CN109589505A - A kind of multifunctional monitoring method for radiation therapy process - Google Patents
A kind of multifunctional monitoring method for radiation therapy process Download PDFInfo
- Publication number
- CN109589505A CN109589505A CN201811419277.2A CN201811419277A CN109589505A CN 109589505 A CN109589505 A CN 109589505A CN 201811419277 A CN201811419277 A CN 201811419277A CN 109589505 A CN109589505 A CN 109589505A
- Authority
- CN
- China
- Prior art keywords
- signal
- radiation therapy
- frame
- image
- radiation
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
- A61N5/00—Radiation therapy
- A61N5/10—X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
- A61N5/1048—Monitoring, verifying, controlling systems and methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Physiology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Cardiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Pulmonology (AREA)
- Radiation-Therapy Devices (AREA)
Abstract
The present invention provides a kind of multifunctional monitoring method for radiation therapy process, can be realized the multi-index monitoring of radiation therapy process.The described method includes: the therapeutic process to radiation therapy patient is recorded;Each frame image of the video of recording is divided into several regions, wherein the region includes: one or more of face, chest, radiotherapy position, background area;The obtained each region of division is handled, determines the monitoring index of radiation therapy patient, wherein the monitoring index includes: that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out one or more of beam signal.The present invention is suitable for being monitored radiation therapy process.
Description
Technical field
The present invention relates to field of radiation therapy, particularly relate to a kind of multifunctional monitoring method for radiation therapy process.
Background technique
Radiotherapy abbreviation radiotherapy refers to using radiation energy to the clinical effect after biological tissue's effect come treating cancer,
It is one of the main means of oncotherapy.Radiotherapy specifically uses X-ray, gamma-rays, electron ray or proton weight
Ion etc. irradiates tumor tissues, and using the biological action of radioactive ray, the maximum amount of killing simultaneously destroys tumor tissues, makes its contracting
It is small.Its principle is the chromosome that cell can be destroyed according to the energy of a large amount of radioactive ray institute band, and cell is made to stop growing.Therefore
It can be used for fighting the tumour cell of fast-growth division, realize the inhibition to tumour cell.
But normal cell can be also killed while radiotherapy kills tumour cell, therefore guarantee radiotherapy mistake
Journey is accurately executed most important by radiotherapy treatment planning.This requires carry out various status monitorings to radiation therapy process.It is existing
Monitoring device it is expensive and have a single function, can not realize the status monitoring to radiation therapy process well.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of multifunctional monitoring methods for radiation therapy process, with solution
Certainly monitoring device present in the prior art is expensive and the problem of having a single function.
In order to solve the above technical problems, the embodiment of the present invention provides a kind of multifunctional monitoring side for radiation therapy process
Method, comprising:
The therapeutic process of radiation therapy patient is recorded;
Each frame image of the video of recording is divided into several regions, wherein the region include: face, chest,
One or more of radiotherapy position, background area;
The each region obtained to division is handled, and determines the monitoring index of radiation therapy patient, wherein the monitoring
Index includes: that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out one or more of beam signal.
Further, each frame image of the video by recording is divided into several regions and includes:
Face, the chest of radiation therapy patient are oriented in each frame image of the video of recording by cascade classifier
Portion, radiotherapy position and background area.
Further, it is determined that the heart rate signal of radiation therapy patient includes:
Extract the triple channel color signal of each frame image face area;
New twocomponent signal is obtained to the triple channel color signal decorrelation of extraction;
Fourier transform is carried out after carrying out bandpass filtering to obtained new twocomponent signal, frequency when by amplitude highest is made
The heart rate signal of radiation therapy patient is determined according to the relationship between target palmic rate and heart rate for target palmic rate.
Further, the triple channel color signal for extracting each frame image face area includes:
Primary colours separation is carried out to the face area of each frame image, obtain the red of each frame image face area, green,
Blue triple channel signal.
Further, it is determined that the breath signal of radiation therapy patient includes:
Extract the signal of each frame image chest area;
The signal of the chest area of extraction is filtered;
Filtered signal is amplified, binary conversion treatment, obtains respirometric foreground point;
The breath signal of radiation therapy patient is obtained according to the variation of foreground point respirometric in time-domain.
Further, described that the breathing of radiation therapy patient is obtained according to the variation of foreground point respirometric in time-domain
Signal includes:
The sum of the gray value for counting the respirometric foreground point that each frame extracts obtains point diagram according to the peak value of statistics point
With fitting cyclic curve figure, wherein the fluctuation of fitting cyclic curve figure is for describing the respiratory variations of radiation therapy patient.
Further, it is determined that the involuntary movement signal of radiation therapy patient includes:
Extract the region at each frame image radiotherapy position;
The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracts echo signal;
Signal after extraction is amplified, binary conversion treatment, obtains the foreground point of involuntary movement;
Involuntary movement signal is obtained according to the variation of the foreground point of involuntary movement in time-domain.
Further, the region by radiotherapy position carries out Laplacian Pyramid Transform, extracts target letter
Number include:
The image-region at radiotherapy position is subjected to low pass subband decomposition, and using to by the way of up-sampling, by its with
A upper tomographic image compares, and calculates difference between the two, the laplacian pyramid decomposed;
The signal extraction in the channel Y of the bottom in Laplacian-pyramid image is come out, as echo signal.
Further, it is determined that the radiotherapy machine of radiation therapy patient goes out beam signal includes:
The background area of each frame image is separated;
Obtain the difference image of each frame image frame adjacent thereto;
It whether counts in each frame difference image containing radiation speck;
According to the core spoke under the ratio-dependent video recording equipment local environment of frame number and video totalframes that radiation speck occur
Penetrate dosage rate, wherein the nuclear radiation dosage rate goes out beam signal for characterizing radiotherapy machine.
Further, the difference image of each frame image frame adjacent thereto of acquisition includes: that each frame image is adjacent thereto
The forward difference image and backward difference image of frame;
Whether containing radiation speck in each frame difference image of statistics includes:
The forward difference image of each frame image is synthesized into a frame image with backward difference image;
Judge whether the maximum gradation value of newly synthesized image is greater than preset gray threshold, if more than then present frame contains
There is radiation speck, otherwise, present frame is without containing radiation speck.
The advantageous effects of the above technical solutions of the present invention are as follows:
In above scheme, the therapeutic process of radiation therapy patient is recorded;By each frame image of the video of recording
Be divided into several regions, wherein the region include: face, chest, radiotherapy position, one in background area or
It is multiple;The each region obtained to division is handled, and determines the monitoring index of radiation therapy patient, wherein the monitoring refers to
Mark includes: that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out one or more of beam signal, thus real
The multi-index monitoring of existing radiation therapy process, and monitoring cost is low, has preferable application potential.
Detailed description of the invention
Fig. 1 is the flow diagram of the multifunctional monitoring method provided in an embodiment of the present invention for radiation therapy process;
Fig. 2 is the detailed process schematic diagram of the multifunctional monitoring method of radiation therapy process provided in an embodiment of the present invention;
Fig. 3 is R, G, B triple channel color component schematic diagram provided in an embodiment of the present invention;
Fig. 4 is the spectrum diagram provided in an embodiment of the present invention comprising heart rate signal;
Fig. 5 is respiratory movement matched curve schematic diagram provided in an embodiment of the present invention;
Fig. 6 is involuntary movement matched curve schematic diagram provided in an embodiment of the present invention;
Fig. 7 is the Three-Dimensional Gray value schematic diagram of speck feature in frame image provided in an embodiment of the present invention;
Fig. 8 (a) is that the V that non-radiative frame provided in an embodiment of the present invention generates illustrates intention;
Fig. 8 (b) is that the V that radiation frame provided in an embodiment of the present invention generates illustrates intention;
Fig. 9 is that the frame image of the video provided in an embodiment of the present invention in the radiationless situation of not shading dynamic scene generates
The η Distribution value histogram representative of grayscale image V;
Figure 10 is that the frame image of the video provided in an embodiment of the present invention under not shading dynamic scene difference radiation intensity is raw
At grayscale image V η Distribution value histogram;
Figure 11 is the structural schematic diagram of the multifunctional monitoring system provided in an embodiment of the present invention for radiation therapy process.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.
The present invention is expensive existing monitoring device and aiming at the problem that having a single function, and provides a kind of for radiotherapy
The multifunctional monitoring method of process.
Embodiment one
As shown in Figure 1, the multifunctional monitoring method provided in an embodiment of the present invention for radiation therapy process, comprising:
S101 records the therapeutic process of radiation therapy patient;
Each frame image of the video of recording is divided into several regions by S102, wherein the region include: face,
One or more of chest, radiotherapy position, background area;
S103, each region obtained to division are handled, and determine the monitoring index of radiation therapy patient, wherein institute
Stating monitoring index includes: one or more that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out in beam signal
It is a.
It is used for the multifunctional monitoring method of radiation therapy process described in the embodiment of the present invention, radiation therapy patient is controlled
Treatment process is recorded;Each frame image of the video of recording is divided into several regions, wherein the region includes: face
One or more of portion, chest, radiotherapy position, background area;The each region obtained to division is handled, and is determined
The monitoring index of radiation therapy patient, wherein the monitoring index includes: heart rate signal, breath signal, involuntary movement letter
Number, radiotherapy machine go out one or more of beam signal, to realize the multi-index monitoring of radiation therapy process, and monitoring cost
It is low, there is preferable application potential.
In the present embodiment, when patient carries out radiotherapy, it can be carried out by therapeutic process of the video recording equipment to patient
It records, and sub-frame processing is carried out to the video of recording;Wherein, the video recording equipment includes: road monitoring camera, network shooting
One of head or mobile phone camera are a variety of.
In the present embodiment, to video carry out sub-frame processing include: to the video of recording carry out sub-frame processing obtain it is a series of
Frame image, and store the relevant parameter of video;Wherein, the relevant parameter of the video includes: video duration length, video
Coded format, video totalframes, video record time point, video time for exposure, video frame rate and video record location
Longitude and latitude.
It is further, described in the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process
Each frame image of the video of recording, which is divided into several regions, includes:
Face, the chest of radiation therapy patient are oriented in each frame image of the video of recording by cascade classifier
Portion, radiotherapy position and background area.
It, can be by adaptive boosting (Adaboost) cascade classifier in each frame image of video in the present embodiment
Orient face, chest, radiotherapy position and the background area of patient.
In the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process, further, such as Fig. 2
It is shown, determine that the heart rate signal of radiation therapy patient includes:
Extract the triple channel color signal of each frame image face area;
New twocomponent signal is obtained to the triple channel color signal decorrelation of extraction;
Fourier transform is carried out after carrying out bandpass filtering to obtained new twocomponent signal, frequency when by amplitude highest is made
The heart rate signal of radiation therapy patient is determined according to the relationship between target palmic rate and heart rate for target palmic rate.
It is further, described in the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process
The triple channel color signal for extracting each frame image face area includes:
Primary colours separation is carried out to the face area of each frame image, obtain the red of each frame image face area, green,
Blue triple channel signal.
In the present embodiment, in order to obtain the heart rate signal of radiation therapy patient, facial regions that can first to each frame image
Domain carries out primary colours separation, obtains R, G, B triple channel signal of each frame image face area, as shown in Figure 3, wherein R represents red
Chrominance signal component, G represent green color signal component, and B represents blue signal component;Then, using principal component analysis to obtained R,
G, the decorrelation of B triple channel signal obtains new twocomponent signal and designs bandpass filter, utilizes the bandpass filter of design
The frequency range in human normal heart rate range is intercepted, useless noise is filtered out;The periodical bounce of heart possesses fixed frequency range,
As can be seen from Figure 4, Fast Fourier Transform (FFT) is carried out to the signal after bandpass filtering, it is transformed into frequency domain from time domain, in frequency domain figure
The corresponding frequency of peak value (amplitude highest) is exactly target palmic rate;By the corresponding frequency of peak value in frequency domain (target palmic rate)
It is denoted as f, heart rate is denoted as H, then the calculation formula of heart rate are as follows:
H=f*60.
In the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process, further, such as Fig. 2
It is shown, determine that the breath signal of radiation therapy patient includes:
Extract the signal of each frame image chest area;
The signal of the chest area of extraction is filtered;
Filtered signal is amplified, binary conversion treatment, obtains respirometric foreground point;
The breath signal of radiation therapy patient is obtained according to the variation of foreground point respirometric in time-domain.
It is further, described in the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process
Include: according to the breath signal that the variation of foreground point respirometric in time-domain obtains radiation therapy patient
The sum of the gray value for counting the respirometric foreground point that each frame extracts obtains point diagram according to the peak value of statistics point
With fitting cyclic curve figure, wherein the fluctuation of fitting cyclic curve figure is for describing the respiratory variations of radiation therapy patient.
In the present embodiment, in order to determine the breath signal of radiation therapy patient, each frame image chest area is first extracted
Signal;Spatial decomposition is carried out to each frame chest area signal of extraction and obtains the signal of different space frequency, because with breathing
It moves relevant frequency and only concentrates on fixed frequency range, the signal that decomposition obtains is carried out so designing corresponding bandpass filter
Filtering only intercepts wherein frequency range relevant to respiratory movement, and filtered signal is fainter, further amplifies to it,
Because being exaggerated the noise of image institute band itself, also while extracting signal required for amplification to avoid image self-noise
Interference, so also needing to do binary conversion treatment to amplified signal, obtains respirometric foreground point;Then, count each
The sum of the gray value of foreground point that frame extracts obtains point diagram and fitting cyclic curve figure with the peak value of statistics point, passes through fitting
The respiratory variations of radiation therapy patient are depicted in the fluctuation of cyclic curve figure, as shown in Figure 5.
In the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process, further, such as Fig. 2
It is shown, determine that the involuntary movement signal of radiation therapy patient includes:
Extract the region at each frame image radiotherapy position;
The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracts echo signal;
Signal after extraction is amplified, binary conversion treatment, obtains the foreground point of involuntary movement;
Involuntary movement signal is obtained according to the variation of the foreground point of involuntary movement in time-domain.
In the present embodiment, in order to determine the involuntary movement signal of radiation therapy patient, each frame image radiation is first extracted
The region of therapentic part;The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracts echo signal;It will mention
Echo signal after taking amplifies, and for the interference for avoiding image self-noise, does binary conversion treatment to amplified signal, obtains
To the foreground point of involuntary movement;Then, the sum of the gray value of foreground point of involuntary movement that each frame extracts is counted, is used
Statistics point peak value obtain point diagram and fitting cyclic curve figure, by the fluctuation of curve graph be depicted radiation therapy patient not certainly
The variation of main motion, as shown in Figure 6.
It is further, described in the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process
The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracting echo signal includes:
The image-region at radiotherapy position is subjected to low pass subband decomposition, and using to by the way of up-sampling, by its with
A upper tomographic image compares, and calculates difference between the two, the laplacian pyramid decomposed;
The signal extraction in the channel Y of the bottom in Laplacian-pyramid image is come out, as echo signal.
In the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process, further, such as Fig. 2
It is shown, determine that the radiotherapy machine of radiation therapy patient goes out beam signal and includes:
The background area of each frame image is separated;
Obtain the difference image of each frame image frame adjacent thereto;
It whether counts in each frame difference image containing radiation speck;
According to the core spoke under the ratio-dependent video recording equipment local environment of frame number and video totalframes that radiation speck occur
Penetrate dosage rate, wherein the nuclear radiation dosage rate goes out beam signal for characterizing radiotherapy machine.
In the specific embodiment of multifunctional monitoring method for being previously used for radiation therapy process, further, obtain
The difference image of each frame image frame adjacent thereto include: the forward difference image of each frame image frame adjacent thereto and backward
Difference image;
Whether containing radiation speck in each frame difference image of statistics includes:
The forward difference image of each frame image is synthesized into a frame image with backward difference image;
Judge whether the maximum gradation value of newly synthesized image is greater than preset gray threshold, if more than then present frame contains
There is radiation speck, otherwise, present frame is without containing radiation speck.
In the present embodiment, in order to determine that the radiotherapy machine of radiation therapy patient goes out beam signal, first by the back of each frame image
Scene area is separated, and then carries out smooth pretreatment to each frame image to eliminate system noise.Fig. 7 is bright in a frame image
The Three-Dimensional Gray value schematic diagram of spot feature, as shown in Figure 7, system noise and the gray value that generates on the image of radiation speck have compared with
Big difference, therefore can be used includes but is not limited to that the smooth preprocess method such as dimensional Gaussian convolution kernel filter method removes system noise
Sound.After denoising, the forward difference image and backward difference image of each frame image frame adjacent thereto are obtained, D1, D2 are denoted as.In order to
Better robustness is obtained, the forward difference image D1 of each frame and backward difference image D2 are synthesized into a frame image, and make
Judge whether the frame image of synthesis contains radiation speck with thresholding method, specific:
Forward difference image D1 and backward difference image D2 for each frame image, use formula V=min (D1, D2)
Each of image pixel is calculated, a new image V is synthesized, by Fig. 8 (a), (b) it is found that non-radiative frame is raw
At V figure maximum gray scale and the maximum gray scale of V figure that generates of radiation frame have apparent difference, so can be used in V
Maximum gradation value (being denoted as η, wherein η=max (V)) as judge frame to be screened whether be radiate frame gray feature value.More
Specifically, a gray threshold T is first set, when the η value in the V figure that present frame generates is greater than T, then it is assumed that present frame is spoke
Frame is penetrated, containing radiation speck, otherwise, then it is assumed that present frame is non-radiative frame, without containing radiation speck.The setting of gray threshold T
According to complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor, CMOS) camera with
The difference of environment where camera and it is different.For example, Fig. 9 is certain CMOS camera 1000 frame figures in video under radiationless source scene
As the η distribution map of the V figure generated respectively.Gained distribution is counted, characteristics of image gray value η is greater than 10 after can must handling
It is 0.2 ‰ that probability, which has been less than, it can be considered that maximum probability speck containing radiation in video image of the η value greater than 10, i.e., by threshold
Value T is set as 10.Figure 10 is the η value point for the grayscale image V that the frame image of video under not shading dynamic scene difference radiation intensity generates
Cloth histogram.
Determining whether a certain frame is frame number and video totalframes by calculating containing radiation speck after radiation frame
Ratio, so that it may determine the nuclear radiation dosage rate under video recording equipment local environment.
In the present embodiment, formula can be passed through:Determine the nuclear radiation dosage rate under video recording equipment local environment;
Wherein, R indicates the nuclear radiation dosage rate of video recording equipment local environment, and N is the totalframes of the video in the unit time,
M be the unit time in include radiate speck totalframes.
Embodiment two
The present invention also provides a kind of specific embodiments of multifunctional monitoring system for radiation therapy process, due to this
The multifunctional monitoring that the multifunctional monitoring system provided for radiation therapy process is provided and is previously used for radiation therapy process
The specific embodiment of method is corresponding, which can be by executing above-mentioned side
Process step in method specific embodiment achieves the object of the present invention, therefore above-mentioned for the multi-functional of radiation therapy process
Explanation in monitoring method specific embodiment, is also applied for provided by the present invention for the multi-functional of radiation therapy process
The specific embodiment of monitoring system will not be described in great detail in present invention specific embodiment below.
The embodiment of the present invention also provides a kind of multifunctional monitoring system for radiation therapy process, which is characterized in that packet
It includes:
Picture recording module 11 is recorded for the therapeutic process to radiation therapy patient;
Division module 12, for each frame image of the video of recording to be divided into several regions, wherein the region
It include: one or more of face, chest, radiotherapy position, background area;
Determining module 13, each region for obtaining to division are handled, and determine that the monitoring of radiation therapy patient refers to
Mark, wherein the monitoring index includes: that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out in beam signal
One or more.
The multifunctional monitoring system of radiation therapy process is used for described in the embodiment of the present invention, by picture recording module to radiation
The therapeutic process for treating patient is recorded;Each frame image of the video of recording is divided into several regions by division module,
Wherein, the region includes: one or more of face, chest, radiotherapy position, background area;Determining module to draw
The each region got is handled, and determines the monitoring index of radiation therapy patient, wherein the monitoring index includes: the heart
Rate signal, breath signal, involuntary movement signal, radiotherapy machine go out one or more of beam signal, to realize that radiation is controlled
The multi-index monitoring for the treatment of process, and monitoring cost is low, has preferable application potential.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Division module, specifically for orienting radiation therapy patient in each frame image of the video of recording by cascade classifier
Face, chest, radiotherapy position and background area.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Determining module includes: the first determination unit;
First determination unit, for extracting the triple channel color signal of each frame image face area, to extraction
Triple channel color signal decorrelation obtains new twocomponent signal, carries out after carrying out bandpass filtering to obtained new twocomponent signal
Fourier transform, frequency when using amplitude highest is as target palmic rate, according to the pass between target palmic rate and heart rate
System, determines the heart rate signal of radiation therapy patient.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
The triple channel color signal for extracting each frame image face area includes:
Primary colours separation is carried out to the face area of each frame image, obtain the red of each frame image face area, green,
Blue triple channel signal.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Determining module includes: the second determination unit;
Second determination unit, for extracting the signal of each frame image chest area, to the chest area of extraction
Signal is filtered, and is amplified to filtered signal, binary conversion treatment, respirometric foreground point is obtained, according to the time
The variation of respirometric foreground point obtains the breath signal of radiation therapy patient on domain.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Include: according to the breath signal that the variation of foreground point respirometric in time-domain obtains radiation therapy patient
The sum of the gray value for counting the respirometric foreground point that each frame extracts obtains point diagram according to the peak value of statistics point
With fitting cyclic curve figure, wherein the fluctuation of fitting cyclic curve figure is for describing the respiratory variations of radiation therapy patient.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Determining module includes: third determination unit;
The third determination unit, for extracting the region at each frame image radiotherapy position, by radiotherapy position
Region carry out Laplacian Pyramid Transform, extract echo signal, the signal after extraction amplified, at binaryzation
Reason, obtains the foreground point of involuntary movement, obtains involuntary movement according to the variation of the foreground point of involuntary movement in time-domain
Signal.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracting echo signal includes:
The image-region at radiotherapy position is subjected to low pass subband decomposition, and using to by the way of up-sampling, by its with
A upper tomographic image compares, and calculates difference between the two, the laplacian pyramid decomposed;
The signal extraction in the channel Y of the bottom in Laplacian-pyramid image is come out, as echo signal.
It is further, described in the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process
Determining module includes: the 4th determination unit;
4th determination unit, for the background area of each frame image to be separated, obtain each frame image with
Whether the difference image of its consecutive frame counts containing radiation speck in each frame difference image, according to the frame for radiation speck occur
Nuclear radiation dosage rate under several ratio-dependent video recording equipment local environments with video totalframes, wherein the nuclear radiation dosage
Rate goes out beam signal for characterizing radiotherapy machine.
In the specific embodiment for the multifunctional monitoring system for being previously used for radiation therapy process, further, obtain
The difference image of each frame image frame adjacent thereto include: the forward difference image of each frame image frame adjacent thereto and backward
Difference image;
Whether containing radiation speck in each frame difference image of statistics includes:
The forward difference image of each frame image is synthesized into a frame image with backward difference image;
Judge whether the maximum gradation value of newly synthesized image is greater than preset gray threshold, if more than then present frame contains
There is radiation speck, otherwise, present frame is without containing radiation speck.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, several improvements and modifications can also be made, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of multifunctional monitoring method for radiation therapy process characterized by comprising
The therapeutic process of radiation therapy patient is recorded;
Each frame image of the video of recording is divided into several regions, wherein the region includes: face, chest, radiation
One or more of therapentic part, background area;
The each region obtained to division is handled, and determines the monitoring index of radiation therapy patient, wherein the monitoring index
It include: that heart rate signal, breath signal, involuntary movement signal, radiotherapy machine go out one or more of beam signal.
2. the multifunctional monitoring method according to claim 1 for radiation therapy process, which is characterized in that described to record
Each frame image of the video of system is divided into several regions and includes:
The face of radiation therapy patient is oriented in each frame image of the video of recording by cascade classifier, chest, is put
Penetrate therapentic part and background area.
3. the multifunctional monitoring method according to claim 1 for radiation therapy process, which is characterized in that determine radiation
The heart rate signal for treating patient includes:
Extract the triple channel color signal of each frame image face area;
New twocomponent signal is obtained to the triple channel color signal decorrelation of extraction;
Fourier transform is carried out after carrying out bandpass filtering to obtained new twocomponent signal, frequency when using amplitude highest is as mesh
It marks palmic rate and the heart rate signal of radiation therapy patient is determined according to the relationship between target palmic rate and heart rate.
4. the multifunctional monitoring method according to claim 3 for radiation therapy process, which is characterized in that the extraction
The triple channel color signal of each frame image face area includes:
Primary colours separation is carried out to the face area of each frame image, obtains red, green, the blue of each frame image face area
Triple channel signal.
5. the multifunctional monitoring method according to claim 1 for radiation therapy process, which is characterized in that determine radiation
The breath signal for treating patient includes:
Extract the signal of each frame image chest area;
The signal of the chest area of extraction is filtered;
Filtered signal is amplified, binary conversion treatment, obtains respirometric foreground point;
The breath signal of radiation therapy patient is obtained according to the variation of foreground point respirometric in time-domain.
6. the multifunctional monitoring method according to claim 5 for radiation therapy process, which is characterized in that the basis
The variation of respirometric foreground point obtains the breath signal of radiation therapy patient and includes: in time-domain
The sum of the gray value for counting the respirometric foreground point of each frame extraction, obtains point diagram according to the peak value of statistics point and intends
Close cyclic curve figure, wherein the fluctuation of fitting cyclic curve figure is for describing the respiratory variations of radiation therapy patient.
7. the multifunctional monitoring method according to claim 1 for radiation therapy process, which is characterized in that determine radiation
The involuntary movement signal for treating patient includes:
Extract the region at each frame image radiotherapy position;
The region at radiotherapy position is subjected to Laplacian Pyramid Transform, extracts echo signal;
Signal after extraction is amplified, binary conversion treatment, obtains the foreground point of involuntary movement;
Involuntary movement signal is obtained according to the variation of the foreground point of involuntary movement in time-domain.
8. the multifunctional monitoring method according to claim 7 for radiation therapy process, which is characterized in that described to put
The region for penetrating therapentic part carries out Laplacian Pyramid Transform, and extracting echo signal includes:
The image-region at radiotherapy position is subjected to low pass subband decomposition, and using to by the way of up-sampling, by itself and upper one
Tomographic image compares, and calculates difference between the two, the laplacian pyramid decomposed;
The signal extraction in the channel Y of the bottom in Laplacian-pyramid image is come out, as echo signal.
9. the multifunctional monitoring method according to claim 1 for radiation therapy process, which is characterized in that determine radiation
The radiotherapy machine for treating patient goes out beam signal and includes:
The background area of each frame image is separated;
Obtain the difference image of each frame image frame adjacent thereto;
It whether counts in each frame difference image containing radiation speck;
According to the nuclear radiation agent under the ratio-dependent video recording equipment local environment of frame number and video totalframes that radiation speck occur
Dose rate, wherein the nuclear radiation dosage rate goes out beam signal for characterizing radiotherapy machine.
10. the multifunctional monitoring method according to claim 9 for radiation therapy process, which is characterized in that acquisition
The difference image of each frame image frame adjacent thereto includes: the forward difference image of each frame image frame adjacent thereto and backward poor
Partial image;
Whether containing radiation speck in each frame difference image of statistics includes:
The forward difference image of each frame image is synthesized into a frame image with backward difference image;
Judge whether the maximum gradation value of newly synthesized image is greater than preset gray threshold, if more than then present frame contains spoke
Speck is penetrated, otherwise, present frame is without containing radiation speck.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811419277.2A CN109589505B (en) | 2018-11-26 | 2018-11-26 | Multifunctional monitoring method for radiotherapy process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811419277.2A CN109589505B (en) | 2018-11-26 | 2018-11-26 | Multifunctional monitoring method for radiotherapy process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109589505A true CN109589505A (en) | 2019-04-09 |
CN109589505B CN109589505B (en) | 2020-12-29 |
Family
ID=65959740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811419277.2A Active CN109589505B (en) | 2018-11-26 | 2018-11-26 | Multifunctional monitoring method for radiotherapy process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109589505B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114302760A (en) * | 2020-04-20 | 2022-04-08 | 西安大医集团股份有限公司 | Radiotherapy system and emergency control method and device thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070237304A1 (en) * | 2006-03-31 | 2007-10-11 | Nelson Ian A | Portal imaging using modulated treatment beam |
CN102309318A (en) * | 2011-07-08 | 2012-01-11 | 首都医科大学 | Method for detecting human body physiological parameters on basis of infrared sequence image |
CN102499664A (en) * | 2011-10-24 | 2012-06-20 | 西双版纳大渡云海生物科技发展有限公司 | Video-image-based method and system for detecting non-contact vital sign |
CN102641562A (en) * | 2012-04-28 | 2012-08-22 | 徐州医学院 | Radiotherapy radiation field performance monitoring and adjusting device based on video |
CN104305996A (en) * | 2014-10-15 | 2015-01-28 | 大连现代医疗设备科技有限公司 | Image recognition technology-based respiration monitoring method and system |
CN105520724A (en) * | 2016-02-26 | 2016-04-27 | 严定远 | Method for measuring heart rate and respiratory frequency of human body |
CN107566797A (en) * | 2017-09-07 | 2018-01-09 | 青岛博晶微电子科技有限公司 | A kind of drowned monitor and detection device of swimming pool |
-
2018
- 2018-11-26 CN CN201811419277.2A patent/CN109589505B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070237304A1 (en) * | 2006-03-31 | 2007-10-11 | Nelson Ian A | Portal imaging using modulated treatment beam |
CN102309318A (en) * | 2011-07-08 | 2012-01-11 | 首都医科大学 | Method for detecting human body physiological parameters on basis of infrared sequence image |
CN102499664A (en) * | 2011-10-24 | 2012-06-20 | 西双版纳大渡云海生物科技发展有限公司 | Video-image-based method and system for detecting non-contact vital sign |
CN102641562A (en) * | 2012-04-28 | 2012-08-22 | 徐州医学院 | Radiotherapy radiation field performance monitoring and adjusting device based on video |
CN104305996A (en) * | 2014-10-15 | 2015-01-28 | 大连现代医疗设备科技有限公司 | Image recognition technology-based respiration monitoring method and system |
CN105520724A (en) * | 2016-02-26 | 2016-04-27 | 严定远 | Method for measuring heart rate and respiratory frequency of human body |
CN107566797A (en) * | 2017-09-07 | 2018-01-09 | 青岛博晶微电子科技有限公司 | A kind of drowned monitor and detection device of swimming pool |
Non-Patent Citations (1)
Title |
---|
魏清阳等: "基于静态场景下不遮光CMOS摄像头的核辐射探测", 《原子能科学技术》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114302760A (en) * | 2020-04-20 | 2022-04-08 | 西安大医集团股份有限公司 | Radiotherapy system and emergency control method and device thereof |
Also Published As
Publication number | Publication date |
---|---|
CN109589505B (en) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106156757B (en) | In conjunction with the face identification method and face identification system of In vivo detection technology | |
Sheng et al. | Denoised and texture enhanced MVCT to improve soft tissue conspicuity | |
US20090112287A1 (en) | Saliency-based apparatus and methods for visual prostheses | |
US20200185079A1 (en) | Radiotherapy system, data processing method and storage medium | |
CN104305964A (en) | Head mounted fatigue detector and method | |
Al‐Ameen et al. | A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single‐scale Retinex | |
Mylonas et al. | A deep learning framework for automatic detection of arbitrarily shaped fiducial markers in intrafraction fluoroscopic images | |
CN109589505A (en) | A kind of multifunctional monitoring method for radiation therapy process | |
CN101507861B (en) | Method for generating digitization breath gate-control signal based on abdomen body-surface skeleton line | |
Abdullah et al. | A comparative study of image segmentation technique applied for lung cancer detection | |
Qiu et al. | Deep learning-based thoracic CBCT correction with histogram matching | |
CN105184741A (en) | Three-dimensional CBCT (cone-beam computed tomography) image denoising method on the basis of improved nonlocal means | |
Salwe et al. | Brain tumor pixels detection using adaptive wavelet based histogram thresholding and fine windowing | |
Ghaempanah et al. | Electronic portal image enhancement based on nonuniformity correction in wavelet domain | |
Chavan et al. | Multimodality image fusion in frequency domain for radiation therapy | |
US20170270640A1 (en) | Method and system for reducing grid line artifacts in x-ray image | |
Saini et al. | A survey of noise removal methodologies for lung cancer diagnosis | |
Faris et al. | Detection of tumor region in MR image through fusion of Dam construction and K-mean clustering algorithms | |
CN112801167A (en) | Analysis method of medical image big data | |
CN108009992B (en) | Image adjusting method and device | |
Arjun et al. | Analysis of the liver in CT images using an improved region growing technique | |
Habib et al. | Modified Hybrid Edge Detection in MR image via Image Processing Techniques | |
González-López | A multiresolution processing method for contrast enhancement in portal imaging | |
Saleh et al. | MRI images classification based on software agent | |
Kaur et al. | Image Enhancement Using Particle Swarm Optimization and Honey Bee |
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 |