embodiment of the present disclosure, the distance characteristic value is a ratio of a width of a second half waveform of a first waveform of the two adjacent waveforms to a width of a first half waveform of a second waveform of the two adjacent waveforms; and/or the point characteristic value is the ratio of the width of a section of rising waveform to the peak point of a first waveform in the two adjacent waveforms to the width of a section of falling waveform to the valley point of the first waveform; and/or the area characteristic value is the ratio of the area formed by two peak points of the two adjacent waveforms and a valley point between the two waveforms to the area formed by the second waveform.

By extracting waveform change characteristics, such as distance characteristic values, point characteristic values and area characteristic values, which characterize two adjacent waveforms of the respiratory signal, the respiratory phase can be identified by comparing the curve shapes of inspiration and expiration by utilizing the characteristics of the respiratory curve.

In an exemplary embodiment of the present disclosure, before extracting the distance feature value, the point feature value, and the area feature value from the respiration signal, the method further includes: acquiring a peak point of a first waveform and a peak point of a second waveform in the two waveforms, and respectively taking the peak points as a first maximum value point and a second maximum value point; acquiring a valley point between the two waveforms as a first minimum value point, and acquiring a valley point of the second waveform after the second maximum value point as a second minimum value point; and determining time points corresponding to the first maximum value point, the first minimum value point, the second maximum value point and the second minimum value point respectively as a first maximum value time point, a first minimum value time point, a second maximum value time point and a second minimum value time point.

By the method, the related extreme points of two adjacent waveforms of the respiratory signal and the corresponding time points thereof can be obtained, so that the respiratory characteristic value of the respiratory signal related to waveform change can be simply and quickly calculated by using the obtained extreme points and the corresponding time points.

In an exemplary embodiment of the present disclosure, extracting the distance feature value from the respiration signal includes: calculating a ratio of a difference between the first minimum time point and the first maximum time point to a difference between the second maximum time point and the first minimum time point; the calculated ratio is taken as the extracted distance feature value.

By calculating the ratio of the bottom width of the second half of the first waveform to the bottom width of the first half of the second waveform in the two adjacent waveforms, the change of the second half of the first waveform and the first half of the second waveform can be compared, and the distance characteristic value of the respiratory signal can be extracted relatively easily.

In an exemplary embodiment of the present disclosure, extracting point feature values from the respiratory signal includes: determining a starting time point of a section of rising waveform of the first waveform to the first maximum point and a starting time point of a section of falling waveform of the first waveform to the first minimum value according to a predetermined amplitude proportion parameter and the first maximum point and the first minimum point, as a first time point and a second time point for determining an end-expiratory starting time point of the respiratory phase respectively; calculating a ratio of a difference between the first maximum time point and the first time point to a difference between the first minimum time point and the second time point; and taking the calculated ratio as the extracted point characteristic value.

By calculating the ratio of the time corresponding to a section of rising waveform to the peak point in the first waveform to the time corresponding to a section of falling waveform to the valley point in the first waveform, the change of the waveform near the peak and the waveform near the valley of the first waveform can be compared, and the point characteristic value of the respiratory signal can be extracted relatively easily.

In an exemplary embodiment of the present disclosure, the first time point and the second time point are respectively determined according to the following two formulas: mag (t _1) ═ mag (t _ max1) × p + mag (t _ min1) × (1-p); mag (t _2) ═ mag (t _ max1) × (1-p) + mag (t _ min1) × p; wherein t _1 is the first time point, t _ max1 is the first maximum time point, p is the amplitude scaling parameter, t _ min1 is the first minimum time point, and mag is an amplitude function.

Through the formula, the point characteristic value of the respiratory signal can be accurately calculated.

In an exemplary embodiment of the present disclosure, the amplitude scaling parameter p is equal to 80%.

The amplitude proportional parameter value of 80% is an empirical value determined in practice in consideration of other parameters of the magnetic resonance imaging system, and by setting the amplitude proportional parameter to 80%, the point characteristic value of the respiratory signal can be calculated more accurately.

In an exemplary embodiment of the present disclosure, extracting the area feature value from the respiration signal includes: calculating the ratio of a first polygon area determined by the first maximum value point, the second maximum value point and the first minimum value point to a second polygon area determined by the first minimum value point, the second maximum value point and the second minimum value point; the calculated ratio is taken as the extracted area feature value.

By calculating the ratio of the area formed by two peak points of two adjacent waveforms and the valley point between the two waveforms to the area formed by two valley points of the two waveforms and the peak point of the second waveform, the change of the first waveform and the second waveform can be compared, and the area characteristic value of the respiratory signal can be extracted more easily.

According to another aspect of an embodiment of the present disclosure, there is provided an apparatus for determining a respiratory phase of a respiratory signal, comprising: an extraction module configured to extract a distance feature value, a point feature value and an area feature value from a respiration signal, wherein the distance feature value, the point feature value and the area feature value are used for indicating waveform changes of two adjacent waveforms in the respiration signal; a determination module configured to train a respiratory signal model from the distance feature values, the point feature values, and the area feature values to determine a respiratory phase of a respiratory signal using the respiratory signal model.

By the device, the problem that the breathing phase of the breathing signal cannot be accurately determined in the related technology is solved, and the device has the beneficial effect that the breathing phase can be accurately determined

In an exemplary embodiment of the present disclosure, the extraction module includes: a maximum value point acquisition unit configured to acquire a peak point of a first waveform and a peak point of a second waveform of the two waveforms as a first maximum value point and a second maximum value point, respectively; a minimum value point acquisition unit configured to acquire a valley point between the two waveforms as a first minimum value point, and acquire a valley point of the second waveform after the second maximum value point as a second minimum value point; a time point determining unit configured to determine time points corresponding to the first maximum value point, the first minimum value point, the second maximum value point, and the second minimum value point, respectively, as a first maximum value time point, a first minimum value time point, a second maximum value time point, and a second minimum value time point.

Through the structure, the related extreme points of two adjacent waveforms of the respiratory signal and the corresponding time points thereof can be obtained, so that the respiratory characteristic value of the respiratory signal related to waveform change can be simply and quickly calculated by using the obtained extreme points and the corresponding time points.

In an exemplary embodiment of the present disclosure, the extraction module includes: a distance calculation unit configured to calculate a ratio of a difference between the first minimum time point and the first maximum time point to a difference between the second maximum time point and the first minimum time point; a distance extraction unit configured to take the calculated ratio as the extracted distance feature value.

By calculating the ratio of the bottom width of the second half of the first waveform to the bottom width of the first half of the second waveform in the two adjacent waveforms, the change of the second half of the first waveform and the first half of the second waveform can be compared, and the distance characteristic value of the respiratory signal can be extracted relatively easily.

In an exemplary embodiment of the present disclosure, the extraction module includes: a feature point determination unit configured to determine, according to a predetermined amplitude scale parameter and the first maximum value point and the first minimum value point, a start time point of a segment of a rising waveform of the first waveform to the first maximum value point and a start time point of a segment of a falling waveform of the first waveform to the first minimum value as a first time point and a second time point for determining an end-expiratory start time point of the respiratory phase, respectively; a feature point calculation unit configured to calculate a ratio of a difference between the first maximum time point and the first time point to a difference between the first minimum time point and the second time point; a feature point extraction unit configured to take the calculated ratio as an extracted point feature value.

By calculating the ratio of the time corresponding to a section of rising waveform to the peak point in the first waveform to the time corresponding to a section of falling waveform to the valley point in the first waveform, the change of the waveform near the peak and the waveform near the valley of the first waveform can be compared, and the point characteristic value of the respiratory signal can be extracted relatively easily.

In an exemplary embodiment of the present disclosure, the extraction module includes: an area calculation unit configured to calculate a ratio of a first polygon area determined by the first maximum point, the second maximum point, and the first minimum point to a second polygon area determined by the first minimum point, the second maximum point, and the second minimum point; an area feature extraction unit configured to take the calculated ratio as an extracted area feature value.

By calculating the ratio of the area formed by two peak points of two adjacent waveforms and the valley point between the two waveforms to the area formed by two valley points of the two waveforms and the peak point of the second waveform, the change of the first waveform and the second waveform can be compared, and the area characteristic value of the respiratory signal can be extracted more easily.

According to yet another aspect of the present disclosure, there is provided a magnetic resonance imaging method including: determining a respiratory phase of a respiratory signal according to the method for determining the respiratory phase of a respiratory signal provided by the present disclosure; and magnetic resonance imaging of the examined part of the examined object according to the determined breathing phase.

In the method, by determining the end-expiration period of the respiration signal, the magnetic resonance imaging system can be triggered to scan at the starting time point of the determined end-expiration period, so that the motion artifact in the magnetic resonance imaging is avoided.

According to yet another aspect of the present disclosure, there is provided a magnetic resonance imaging system comprising: the above apparatus for determining a respiratory phase of a respiratory signal provided by the present disclosure is configured to determine a respiratory phase of a respiratory signal; an imaging device configured to perform magnetic resonance imaging of the examined part of the examined object according to the determined breathing phase.

In the magnetic resonance imaging system, by determining the end expiration period of the respiration signal, the magnetic resonance imaging system can be triggered to scan at the determined starting time point of the end expiration period, thereby avoiding the motion artifact in the magnetic resonance imaging.

According to yet another aspect of the present disclosure, a non-transitory readable storage medium is provided, having stored thereon a program that, when executed, causes a processor to perform a method of determining a respiratory phase of a respiratory signal as provided by the present disclosure.

Drawings

The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure. In the drawings:

FIG. 1 is a timing diagram of a respiration signal according to the related art;

FIG. 2 is a flow chart of a method of determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure;

FIG. 3 is a flow chart for obtaining respiratory characteristic values according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating two adjacent waveforms of a respiration signal, according to an embodiment of the disclosure;

FIG. 5 is a schematic diagram illustrating a distance signature of a respiration signal, according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram illustrating a point feature of a respiratory signal, according to an embodiment of the present disclosure;

FIG. 7 is a schematic diagram illustrating area characteristics of a respiration signal, according to an embodiment of the disclosure;

FIG. 8 is a schematic diagram of a configuration of an apparatus for determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure;

FIG. 9 is a graphical illustration of the classification effect of respiratory feature values using embodiments of the present disclosure; and

fig. 10 is a schematic diagram of an example of a computing device 100 implementing part of the hardware portion of the device as a method of determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure.

Detailed Description

In order that those skilled in the art will better understand the disclosure, embodiments of the disclosure will be described more clearly and completely in conjunction with the accompanying drawings of the disclosure, and it is to be understood that the described embodiments are only a part of the embodiments of the disclosure, not all of them. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without inventive step, are within the scope of the present disclosure.

According to a natural understanding of respiratory motion, a typical respiratory motion cycle consists of three phases: inspiration, expiration, and end expiration. Fig. 1 is a timing diagram of a respiration signal according to the related art, in which the horizontal axis represents time and the vertical axis represents the amplitude of respiration. As shown IN FIG. 1, EX represents the expiratory phase, IN represents the inspiratory phase, and EOE represents the end-expiratory phase. The respiratory motion is small near the end of expiration, the EOE phase. For magnetic resonance imaging, motion artifacts are negligible if image data is acquired during the end-expiration period. It follows that the key to the problem is how to determine the end-expiration phase of the breathing signal.

An exemplary embodiment of the present disclosure provides a method of determining a respiratory phase of a respiratory motion. Fig. 2 is a flow chart of a method of determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure. As shown in fig. 2, the method comprises the steps of:

in step S22, a respiratory feature value is extracted from the respiratory signal.

Respiratory feature values such as distance feature values, point feature values, and area feature values are extracted from the respiratory signal. These respiratory characteristic values are primarily indicative of waveform variations of two adjacent waveforms in the respiratory signal. Therefore, by comparing the waveform changes of two adjacent waveforms and utilizing the difference of the curve shapes of inspiration and expiration, the end-expiration stage in one waveform can be determined.

And step S24, training a respiratory signal model according to the extracted respiratory characteristic value, and determining the respiratory phase of the respiratory signal by using the respiratory signal model.

These respiration feature values are extracted from a respiration signal, such as a Pilot Tone respiration signal, and then used to train a Support Vector Machine (SVM) model. After the training of the SVM model is completed, the breathing phase of the breathing signal can be judged by using the model.

Fig. 3 is a flowchart of acquiring a respiratory characteristic value according to an embodiment of the present disclosure, as shown in fig. 3, the method includes the steps of:

in step S32, extreme points and corresponding time points of two adjacent waveforms of the respiration signal are determined.

Fig. 4 is a schematic diagram illustrating two adjacent waveforms of a respiration signal, with time represented laterally and amplitude of the respiration signal represented longitudinally, according to an embodiment of the disclosure.

First, the peak point of the first waveform and the peak point of the second waveform of the two waveforms are acquired as the first maximum value point max1 and the second maximum value point max2, respectively. Next, a valley point between the two waveforms is acquired as the first minimum point min1, and a valley point immediately after the second maximum point max2 is acquired as the second minimum point min 2.

Next, time points corresponding to the first maximum value point max1, the first minimum value point min1, the second maximum value point max2 and the second minimum value point min2, i.e., a first maximum value time point t _ max1, a first minimum value time point t _ min1, a second maximum value time point t _ max2 and a second minimum value time point t _ min2, are determined.

In step S34, a distance feature value is determined.

After the extreme point and its corresponding time point are determined, the distance feature value is calculated using the corresponding time point.

Fig. 5 is a schematic diagram illustrating a distance characteristic of a respiration signal according to an embodiment of the present disclosure, and as shown in fig. 5, D1 represents a distance difference between a first minimum time point t _ min1 and a first maximum time point t _ max1, and D2 represents a distance difference between a second maximum time point t _ max2 and a first minimum time point t _ min 1. The distance characteristic value can be calculated by using the following formula:

f1＝(t_min1–t_max1)/(t_max2–t_min1)。

the above formula can also be expressed as f1 ═ D1/D2, where f1 represents the distance eigenvalue.

In step S36, a point feature value is determined.

After the extreme points and their corresponding time points are determined, the point feature values are calculated using the corresponding time points.

Fig. 6 is a schematic diagram illustrating the point characteristics of the respiration signal, as shown in fig. 6, with N1 and N2 representing possible end-expiration periods on the first waveform, and h representing the amplitude of the respiration signal at the first maximum point, according to an embodiment of the disclosure.

The start time point t _1 (not shown) of a segment of the rising waveform N1 on the first waveform to the first max1 is determined based on the predetermined amplitude scaling parameter p, the first max point max1 and the first min point 1, and the start time point t _2 (not shown) of a segment of the falling waveform N2 on the first waveform to the first min point min _1 is determined. t _1 is referred to as a first time, and t _2 is referred to as a second time.

In an exemplary embodiment of the present disclosure, the first time t _1 and the second time t _2 are respectively calculated according to the following two formulas:

mag(t_1)＝mag(t_max1)*p+mag(t_min1)*(1-p)；

mag(t_2)＝mag(t_max1)*(1-p)+mag(t_min1)*p。

where mag (t) is the amplitude of the respiration signal as a function of time t, and p is a predetermined amplitude scaling parameter.

For example, assuming that the predetermined amplitude scaling parameter p is 80%, the first time t _1 and the second time t _2 should satisfy:

mag(t_1)＝mag(t_max1)*0.8+mag(t_min1)*0.2；

mag(t_2)＝mag(t_max1)*0.2+mag(t_min1)*0.8。

after the possible end-expiratory phase start time points, i.e. the first time point t _1 and the second time point t _2, have been determined, the ratio of the difference between the first maximum time point t _ max1 and the first time point t _1 to the difference between the first minimum time point t _ min1 and the second time point t _2 is calculated, taking the result of the calculation as the point feature value. That is, the point feature value is calculated using the following formula:

f2＝(t_max1-t_1)/(t_min1-t_2)。

in step S38, an area feature value is determined.

After the extreme points and their corresponding time points are determined, the area feature values are calculated using the corresponding time points.

Fig. 7 is a schematic diagram illustrating an area characteristic of a respiration signal according to an embodiment of the present disclosure, and as shown in fig. 7, a first maximum point max1 and a second maximum point max2 are connected such that a first polygon having an area represented as S1 is formed between the first maximum point max1, the second maximum point max2, and the first minimum point min 1. Meanwhile, the first minimum point min1 and the second minimum point min2 are connected such that a second polygon having an area represented as S2 is formed between the first minimum point min1, the second maximum point max2 and the second minimum point min 2.

In one embodiment of the present disclosure, the area eigenvalue is calculated using the following formula:

f3＝s(t_max1,t_max2)/s(t_min1,t_min2)。

where f3 denotes an area characteristic value and S denotes an area of a polygon surrounded by extreme points, in practice, f3 is a ratio S1/S2 of the two areas S1 and S2 shown in fig. 7.

The steps S34 to S38 in the embodiment of the present disclosure are not limited to be executed in the order, and may be executed in different orders or simultaneously.

An embodiment of the present disclosure also provides an apparatus for determining a respiratory phase of a respiratory signal. Fig. 8 is a schematic structural diagram of an apparatus for determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure, and as shown in fig. 8, the apparatus includes an extraction module 82 and a determination module 84.

The extraction module 82 is configured to extract respiratory feature values from the respiratory signal for training the SVM model. These respiratory characteristics include, but are not limited to, distance characteristic values, point characteristic values, and area characteristic values.

In an exemplary embodiment of the present disclosure, the distance eigenvalue is calculated by the following formula:

f1＝(t_min1–t_max1)/(t_max2–t_min1)。

f1 denotes a distance characteristic value, t _ min1 denotes a valley point between two adjacent waveforms in the respiration signal, t _ max1 denotes a peak point of the first waveform, and t _ max2 denotes a peak point of the second waveform.

In an exemplary embodiment of the present disclosure, it is assumed that the time points of 80% of the maximum and minimum point amplitudes are the first time t _1 and the second time t _2, respectively, that is, the conditions mag (t _1) ═ mag (t _ max1) × 0.8+ mag (t _ min1) × 0.2 and mag (t _2) ═ mag (t _ max1) × 0.2+ mag (t _ min1) × 0.8 are satisfied.

After the first time t _1 and the second time t _2 are calculated by the above formula, the point feature value is calculated by the formula f2 ═ t _ max1-t _1)/(t _ min1-t _2), and the area feature value is calculated by the formula f3 ═ s (t _ max1, t _ max2)/s (t _ min1, t _ min2), where f2 represents the point feature value, f3 represents the area feature value, s (t1, t2) is defined as the area of the closed polygon formed between all time points from time t1 to t2 and the waveform, for example, s (t _ max1, t _ max2) represents the area of the closed polygon formed at all time points from time t _1 to t _ max2, and s (t _ min1, t _ min2) represents the area of the closed polygon formed at all time points from time t _ min1 to t _ min 2.

After extracting the respiratory feature values from the respiratory signal, the determination module 84 trains an SVM model, i.e., a respiratory signal model, using the respiratory feature values. After the training of the SVM model is completed, the model can be used for judging the respiratory phase.

Fig. 9 is a schematic diagram of the classification effect of the respiration feature values using the embodiment of the present disclosure. As shown in fig. 9, the three axes respectively represent the distance feature, the point feature and the area feature, the solid square small points represent the peak of the waveform determined by the classifier after inputting the distance feature value, the point feature value and the area feature value, and the solid circular small points represent the valley of the waveform determined by the classifier after inputting the distance feature value, the point feature value and the area feature value. In this way, the end-expiration period of the respiration signal is determined, so that the magnetic resonance system can be triggered to scan in the end-expiration period, the quality of the magnetic resonance image is improved, and the motion artifact is avoided.

An exemplary embodiment of the present disclosure also provides a magnetic resonance imaging method. The magnetic resonance imaging method is an image output method, and firstly, the breathing phase is determined by using the method for determining the breathing phase of the breathing signal, and secondly, the examined part of the examined body is subjected to magnetic resonance imaging according to the determined breathing phase. Specifically, the magnetic resonance imaging system is triggered to scan in the end-expiration period of the respiration signal, so that the motion artifact of the magnetic resonance image is avoided, and the image of the living tissue can be generated with high precision.

An exemplary embodiment of the present disclosure also provides a magnetic resonance imaging system, including the apparatus for determining a respiratory phase and the imaging apparatus provided by the present disclosure. After the subject is placed in the magnetic resonance imaging system, the respiratory phase, in particular the end-expiratory phase, of the respiratory signal is determined using the apparatus for determining respiratory phase provided by the present disclosure. Next, the magnetic resonance imaging system is triggered to emit magnetic resonance signals for scanning at the starting point in time of the end-expiration phase and the external magnetic field is modified with the gradient coils, i.e. on the one hand the slice of the subject is selected and on the other hand a regional encoding of the magnetic resonance signals is generated. The magnetic resonance signals are then reconstructed, for example by fourier transformation, to produce images of selected slice layers for medical diagnosis. The generation and detection of magnetic resonance signals is achieved with a high frequency system comprising a transmitting antenna injecting high frequency excitation pulses into the body of the subject and a receiving antenna receiving resonance signals modulated by the subject.

The disclosed embodiments also provide a non-transitory readable storage medium having stored thereon a program that, when executed, causes a processor to perform the method of determining a respiratory phase of a respiratory signal as provided by the present disclosure.

Fig. 10 is a schematic diagram of an example of a computing device 100 implementing part of the hardware portion of the device as a method of determining a respiratory phase of a respiratory signal according to an embodiment of the present disclosure. As shown in fig. 10, the computing apparatus 100 may include a CPU1010 for performing overall control, a Read Only Memory (ROM) 1020 for storing system software, a Random Access Memory (RAM) 1030 for storing write/Read data, a storage unit 1040 for storing various programs and data, an input/output unit 1050 as an interface for input and output, and a communication unit 1060 for implementing a communication function. Alternatively, the CPU1010 may be replaced by a processor such as a microprocessor MCU or a programmable logic device FPGA. The input/output unit 1050 may include various interfaces such as an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one port of the ports of the I/O interface), a network interface, and the like. It will be understood by those skilled in the art that the structure shown in fig. 10 is merely an illustration, and does not limit the hardware configuration of the master control system. For example, computing device 100 may also include more or fewer components than shown in FIG. 10, or have a different configuration than shown in FIG. 10.

It should be noted that the CPU1010 described above may include one or more processors and/or other data processing circuitry that may be referred to generally in this disclosure as a "means for determining a respiratory phase. The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuitry may be a single, stand-alone processing module, or incorporated, in whole or in part, into any of the other components in the computing device 100.

The storage unit 1040 may be configured to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the main control instruction calculation method described in this disclosure, and the CPU1010 implements the main control instruction calculation method by operating the software programs and modules stored in the storage unit 1040. The storage unit 1040 may include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the storage unit 1040 may further include memory located remotely from the CPU1010, which may be connected to the computing device 100 over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The communication unit 1060 serves to receive or transmit data via a network. Specific examples of such networks may include wireless networks provided by a communications provider of computing device 100. In one example, the communication unit 1060 includes a Network adapter (NIC) that may be connected to other Network devices through a base station to communicate with the internet. In one example, the communication unit 1060 may be a Radio Frequency (RF) module for communicating with the internet in a wireless manner.

In the embodiment of the disclosure, a breathing signal model is trained based on a machine learning method such as an SVM method by extracting feature values of a breathing signal such as Pilot Tone breathing signal, and a breathing phase of the breathing signal is further determined based on the breathing signal model, so that the beneficial effects of robustness and high performance and Pilot Tone application are achieved.

The foregoing is merely a preferred embodiment of the present disclosure, and it should be noted that modifications and embellishments could be made by those skilled in the art without departing from the principle of the present disclosure, and these should also be considered as the protection scope of the present disclosure.