CN109741830A - The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement - Google Patents
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement Download PDFInfo
- Publication number
- CN109741830A CN109741830A CN201910018166.9A CN201910018166A CN109741830A CN 109741830 A CN109741830 A CN 109741830A CN 201910018166 A CN201910018166 A CN 201910018166A CN 109741830 A CN109741830 A CN 109741830A
- Authority
- CN
- China
- Prior art keywords
- breath signal
- signal
- period
- simulation
- ideal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The chest and abdomen surface region breath signal period forecasting method of list binary cycle mixing judgement of the present invention belongs to the technical fields such as medical oncology, precision instrument, engineering technology and mathematics；This method constructs ideal monocycle breath signal first, then periodic extension is carried out, obtain ideal multicycle breath signal, periodicity extraction finally is carried out to ideal multicycle breath signal, entire extraction process is carried out in data volume at during two times of two imagination weeks, and periodicity extraction can be completed within two periods；This method method can accurately extract the period of ideal multicycle breath signal, establish emulation experiment basis for Accurate Prediction respiratory movement.
Description
Technical field
The chest and abdomen surface region breath signal period forecasting method of list binary cycle of the present invention mixing judgement belong to medical oncology,
The technical fields such as precision instrument, engineering technology and mathematics.
Background technique
Radiotherapy (being hereinafter radiotherapy) is one of most important means for the treatment of cancer.About 70% cancer patient
Radiotherapy can be used during treating cancer, there are about 40% cancers can cure by radiotherapy.The effect of radiation therapy with put
The precision of radiation exposure to tumor region is related with dosage.It is intraperitoneal that alimentary system malignant tumour is located at thoracic cavity, by respiratory movement
It influences, the position of tumour and volume can all change over time, and cause radioactive ray irradiation precision to reduce, to influence radiotherapy effect
Fruit.
In order to solve the problems, such as that respiratory movement reduces radiotherapeutic effect, many scholars have carried out target area flared end, have held one's breath, breathe door
Control, passive pressurization, the research work of the four-dimensional techniques or methods such as radiotherapy and real-time tracking.These work effectively reduce breathing fortune
The dynamic influence to radiotherapeutic effect, however, since these work are all the lag compensation work carried out after respiratory movement generation, because
This can not fundamentally overcome the problems, such as that respiratory movement reduces radiotherapeutic effect.
To solve the above-mentioned problems, some scholars begin one's study lead compensation method, and this method is transported firstly the need of to breathing
It is dynamic to be predicted.Currently, respiratory movement predicting method can be divided into following two major classes: the first, model prediction method, it passes through monitoring
Respiratory movement early period data establish respiratory movement model, then following respiratory movement is speculated based on model；The second, model-free
Prediction technique, it passes through the respiratory movement mode observed and is trained, and didactic learning algorithm is formed, by learning come pre-
Survey following respiratory movement.
Although respiratory movement constantly repeats air-breathing and expiration movement, respiratory movement with air-breathing and is not exhaled as one
Period is simply repeated, and during each air-breathing and expiration, by itself and external influence, period and amplitude all can
There is change, model prediction method can not look after this variation, therefore precision of prediction will receive restriction, so, more scholars open
Beginning is attempted in model-free prediction technique, for example, predicting respiratory movement with Gaussian process recurrence.
It is a kind of pervasive prediction algorithm that Gaussian process, which returns, predicts Future Data by study given data, is predicted
As a result it is provided in the form of mean value and variance.Since Gaussian process regression algorithm itself is not to predict for respiratory movement merely
And it proposes, therefore do not take into account that respirometric some constraint conditions.If respirometric constraint condition taken into account,
Estimation range will be reduced, prediction result also will be more accurate.
For respiratory movement, frequency can be limited within the scope of some, therefore can be by obtaining breath signal
Period or frequency carry out constrained forecast as a result, improve precision of prediction.Be conducive to improve prediction as it can be seen that obtaining the respirometric period
Precision.
However, since respiratory movement is not monocyclic simple repetition, be difficult with two same characteristic features values away from
From judging the period.So, if obtaining the respirometric period has become the key technical problem for improving precision of prediction.
Summary of the invention
In order to predict the period of breath signal, the present invention starts with from ideal breath signal, proposes a kind of breath signal
Periodicity extraction method, this method not only include according to the work of breathing rule building identical breaths signal, but also including to ideal
The work that the breath signal period extracts.
The object of the present invention is achieved like this:
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement, comprises the steps of:
Step a, ideal monocycle breath signal is constructed；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breathing
Signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
Above-mentioned list binary cycle mixes the chest and abdomen surface region breath signal period forecasting method of judgement, structure described in step a
Build ideal monocycle breath signal, comprising the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal.
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement, comprises the steps of:
Step a, ideal monocycle breath signal is constructed；
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breathing
Signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
A kind of ideal monocycle breath signal construction method, comprising the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal.
A kind of ideal multicycle breath signal periodicity extraction method, comprising the following steps:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
The utility model has the advantages that
Although first, the present invention is under the jurisdiction of medical oncology technical field, the present invention be pair from the technical point of view
Signal characteristic quantity extracts, and singly cannot achieve and diagnose to disease from the point of view of technical purpose and effect of the invention
And treatment, therefore it is not belonging to the diagnostic and therapeutic method of disease described in Patent Law Article 25, object is not present in the present invention
Problem.
The second, the present invention discloses abundant enough, as long as the source code that specification part is recorded is transported in MATLAB software
Row, can be obtained operation result, either those skilled in the art are also non-those skilled in the art, can realize this Shen
Please.
Third, the present invention also provides a kind of ideal monocycle breath signal construction method, this method only needs to use three
Section SIN function can fit the breath signal in a cycle, method is simple, function is simple, and fitting result with really exhale
It is corresponding to inhale movement.
4th, the method for the present invention carries out during data volume identical two imaginations week, and with this research team Shen on the same day
The patent of invention " the human body chest and abdomen surface region breath signal period forecasting method calculated based on variance " of report is compared, as long as one
Periodicity extraction can be completed in a true period, therefore calculation amount is smaller, from simulation result it can also be seen that, runing time from
0.40s is increased to 0.26s.
5th, the method for the present invention carries out during data volume identical two imaginations week, declares on the same day with this research team
Patent of invention " in conjunction with three periods judge chest and abdomen surface region breath signal period forecasting method ", it is contemplated that respiratory movement is exhaled
Gas and breathing process are asymmetric, therefore data can be realized within two imaginary periods and be mutually authenticated, and pseudoperiodicity is being avoided to occur,
Prediction result more accurately meanwhile, it is capable to runing time is further increased, from simulation result it can also be seen that, runing time
0.26s is increased to from 0.32s.
Detailed description of the invention
Fig. 1 is ideal multicycle breath signal figure.
Program operation result when Fig. 2 is periodicity extraction.
Fig. 3 is program runnable interface.
Specific embodiment
The specific embodiment of the invention is described in further detail with reference to the accompanying drawing.
Specific embodiment one
The present embodiment is the chest and abdomen surface region breath signal period forecasting embodiment of the method for single binary cycle mixing judgement.
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement of the present embodiment, by following step
Rapid composition:
Step a, ideal monocycle breath signal is constructed；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breathing
Signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
Specific embodiment two
The present embodiment is the chest and abdomen surface region breath signal period forecasting embodiment of the method for single binary cycle mixing judgement.
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement of the present embodiment, specific real
On the basis of applying example one, the ideal monocycle breath signal of building described in step a is further limited, comprising the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal.
Specific embodiment three
The present embodiment is the chest and abdomen surface region breath signal period forecasting embodiment of the method for single binary cycle mixing judgement.
The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement of the present embodiment, by following step
Rapid composition:
Step a, ideal monocycle breath signal is constructed；
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breathing
Signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
Specific embodiment four
The present embodiment is a kind of ideal monocycle breath signal construction method embodiment.
A kind of ideal monocycle breath signal construction method of the present embodiment, comprising the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and is suspended
Process three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With class pause process
Duration T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation air-breathing letter
Number；It is 4T with the period2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3
Phase is that the sine function simulation class of [π, 3 pi/2s] suspends process, obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the opposite width of breath signal will be simulated
Value is adjusted between [c, b], and the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, it obtains
Ideal monocycle breath signal.
Specific embodiment five
The present embodiment is a kind of ideal multicycle breath signal periodicity extraction embodiment of the method.
A kind of ideal multicycle breath signal periodicity extraction method of the present embodiment, comprising the following steps:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, the sum of period 1 all data and all numbers of the first two cycles are calculated
The sum of according to, enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold
Value, if:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
Specific embodiment seven
The present embodiment is the chest and abdomen surface region breath signal period forecasting embodiment of the method for single binary cycle mixing judgement.
In order to verify the method for the present invention, this method is run on MATLAB R2014a software.Applied computer is matched
It sets as follows:
Allocation of computer table
| Operating system | 7 Ultimate X86 of Windows |
| Processor | Intel(R)Core(TM)i5-8250OU@1.60GHz 1.80GHz |
| Memory is installed | 8.00GB |
The MATLAB program write is as follows:
Program operation result is distinguished.Wherein, Fig. 1 is the signal of ideal multicycle breath signal
Figure, program operation result when Fig. 2 is periodicity extraction, Fig. 3 is program runnable interface.
Program operation result shows that the method for the present invention has accurately extracted the signal period from respiratory movement signal.
Finally, thank state natural sciences fund general project " in radiotherapy human body chest and abdomen surface dynamic 3 D measurement and
Region breath Motion Estimation and space-time integrated are predicted " (project number: 61571168) and Students' Innovation project is " swollen towards lung
The chest and abdomen surface respiratory movement forecasting research of tumor radiotherapy " (project number: 201810214267) to the fund branch of this patent
It holds.
Claims (5)
1. the chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement, which is characterized in that by following step
Rapid composition:
Step a, ideal monocycle breath signal is constructed；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breath signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, calculate the sum of period 1 all data and all data of the first two cycles it
With enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold value,
If:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
2. the chest and abdomen surface region breath signal period forecasting method of list binary cycle mixing judgement according to claim 1,
It is characterized in that, the ideal monocycle breath signal of building described in step a, comprising the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and suspends process
Three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With continuing for class pause process
Time T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation inspiration signal；With
Period is 4T2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3Phase
Suspend process for the sine function simulation class of [π, 3 pi/2s], obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the relative magnitude tune of breath signal will be simulated
It is whole to arrive between [c, b], the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, obtain ideal
Monocycle breath signal.
3. the chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement, which is characterized in that by following step
Rapid composition:
Step a, ideal monocycle breath signal is constructed；
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and suspends process
Three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With continuing for class pause process
Time T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation inspiration signal；With
Period is 4T2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3Phase
Suspend process for the sine function simulation class of [π, 3 pi/2s], obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the relative magnitude tune of breath signal will be simulated
It is whole to arrive between [c, b], the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, obtain ideal
Monocycle breath signal；
Step b, periodic extension is carried out to the ideal monocycle breath signal that step a is obtained, obtains ideal multicycle breath signal；
Step c, periodicity extraction is carried out to the ideal multicycle breath signal that step b is obtained, comprising:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, calculate the sum of period 1 all data and all data of the first two cycles it
With enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold value,
If:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
4. a kind of ideal monocycle breath signal construction method, which comprises the following steps:
Step a1, according to the process of mankind's eupnea, respiratory movement is divided into breathing process, exhalation process and class and suspends process
Three phases；
Step a2, the duration T of breathing process is determined respectively1, exhalation process duration T2With continuing for class pause process
Time T3；
It step a3, is 4T with the period1Phase is the sine function simulation breathing process of [0, pi/2], obtains simulation inspiration signal；With
Period is 4T2Phase is the sine function simulation exhalation process of [pi/2, π], obtains simulation breath signal；It is 4T with the period3Phase
Suspend process for the sine function simulation class of [π, 3 pi/2s], obtains simulation class pause signal；
Step a4, the relative magnitude for simulating inspiration signal is adjusted between [a, b], the relative magnitude tune of breath signal will be simulated
It is whole to arrive between [c, b], the relative magnitude for simulating class pause signal is adjusted between [a, c]；
Step a5, obtained simulation inspiration signal, simulation breath signal and simulation class pause signal is end to end, obtain ideal
Monocycle breath signal.
5. a kind of ideal multicycle breath signal periodicity extraction method, which comprises the following steps:
Step c1, the DC component for the ideal multicycle breath signal that extraction step b is obtained；
Step c2, the DC component that step c1 is obtained is subtracted with the ideal multicycle breath signal that step b is obtained；
Step c3, given threshold；
Step c4, cycle data variable is set as 1, enters step c5；
Step c5, according to cycle data variable, calculate the sum of period 1 all data and all data of the first two cycles it
With enter step c3；
Step c6, judge whether the difference of the sum of the sum of period 1 all data and all data of the first two cycles is greater than threshold value,
If:
It is cycle data variable+1, return step c5；
It is no, enter step c7；
Step c7, cycle data variable is the period of multicycle breath signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910018166.9A CN109741830B (en) | 2019-01-09 | 2019-01-09 | Single-cycle and double-cycle mixed judgment type chest and abdomen surface area respiratory signal cycle prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910018166.9A CN109741830B (en) | 2019-01-09 | 2019-01-09 | Single-cycle and double-cycle mixed judgment type chest and abdomen surface area respiratory signal cycle prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109741830A true CN109741830A (en) | 2019-05-10 |
| CN109741830B CN109741830B (en) | 2022-12-06 |
Family
ID=66363966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910018166.9A Active CN109741830B (en) | 2019-01-09 | 2019-01-09 | Single-cycle and double-cycle mixed judgment type chest and abdomen surface area respiratory signal cycle prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741830B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109741827A (en) * | 2019-01-09 | 2019-05-10 | 哈尔滨理工大学 | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with binary cycle |
| CN109741829A (en) * | 2019-01-09 | 2019-05-10 | 哈尔滨理工大学 | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with three periods |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2008686C1 (en) * | 1991-07-09 | 1994-02-28 | Ростовский медицинский институт | Method for forecasting development of complications in children suffering from generalized respiratory conservative infection |
| CN101628154A (en) * | 2008-07-16 | 2010-01-20 | 深圳市海博科技有限公司 | Image guiding and tracking method based on prediction |
| CN101637388A (en) * | 2008-07-29 | 2010-02-03 | 深圳市海博科技有限公司 | Respiratory movement predicting method |
| CN102481127A (en) * | 2009-08-13 | 2012-05-30 | 帝人制药株式会社 | Device for calculating respiratory waveform information and medical device using respiratory waveform information |
| CN102613964A (en) * | 2012-03-12 | 2012-08-01 | 深圳市视聆科技开发有限公司 | Method and system for acquiring physiological signal cycle |
| TW201544074A (en) * | 2014-05-22 | 2015-12-01 | Apex Medical Corp | Breathing waveform recognition method and system thereof |
| CN105286998A (en) * | 2015-11-03 | 2016-02-03 | 苏州大学 | Human body pleuroperitoneal cavity motion simulation device caused by breathing |
-
2019
- 2019-01-09 CN CN201910018166.9A patent/CN109741830B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2008686C1 (en) * | 1991-07-09 | 1994-02-28 | Ростовский медицинский институт | Method for forecasting development of complications in children suffering from generalized respiratory conservative infection |
| CN101628154A (en) * | 2008-07-16 | 2010-01-20 | 深圳市海博科技有限公司 | Image guiding and tracking method based on prediction |
| CN101637388A (en) * | 2008-07-29 | 2010-02-03 | 深圳市海博科技有限公司 | Respiratory movement predicting method |
| CN102481127A (en) * | 2009-08-13 | 2012-05-30 | 帝人制药株式会社 | Device for calculating respiratory waveform information and medical device using respiratory waveform information |
| CN102613964A (en) * | 2012-03-12 | 2012-08-01 | 深圳市视聆科技开发有限公司 | Method and system for acquiring physiological signal cycle |
| TW201544074A (en) * | 2014-05-22 | 2015-12-01 | Apex Medical Corp | Breathing waveform recognition method and system thereof |
| CN105286998A (en) * | 2015-11-03 | 2016-02-03 | 苏州大学 | Human body pleuroperitoneal cavity motion simulation device caused by breathing |
Non-Patent Citations (2)
| Title |
|---|
| 周寿军: "基于后验概率的呼吸信号预测", 《中国医学生物工程学报》 * |
| 孟晓亮: "基于三维傅里叶变换的胸腹表面测量", 《光学精密工程》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109741827A (en) * | 2019-01-09 | 2019-05-10 | 哈尔滨理工大学 | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with binary cycle |
| CN109741829A (en) * | 2019-01-09 | 2019-05-10 | 哈尔滨理工大学 | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with three periods |
| CN109741829B (en) * | 2019-01-09 | 2022-10-28 | 哈尔滨理工大学 | Chest and abdomen surface area respiratory signal period prediction method combining three-period judgment |
| CN109741827B (en) * | 2019-01-09 | 2022-11-01 | 哈尔滨理工大学 | Chest and abdomen surface area respiratory signal period prediction method combining double period judgment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109741830B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3695882A1 (en) | Computing radiotherapy dose distribution | |
| Vedam et al. | Predicting respiratory motion for four‐dimensional radiotherapy | |
| Liu et al. | Range and dose verification in proton therapy using proton-induced positron emitters and recurrent neural networks (RNNs) | |
| Seregni et al. | Real-time tumor tracking with an artificial neural networks-based method: a feasibility study | |
| CN109741830A (en) | The chest and abdomen surface region breath signal period forecasting method of single binary cycle mixing judgement | |
| CN109741828A (en) | A kind of human body chest and abdomen surface region breath signal period forecasting method in radiotherapy | |
| CN109741831A (en) | The human body chest and abdomen surface region breath signal period forecasting method calculated based on variance | |
| Li et al. | A novel deep learning framework for internal gross target volume definition from 4D computed tomography of lung cancer patients | |
| Geneser et al. | Quantifying variability in radiation dose due to respiratory-induced tumor motion | |
| CN109741827A (en) | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with binary cycle | |
| Chang et al. | Real-time respiratory tumor motion prediction based on a temporal convolutional neural network: Prediction model development study | |
| CN109741829A (en) | The chest and abdomen surface region breath signal period forecasting method judged in conjunction with three periods | |
| Rostampour et al. | Markerless respiratory tumor motion prediction using an adaptive neuro-fuzzy approach | |
| Thaper et al. | Degree of reduction in normal liver complication probability from free-breathing to breath-hold liver SBRT: a dose-escalation strategy using radiation dose-volume effect | |
| Yoganathan et al. | Predicting respiratory motion using a novel patient specific dual deep recurrent neural networks | |
| CN109887573A (en) | Human body chest and abdomen apparent motion prediction technique towards radiotherapy | |
| Waghorn et al. | A comparison of the dosimetric effects of intrafraction motion on step‐and‐shoot, compensator, and helical tomotherapy‐based IMRT | |
| Shan et al. | A comparative study on the generalization ability of back propagation neural network and support vector machine for tracking tumor motion in radiotherapy | |
| Zhang et al. | Comparison of two different kernel functions of support vector regression for tracking tumor motion: radial basis function and linear function | |
| Ichiji et al. | Intelligent sensing of biomedical signals-lung tumor motion prediction for accurate radiotherapy | |
| Okusako et al. | Prediction of lung tumor motion with combinational use of High-order repetitive control and Long-Short term memory | |
| Khalifa et al. | Machine learning automated treatment planning for online magnetic resonance guided adaptive radiotherapy of prostate cancer | |
| Wu et al. | Knowledge discovery from tumor respiratory motion data | |
| Kumaragamage | Validation of calypso surface beacons for deep inspiration breath hold radiotherapy | |
| 城野悠志 | Prediction-based compensation for gate on/off latency during respiratory-gated radiotherapy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |