Method for predicting human body thoracico-abdominal surface area respiratory movement in radiotherapy

A technology of surface area and breathing movement, applied in radiation therapy, X-ray/γ-ray/particle irradiation therapy, treatment, etc., can solve the problems of normal tissue damage, poor patient tolerance, low treatment efficiency, etc., to improve curative effect, Increased applicability and easy parameter optimization

Inactive Publication Date: 2018-06-15
HARBIN UNIV OF SCI & TECH
2 Cites 7 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0003] At present, the conventional methods for dealing with respiratory movement in radiotherapy include: exercise inclusion method, compressed shallow breathing method, breath-holding method and respiratory gating method, etc.,...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Abstract

The method provides a method for predicting the human body thoracico-abdominal surface area respiratory movement in radiotherapy, belonging to the field of tumor treatment and respiratory motion prediction. The prediction method with the respiratory motion prediction function adopts a dual-camera to collect respiration motion signal data, the collected data are preprocessed, and the obtained datais used as the input of a Gaussian process regression prediction algorithm. Then, a Gaussian process model is provided for predicting the regression problem. A proper regression model is constructedby utilizing the data, training and prediction are carried out, a kernel function is selected in the training process, and moreover, the hyper-parameter can be obtained and the feasibility of the algorithm is verified through an off-line simulation experiment. Finally, a quasi-periodic kernel function is selected, and hyper-parameters are solved by utilizing a conjugation gradient method, and themodel prediction on the respiratory movement data through a Gaussian process regression method. According to the method for predicting the human body thoracico-abdominal surface area respiratory movement in radiotherapy, the influence of the respiratory movement on the radiotherapy precision can be reduced.

Application Domain

Technology Topic

Respiratory motionAbdominal surface +10

Image

  • Method for predicting human body thoracico-abdominal surface area respiratory movement in radiotherapy
  • Method for predicting human body thoracico-abdominal surface area respiratory movement in radiotherapy
  • Method for predicting human body thoracico-abdominal surface area respiratory movement in radiotherapy

Examples

  • Experimental program(1)

Example Embodiment

Specific embodiment one
[0025] The method for predicting the respiratory motion of the human body's chest and abdomen surface area in radiotherapy of this embodiment includes the following steps:
[0026] Step a. Use a light pattern projector to project a color pattern composed of three different frequency RGB cosine curves onto the surface of the human body's chest and abdomen, and place a 3CCD color camera on each side of the light pattern projector to collect scene images and send them to the computer Perform post-processing, using dual cameras to obtain the three-dimensional coordinates of the characteristic landmark points and the regional boundary line according to the principle of binocular vision;
[0027] Step b. For the two video sequences acquired by the left and right cameras, after extracting the same region and its boundary lines and feature landmark points from the corresponding image pairs, match the region boundary lines and feature landmark points respectively, and then use the left and right cameras according to binocular vision The principle is to obtain the three-dimensional coordinates of the points on the boundary line and the characteristic mark points, use the combination of the camera and the projector to obtain the three-dimensional coordinates of the surface points in the area according to the fringe analysis and phase expansion method, and then calculate the three-dimensional coordinates of the characteristic points and the area according to the mathematical definition The horizontal projection of the boundary line perimeter and geometric center, the average value of the coordinates and perimeter of each point of the boundary line of the area, the average value of the coordinates of each point of the area, and the surface area total 7 regional characteristic quantities;
[0028] Step c. Determine the region of interest and its boundary and feature landmark points according to the location of the specific predicted feature quantity; take the predicted feature quantity training observation value as a reference, and perform correlation analysis and significance with all other regional feature quantity training observation values Analyze and optimize the set of regional feature quantities participating in modeling and prediction as Y;
[0029] Step d, select the quasi-periodic kernel function as follows
[0030]
[0031] Among them, r=||x-x'|| 2 Represents the Euclidean distance between two data points, θS, θL, θ p It is a hyperparameter; the necessary and sufficient condition to form the kernel function is that the matrix formed between the points in the test set must be a positive semi-definite matrix;
[0032] Step e, to ensure K c In order to be an effective positive definite covariance function, the Cholisky decomposition is used and the elements of the lower triangular matrix are parameterized to obtain K c =L(θ c )L(θ c ) T , Where L(θ c ) Is a lower triangular matrix with size m×m; L(θ c ) The non-zero elements of θ c To specify that the relevant hyperparameter θ c The number is
[0033] Step f: Minimize the hyperparameters for negative logarithmic edge probability, that is, -log(y|θ), and then use the conjugate gradient method to find its optimal value;
[0034] Step g: Give the mobile hyperparameter θ by maximizing the cross-correlation between the predicted area feature quantity and other area feature quantities S Initial value, give the hyperparameter θ according to the training data of other regional feature quantities p Assign initial values, repeat the experiment many times, and initialize other hyperparameters randomly;
[0035] Step h. In the measurement and prediction stage, first measure the unexpected features of the predicted region according to the sampling frequency, and then predict the predicted time x*=t+Δt and give the predicted estimated value and its error confidence interval, where Δt is the prediction time.
[0036] End up like figure 1 The Gaussian process regression prediction results are shown, where the dark line is the original data curve, the light line is the prediction result curve, and the gray area represents its confidence interval.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Similar technology patents

Air suspension flexibility space buttjunction platform

InactiveCN101081506AAvoid harmAchieving flexible contactWork benchesTorsional ForcesSelf adaptive
Owner:CHONGQING UNIV

Classification and recommendation of technical efficacy words

  • Avoid harm
  • Improve curative effect
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products