System for automatically designing radiotherapy plan based on machine learning

A radiation therapy and automatic design technology, applied in machine learning, mechanical/radiation/invasive therapy, medical automated diagnosis, etc., can solve tedious and time-consuming problems, reduce workload and improve work efficiency

Active Publication Date: 2019-09-06
ANHUI UNIVERSITY
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The entire treatment plan design process is cumbersome and time-consuming, and different radiotherapy physicists make different radiotherapy plans due to different experiences. Therefore, in order to ensure the quality of treatment plans, it is necessary to provide an automatic radiotherapy plan design system, so that radiotherapy Physicists are freed from tedious and repetitive work, improving work efficiency

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
  • System for automatically designing radiotherapy plan based on machine learning
  • System for automatically designing radiotherapy plan based on machine learning
  • System for automatically designing radiotherapy plan based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0015] Figure 1 to Figure 4 Some embodiments according to the invention are shown.

[0016] Such as figure 1 As shown, the system includes an input unit 100 , a field parameter prediction unit 200 , an optimization target and constraint condition prediction unit 300 , and an inverse plan optimization unit 400 .

[0017] The input unit 100 is adapted to acquire the original image of the patient and the segmented ROI information. The ROI includes the tumor target area, organs at risk and other ROIs delineated by the doctor.

[0018] The portal parameter prediction unit 200 is used to construct a learning model based on the neural network, and automatically predict the optimal portal parameter...

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 discloses a system for automatically designing a radiotherapy plan based on machine learning. The system comprises an input unit, a radiation field parameter predicting unit, an optimization target and constrained condition predicting unit, and an inverse plan optimization unit, wherein the input unit is used for acquiring an original image of the patient and segmented interested area information. The radiation parameter predicting unit is used for constructing a learning model based on a neural network and automatically predicting the radiation field parameter. The optimizationtarget and constrained condition predicting unit is used for constructing a dosage distribution predicting model based on a neural network, and automatically converts the predicted expected dosage distribution to a target function and the constrained condition required for inverse optimization. The inverse plan optimization unit is used for performing optimization according to the target function,the constriction setting and the radiation field parameter by means of an optimization method for obtaining the sub-field which corresponds with each radiation field direction and the weight thereof,thereby finishing planned designing. The system has advantages of realizing automatic plan designing, greatly reducing workload of a plan designer and improving working efficiency.

Description

technical field [0001] The invention relates to a system for automatically designing radiotherapy plans based on machine learning. The system can assist radiotherapy physicists to import medical image information drawn by patients to automatically complete the design of radiotherapy plans. Background technique [0002] The purpose of radiation therapy is to deliver a lethal dose to the target area, namely the tumor tissue, while protecting the organs at risk. In order to achieve this goal, it is necessary to formulate an optimal radiotherapy regimen, that is, a treatment plan. In order to meet the goals of treatment, radiotherapy physicists use commercial radiotherapy planning systems to complete the design of radiotherapy plans. [0003] The radiotherapy plan formulation process is as follows: First, the radiotherapy physicist selects field parameters such as field direction and field weight based on experience, and inputs the doctor's expected dose requirements into the r...

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): G16H20/40G16H50/20G06N20/00G06N3/04
CPCG16H20/40G06N20/00G16H50/20G06N3/048
Inventor 曹瑞芬仲红
Owner ANHUI UNIVERSITY
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