Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Radiotherapy dose calculation and verification method based on machine learning and Monte Carlo algorithm

A Monte Carlo algorithm and machine learning technology, applied in mechanical/radiation/invasive therapy, nuclear methods, computer-aided medical procedures, etc., can solve the problem that takes a long time, consumes a lot of time, and cannot detect clinical significance Implement errors and other issues to achieve the effects of improving efficiency, accelerating calculation speed, and facilitating the evaluation of overall accuracy

Pending Publication Date: 2021-02-09
林小惟
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because the accuracy of Monte Carlo simulation is proportional to the square of the number of simulated particle cases, when a certain accuracy needs to be achieved, the Monte Carlo program needs to simulate a large number of particles, which will consume a lot of time.
[0004] Traditional dose verification is performed manually by a physicist on a case-by-case basis before treatment. Most of them use a uniform phantom and various detectors for dose measurement. Physicists are required to place the phantom and then verify each case. One treatment is the same, it takes a long time
A large number of studies have shown that the planar dose verification based on the uniform phantom cannot detect clinically meaningful implementation errors, and at the same time, it will consume a lot of manpower and resources to conduct indiscriminate dose verification for each treatment plan

Method used

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

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Radiotherapy dose calculation and verification method based on machine learning and Monte Carlo algorithm
  • Radiotherapy dose calculation and verification method based on machine learning and Monte Carlo algorithm
  • Radiotherapy dose calculation and verification method based on machine learning and Monte Carlo algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033]A GPU-based parallel Monte Carlo dose calculation method, such asfigure 1 As shown, it is suitable for execution in a computing device and includes the following steps:

[0034](1) Data input: input the patient's CT image, target area organs and organs at risk outline image and DVH image, material density, material information, source parameters, geometric information of the phantom, etc.;

[0035](2) Particle input simulation: use the CUDA framework of NVIDIA Corporation, use the GPU of the graphics card for parallel calculation, and use the Monte Carlo particle transportation principle for particle transportation to obtain the simulated dose distribution;

[0036](3) Output step (2) The simulation result obtained by Monte Carlo based on parallel GPU.

[0037](4) Use parameters to establish a machine learning model. Verify the output of step (3)

Embodiment 2

[0039]A GPU-based parallel computing method, including the following steps:

[0040](41) Before the simulation starts. It is necessary to first apply for enough storage space for each computing unit, that is, each thread to record the data in the transportation process and the final deposition result. Monte Carlo simulation is inherently random and cannot predict which path a given particle will take, so it is impossible to recombine particles with the same fate into the same warpage. When warpage is divergent, it is divergent

[0041](42) Due to the need of parallel computing, all the original photons participating in the transportation are divided into several groups with the same number. Each group of photons is handed over to an arithmetic matrix composed of one or several arithmetic units (usually 32 or 16). The dose accumulation during the transportation of the same group of photons is added to a shared storage matrix representing the distribution of voxels Then the data is returned...

Embodiment 3

[0045]The present invention also provides a computing device, including:

[0046]One or more GPU processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more GPU processors, the one or Multiple programs include instructions for the Monte Carlo dose calculation method, which includes the steps:

[0047]A Monte Carlo dose calculation method, suitable for execution in a calculation device, includes the following steps:

[0048](1) Data input: input the patient's CT image, target area organs and organs at risk outline image and DVH image, material density, material information, source parameters, geometric information of the phantom, etc.;

[0049](2) Particle input simulation: use the CUDA framework of NVIDIA Corporation, use the GPU of the graphics card for parallel calculation, and use the Monte Carlo particle transportation principle for particle transportation to obtain the simulated dose distribution;

[00...

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 Login to View More

Abstract

The invention belongs to the technical field of radiotherapy radiation dose calculation, and relates to a radiotherapy dose verification method based on GPU parallel Monte Carlo dose calculation and machine learning. The method comprises the following steps: (1) data input: inputting an organ and endangered organ delineation CT image and a DVH image of a target area of a patient, material density,material information, source parameters, geometric information of a die body and the like; (2) particle input simulation: employing a CUDA framework of the NVIDIA company, employing a GPU of a display card for parallel calculation, employing a Monte Carlo particle transportation principle for particle transportation, and obtaining dose simulation distribution; (3) outputting a simulation result obtained in the step (2) through Monte Carlo of the parallel GPU; and (4) establishing a machine learning model by using the parameters, and verifying an output result in the step (3). Compared with the prior art, the method has the following beneficial effects that the Monte Carlo calculation speed is greatly improved through parallel GPU hardware, the Monte Carlo calculation result is verified through machine learning, the problems of long time consumption and high manpower and material resource cost in dose verification work of patient treatment in existing radiotherapy are solved, the doseverification efficiency can be improved, and the verification cost is reduced.

Description

Technical field[0001]The invention belongs to the technical field of radiation dose calculation, and relates to a machine learning and Monte Carlo dose calculation and verification method.Background technique[0002]In recent years, intensity-modulated radiotherapy technology has been increasingly used in clinical applications. In order to ensure the efficacy of patients and reduce tumor recurrence and damage to normal organs, it is necessary to calculate and verify the dose of the patient's treatment plan. Dose calculation is one of the core contents of the radiotherapy treatment planning system. The rapid and accurate provision of data on the exposure dose in the area of ​​interest is crucial to the formulation of the radiotherapy plan. How to reduce the dose calculation time under the premise of ensuring the accuracy of dose calculation It is the main bottleneck in making radiotherapy plans.[0003]There are two main ways to increase the speed of dose calculation. One is to use diffe...

Claims

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G16H20/40G16H50/50G06N20/10G06F30/27
CPCG16H20/40G16H50/50G06N20/10G06F30/27
Inventor 林小惟
Owner 林小惟
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com