# US 11,998,308 B2 · Method and apparatus for determining respiration phase, magnetic resonance imaging method and system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,998,308 B2
- Document ID: US11998308B2
- Status: Granted
- Kind: B2
- Application number: 16/998,340
- Filed: 2020-08-20
- Published: 2021-02-25
- Granted: 2024-06-04
- Earliest claimed: 2019-08-21
- Assignees: Siemens Healthineers AG
- Applicants: Siemens Healthcare GmbH
- Inventors: Jin Qiang He; De He Weng; Shu Qun Xie; Fang Dong
- Web page: https://patentgrep.com/patent/US11998308B2

## CPC

- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/0816: {Measuring devices for examining respiratory frequency (measuring frequency of electric signals G01R23/00)}
- A61B 5/113: occurring during breathing
- A61B 5/7235: {Details of waveform analysis (detecting specific parameters of the electrocardiograph cycle A61B5/349)}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/7267: {involving training the classification device}
- A61B 5/7271: {Specific aspects of physiological measurement analysis (specific diagnostics methods using bioelectric or biomagnetic signals A61B5/316)}
- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- A61B 5/7292: {Prospective gating, i.e. predicting the occurrence of a physiological event for use as a synchronisation signal}
- A61B 5/7207: {of noise induced by motion artifacts}
- A61B 5/7285: {for synchronizing or triggering a physiological measurement or image acquisition with a physiological event or waveform, e.g. an ECG signal}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

The present disclosure provides techniques for determining a respiration phase by extracting a distance characteristic value, a score characteristic value, and an area characteristic value from the respiration signal, wherein the distance characteristic value, the score characteristic value and the area characteristic value are used to indicate waveform variation between two adjacent waveforms in the respiration signal. The techniques include training a respiration signal model according to the distance characteristic value, the score characteristic value, and the area characteristic value to determine the respiration phase of the respiration signal using the respiration signal model.

## Claims

### Claim 1

A method for determining a respiration phase of a respiration signal, comprising:
extracting, via one or more processors, a distance characteristic value, a score characteristic value, and an area characteristic value from the respiration signal, the distance characteristic value, the score characteristic value, and the area characteristic value indicating a waveform variation between two adjacent waveforms in the respiration signal;
training, via one or more processors, a respiration signal model according to the distance characteristic value, the score characteristic value, and the area characteristic value;
determining, via one or more processors, the respiration phase of the respiration signal using the respiration signal model; and
performing, via a magnetic resonance imaging (MRI) apparatus, magnetic resonance imaging of an examination region of an examination subject using the determined respiration phase,
wherein the area characteristic value represents a ratio of (i) an area formed by two crest points of the two adjacent waveforms in the respiration signal and a trough point between the two adjacent waveforms in the respiration signal to (ii) an area formed by a second waveform of the two adjacent waveforms in the respiration signal.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the distance characteristic value represents a ratio of (i) a width of a second-half-waveform of a first waveform of the two adjacent waveforms in the respiration signal to (ii) a width of a first-half-waveform of a second waveform of the two adjacent waveforms in the respiration signal.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the score characteristic value represents a ratio of (i) a width of a rising waveform portion leading to a crest point of a first waveform of the two adjacent waveforms in the respiration signal to (ii) a width of a falling waveform portion leading to a trough point of the first waveform.

### Claim 4 (depends on 1)

The method as claimed in claim 1, further comprising:
prior to extracting the distance characteristic value, the score characteristic value, and the area characteristic value from the respiration signal:
acquiring the two crest points of the two adjacent waveforms in the respiration signal as a first maximum point and a second maximum point, respectively;
acquiring the trough point between the two adjacent waveforms in the respiration signal as a first minimum point;
acquiring a trough point of the second waveform after the second maximum point as a second minimum point; and
determining time points corresponding to the first maximum point, the first minimum point, the second maximum point, and the second minimum point, respectively, as a first maximum time point, a first minimum time point, a second maximum time point, and a second minimum time point.

### Claim 5 (depends on 4)

The method as claimed in claim 4, wherein extracting the distance characteristic value from the respiration signal comprises:
calculating a ratio of (i) a difference value between the first minimum time point and the first maximum time point to (ii) the difference value between the second maximum time point and the first minimum time point; and
extracting the distance characteristic value as the calculated ratio.

### Claim 6 (depends on 4)

The method as claimed in claim 4, wherein extracting the score characteristic value from the respiration signal comprises:
determining, based on a predetermined amplitude ratio parameter, the first maximum point, and the first minimum point, (i) a start time point of a rising waveform portion leading to the first maximum point of a first waveform of the two adjacent waveforms, and (ii) a start time point of a falling waveform portion leading to the first minimum point of the first waveform, as (i) a first time point, and (ii) a second time point, respectively, for determining an end-of-expiration start time point of the respiration phase;
calculating a ratio of (i) a difference value between the first maximum time point and the first time point to (ii) a difference value between the first minimum time point and the second time point; and
extracting the score characteristic value as the calculated ratio.

### Claim 7 (depends on 6)

The method as claimed in claim 6, wherein:
the first time point is determined by evaluating:
mag(t_1)=mag(t_max1)*p+mag(t_min1)*(1−p),
the second time point is determined by evaluating:
mag(t_2)=mag(t_max1)*(1−p)+mag(t_min1)*p,
t_1 represents the first time point,
t_max1 represents the first maximum time point,
p represents an amplitude ratio parameter,
t_min1 represents the first minimum time point, and
mag represents an amplitude function.

### Claim 8 (depends on 7)

The method as claimed in claim 7, wherein the amplitude ratio parameter p is equal to 80%.

### Claim 9 (depends on 4)

The method as claimed in claim 4, wherein extracting the area characteristic value from the respiration signal comprises:
calculating a ratio of (i) a first polygon area determined by the first maximum point, the second maximum point, and the first minimum point to (ii) a second polygon area determined by the first minimum point, the second maximum point, and the second minimum point; and
extracting the area characteristic value as the calculated ratio.

### Claim 10

An apparatus for determining a respiration phase of a respiration signal, comprising:
extraction circuitry configured to extract a distance characteristic value, a score characteristic value, and an area characteristic value from the respiration signal, the distance characteristic value, the score characteristic value, and the area characteristic value indicating waveform variation between two adjacent waveforms in the respiration signal; and
determining circuitry configured to (i) train a respiration signal model according to the distance characteristic value, the score characteristic value, and the area characteristic value, and (ii) determine the respiration phase of the respiration signal using the respiration signal model,
wherein a magnetic resonance imaging (MRI) apparatus uses the determined respiration phase of the respiration signal to perform magnetic resonance imaging of an examination region of an examination subject, and
wherein the area characteristic value represents a ratio of (i) an area formed by two crest points of the two adjacent waveforms in the respiration signal and a trough point between the two adjacent waveforms in the respiration signal to (ii) an area formed by a second waveform of the two adjacent waveforms in the respiration signal.

### Claim 11 (depends on 10)

The apparatus as claimed in claim 10, wherein the extraction circuitry is further configured to:
acquire the two crest points of the two adjacent waveforms of the respiration signal as a first maximum point and a second maximum point, respectively;
acquire the trough point between the two adjacent waveforms of the respiration signal as a first minimum point;
acquire a trough point of the second waveform after the second maximum point as a second minimum point; and
determine time points corresponding to the first maximum point, the first minimum point, the second maximum point, and the second minimum point, respectively, as a first maximum time point, a first minimum time point, a second maximum time point, and a second minimum time point.

### Claim 12 (depends on 11)

The apparatus as claimed in claim 11, wherein the extraction circuitry is further configured to:
calculate a ratio of (i) a difference value between the first minimum time point and the first maximum time point to (ii) a difference value between the second maximum time point and the first minimum time point; and
extract the distance characteristic value as the calculated ratio.

### Claim 13 (depends on 11)

The apparatus as claimed in claim 11, wherein the extraction circuitry is further configured to:
determine, based on a predetermined amplitude ratio parameter, the first maximum point, and the first minimum point, (i) a start time point of a rising waveform portion leading to the first maximum point of a first waveform of the two adjacent waveforms, and (ii) a start time point of a falling waveform portion leading to the first minimum point of the first waveform, as (i) a first time point, and (ii) a second time point, respectively, to determine an end-of-expiration start time point of the respiration phase;
calculate a ratio of (i) a difference value between the first maximum time point and the first time point to (ii) a difference value between the first minimum time point and the second time point; and
extract the score characteristic value as the calculated ratio.

### Claim 14 (depends on 11)

The apparatus as claimed in claim 11, wherein the extraction circuitry is further configured to:
calculate a ratio of (i) a first polygon area determined by the first maximum point, the second maximum point, and the first minimum point to (ii) a second polygon area determined by the first minimum point, the second maximum point, and the second minimum point; and
extract the area characteristic value as the calculated ratio.

### Claim 15

A non-transitory readable storage medium having a program stored thereon that, when executed by one or more processors, cause the one or more processors to:
extract a distance characteristic value, a score characteristic value, and an area characteristic value from a respiration signal, the distance characteristic value, the score characteristic value, and the area characteristic value indicating a waveform variation between two adjacent waveforms in the respiration signal;
train a respiration signal model according to the distance characteristic value, the score characteristic value, and the area characteristic value;
determine a respiration phase of the respiration signal using the respiration signal model; and
perform a magnetic resonance imaging of an examination region of an examination subject using the determined respiration phase,
wherein the area characteristic value represents a ratio of (i) an area formed by two crest points of the two adjacent waveforms in the respiration signal and a trough point between the two adjacent waveforms in the respiration signal to (ii) an area formed by a second waveform of the two adjacent waveforms in the respiration signal.

### Claim 16 (depends on 1)

The method as claimed in claim 1, wherein the determined respiration phase is a phase within a respiratory motion cycle of the examination subject that comprises an expiration phase, an aspiration phase, and an end-of-expiration (EOE) phase.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
triggering the MRI apparatus to perform the magnetic resonance imaging of the examination region of the examination subject at a start time point of the EOE phase of the respiratory motion cycle of the examination subject.

### Claim 18 (depends on 1)

The method as claimed in claim 1, wherein the area formed by the second waveform comprises an area formed by three points in the second waveform.

### Claim 19 (depends on 1)

The method as claimed in claim 1, wherein:
the ara formed by the two crest points of the two adjacent waveforms in the respiration signal and the trough point between the two adjacent waveforms in the respiration signal comprises a first polygon area,
the area formed by the second waveform of the two adjacent waveforms in the respiration signal comprises a second polygon area, and
extracting the area characteristic value comprises calculating a ratio of the first polygon area to the second polygon area.