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

Target region automatic drawing method and device based on deep learning, and storage medium

A deep learning and target area technology, applied in the field of medical imaging and computer, can solve problems such as affecting the work efficiency of doctors, affecting the treatment of patients, time-consuming and laborious, etc., to achieve the effect of rapid target detection, improvement of work efficiency, and shortening of time.

Inactive Publication Date: 2018-08-24
BEIJING LINKING MEDICAL TECH CO LTD
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In the process of radiotherapy for patients in the hospital, the delineation of the target area is often involved. At present, doctors mainly use manual delineation. Manual delineation is time-consuming and laborious, which affects the doctor's work efficiency, and is prone to human error, affecting the patient's health. treat

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
  • Target region automatic drawing method and device based on deep learning, and storage medium
  • Target region automatic drawing method and device based on deep learning, and storage medium
  • Target region automatic drawing method and device based on deep learning, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049]A method for automatically delineating a target area in a radiotherapy plan based on deep learning, suitable for execution in a computing device, comprising the following steps (such as Image 6 shown):

[0050] (1) Preprocessing 210 the patient image data; preferably, the patient image is a CT image, a nuclear magnetic image or a PET image, etc.;

[0051] The preprocessing is to perform interpolation processing on the patient image. Preferably, after the interpolation processing, the resolution of the image to be predicted is the same as that of the training picture. In a preferred embodiment of the present invention, the resolution of the image to be drawn is APPI (such as 512*512PPI), and its resolution becomes B PPI (such as 500*500 PPI) after interpolation processing. The pixels of the sketched image are consistent with the pixel size of the x and y axes of the pictures used in the training set of the CNN neural network, thereby improving the prediction accuracy. ...

Embodiment 2

[0082] The invention also provides a computing device, comprising:

[0083] one or more processors;

[0084] storage; and

[0085] one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including for deep learning based radiation therapy Instructions for the method of automatically delineating the target area in the plan, the method comprising the steps of:

[0086](1) Preprocessing the patient image data;

[0087] (2) Input the preprocessed image data into the trained convolutional neural network model to predict the target area;

[0088] (3) Perform edge extraction on the predicted target area to obtain the automatically delineated target area.

Embodiment 3

[0090] A computer-readable storage medium that stores one or more programs, the one or more programs include instructions, and the instructions are suitable for being loaded by the memory and executing a method for automatically delineating target volumes in radiotherapy plans based on deep learning, The method includes the steps of:

[0091] (1) Preprocessing the patient image data;

[0092] (2) Input the preprocessed image data into the trained convolutional neural network model to predict the target area;

[0093] (3) Perform edge extraction on the predicted target area to obtain the automatically delineated target area.

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 present invention belongs to the technical field of medical images and computer, and relates to a target region automatic drawing method in radiotherapy treatment planning based on deep learning.The method comprises the following steps of: (1) performing preprocessing of patient's image data; (2) inputting the image data through preprocessing to a trained convolutional neural network model for prediction of the target region; and (3) performing edge extraction of the predicted target region to obtain an automatically drawing target region. The method provided by the invention can achieverapid target drawing and has high precision, for the same organ, doctors manually draw the organ for 5-10 min, the target region automatic drawing algorithm only needs 15 seconds, and therefore, compared to manual drawing, the time is reduced about 95%, the working efficiency of doctors can be greatly improved, and valuable time is provided for patients for timely treatment.

Description

technical field [0001] The invention belongs to the field of medical imaging and computer technology, and relates to a method for automatically delineating a target area in a radiotherapy plan based on deep learning. Background technique [0002] In the process of radiotherapy for patients in the hospital, the delineation of the target area is often involved. At present, doctors mainly use manual delineation. Manual delineation is time-consuming and laborious, which affects the doctor's work efficiency, and is prone to human error, affecting the patient's health. treat. [0003] Deep learning uses neural networks to try to abstract data at a high level. It focuses on learning the representation of data. In addition, high-level abstraction of data is very similar to artificial intelligence, that is, knowledge can be expressed and intelligent responses can be made. Deep learning has been widely applied to the field of image and pattern recognition. [0004] Convolutional Neu...

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): G16H30/40G06N3/04G06N3/08G06T7/00G06T7/13G06T7/62
CPCG06N3/084G06T7/0012G06T7/13G06T7/62G16H30/40G06T2207/30016G06T2207/20084G06T2207/20081G06T2207/10104G06T2207/10081G06T2207/10088G06N3/048G06N3/045
Inventor 刘春雷崔德琪
Owner BEIJING LINKING MEDICAL TECH CO LTD
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