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

CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method

A nasopharyngeal carcinoma radiotherapy and CT image technology, applied in image analysis, image enhancement, image data processing, etc.

Active Publication Date: 2020-10-20
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies of the existing head and neck nasopharyngeal carcinoma radiotherapy target segmentation algorithm. Aiming at the problems existing in the medical image segmentation method based on deep learning, a method based on 2.5-dimensional convolutional neural network and attention Mechanism-Combined Multiscale Integration Model

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
  • CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method
  • CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method
  • CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In conjunction with the content of the present invention, the following embodiments are provided in the segmentation of the head and neck CT image target area. In this embodiment, the CPU is Intel(R) Core(TM) i7-6850K 3.60GHz GPU and the Nvidia GTX1080Ti memory is 24.0GB. Realized in the computer, the programming language is Python.

[0046] 1. Establish as Figure 5 The 2.5-dimensional convolutional neural network shown,

[0047] Since CT images usually have higher intra-slice resolution and lower inter-slice resolution, in order to keep the convolutional neural network with similar physical receptive fields in different directions, this method combines 3×3×3 convolution with 1×3×3 convolutions are combined to design a 2.5-dimensional convolutional neural network. The entire network consists of an encoder-decoder structure, and the encoder consists of K convolutional modules, in which two adjacent convolutional modules achieve successive reductions in resolution thro...

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 CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method, belongs to the technical field of medical image segmentation, and particularlyrelates to a convolutional neural network automatic segmentation method for a nasopharyngeal carcinoma target region in three-dimensional medical image segmentation. Aiming at the problems of a medical image segmentation method based on deep learning, the invention provides a multi-scale integration model based on combination of a 2.5-dimensional convolutional neural network and an attention mechanism. When a target area is segmented, the method has higher feature learning capability for large-spacing images, more attention is paid to a target segmentation area in the segmentation process so as to obtain a better segmentation effect, the segmentation precision is improved by integrating models under multiple scales, and segmentation result uncertainty evaluation is provided according to amodel integration result so as to better assist doctors in making decisions.

Description

technical field [0001] The invention belongs to the technical field of medical image segmentation, in particular to a convolutional neural network automatic segmentation method for a nasopharyngeal carcinoma target area in three-dimensional medical image segmentation. Background technique [0002] Nasopharyngeal carcinoma refers to malignant tumors that occur on the wall of the nasopharynx, and its incidence rate is the highest among malignant tumors of the ear, nose and throat. Nasopharyngeal carcinoma often occurs in southern China, Southeast Asia, the Middle East and North Africa. The earlier the discovery and treatment of nasopharyngeal carcinoma, the higher the success rate of treatment. Radiation therapy is the most commonly used treatment for nasopharyngeal carcinoma. During radiotherapy, it is necessary to outline the target area in medical images to avoid radiotherapy damage to healthy areas of the human body. At present, the delineation task is usually done manua...

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): G06T7/11G06K9/62G06N3/04G06N3/08G16H20/40
CPCG06T7/11G06N3/08G16H20/40G06T2207/30096G06T2207/10081G06N3/045G06F18/253
Inventor 王国泰梅昊陈雷文辉张少霆
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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