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

Automatic delineation method for organs at risk in pelvic radiotherapy

An organ and pelvic technology, applied in the field of automatic delineation of organs at risk in pelvic radiotherapy, can solve the problems of low efficiency of manual delineation, poor repeatability, and dependence on experience level, etc., to improve prediction accuracy and generalization ability, improve consistency, and improve The effect of precision

Active Publication Date: 2020-12-11
XIANGYA HOSPITAL CENT SOUTH UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, the outline of radiotherapy is generally drawn manually, which has low efficiency and poor repeatability, and relies heavily on the experience level of the drawing doctor.

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
  • Automatic delineation method for organs at risk in pelvic radiotherapy
  • Automatic delineation method for organs at risk in pelvic radiotherapy
  • Automatic delineation method for organs at risk in pelvic radiotherapy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This example provides a method for automatic delineation of organs at risk in pelvic radiotherapy, including the following steps:

[0038] S1: Obtain the CT image data of the external irradiation plan and the CT image data of the intracavitary irradiation plan of the cervical cancer patients in the training data set, and perform preprocessing on the CT image data of the external irradiation plan and the CT image data of the intracavitary irradiation plan;

[0039] S2: Extract the outline of each organ at risk outlined on the CT image of the external irradiation plan of cervical cancer patients in the training data set, and assign the area inside the outline as 1 and the area outside the outline as 0, and obtain the binary value of the organ at risk in external irradiation mask image;

[0040] S3: Extract the contour of each organ at risk outlined on the CT image of the endocavitary irradiation plan of cervical cancer patients in the training data set, and assign the are...

Embodiment 2

[0063] Based on Example 1, this embodiment compares the present invention: a method for automatically delineating organs at risk in pelvic radiotherapy with other conventional methods, including the following steps:

[0064] S1: The external radiation plan CT image data of cervical cancer patients and the binary mask image of organs at risk in the training data set obtained and processed in steps S1-S4 in Example 1 are performed on the convolutional neural network with the same structure as the present invention. training, the training process is as follows image 3 As shown, the delineation model A of organs at risk for external exposure is obtained;

[0065] S2: The intracavity irradiation plan CT image data of cervical cancer patients and the binary mask image of organs at risk obtained and processed in the training data set obtained and processed in steps S1-S4 in Example 1 are paired with the convolutional neural network with the same structure as the present invention F...

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 provides an automatic delineation method for organs at risk in pelvic radiotherapy. The automatic delineation method for the organs at risk in the pelvic radiotherapy synchronously carries out semi-supervised learning of the same convolutional neural network model through CT images of external irradiation and intracavitary irradiation for cervical cancer, synchronously; and thus, delineation accuracy under the same data size is raised with working efficiency and delineation consistency of medical workers improved, thereby improving accuracy of radiotherapy for cervical cancer.

Description

technical field [0001] The invention belongs to the technical field of radiotherapy, and in particular relates to a method for automatically delineating organs at risk for pelvic radiotherapy. Background technique [0002] In the clinical radiation plan for patients with cervical cancer, a combination of intensity-modulated radiation (external irradiation) and afterloading radiation (intracavitary irradiation) is generally used, and there are certain differences in the organs at risk that need to be delineated by external irradiation and internal irradiation. difference. For example, in external irradiation, it is generally necessary to outline the femoral head, rectum, bladder, sigmoid colon, small intestine, perineum and other organs at risk; while in intracavitary irradiation, it is generally necessary to outline the rectum, bladder, sigmoid colon and other organs at risk. In intracavity irradiation, the external applicator is included in the image, the anatomical struct...

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
IPC IPC(8): A61N5/10
CPCA61N5/103A61N5/1039A61N5/1048A61N5/1002
Inventor 张子健周蓉蓉王姝婷陈海斌程婷婷
Owner XIANGYA HOSPITAL CENT SOUTH UNIV
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