Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-organ sketching method and device

A multi-organ and organ technology, applied in the field of medical devices, can solve the problem of low radiotherapy treatment efficiency, and achieve the effect of improving radiotherapy treatment efficiency, high accuracy, and fast organ delineation.

Pending Publication Date: 2020-12-22
海创时代(深圳)医疗科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to ensure the curative effect of radiotherapy and avoid radiation damage to normal tissues and organs, doctors need to accurately delineate the organs at risk in CT images. However, it takes 3-4 hours to manually delineate a set of CT, resulting in extremely low radiotherapy treatment 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
  • Multi-organ sketching method and device
  • Multi-organ sketching method and device
  • Multi-organ sketching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a schematic flowchart of a multi-organ delineation method provided in Embodiment 1 of the present invention, as shown in figure 1 As shown, the method may include the following steps:

[0053] Step 1: Construct a multi-category training set containing historical data of multiple patients, wherein the historical data of each patient includes historical 3D CT image data of the patient and corresponding multi-organ delineation data.

[0054] Step 2: using a multi-classification training set containing historical data of multiple patients to train a convolutional neural network for synchronously delineating multiple organs to obtain a trained convolutional neural network for synchronously delineating multiple organs;

[0055] Step 3: Using the trained convolutional neural network for synchronously delineating multiple organs, perform multi-organ synchronous delineation processing on the 3D CT image data to be delineated, and obtain a 3D CT image containing d...

Embodiment 2

[0064] figure 2 It is a schematic structural diagram of a multi-organ delineation device provided in Embodiment 2 of the present invention, as shown in figure 2 As shown, the device may include a multi-organ synchronous delineation training set building module, a multi-organ synchronous delineation model training module and a multi-organ synchronous delineation module, wherein:

[0065] 1. Multi-organ synchronous delineation training set building block

[0066] The multi-organ synchronous delineation training set construction module is used to construct a multi-classification training set containing historical data of multiple patients, wherein the historical data of each patient includes the patient's historical 3D CT image data and corresponding multi-organ delineation data .

[0067] Specifically, the multi-organ synchronous delineation training set construction module can determine multiple organs that need to be delineated simultaneously according to actual needs; obt...

Embodiment 3

[0078]In actual work, doctors need to outline multiple organs, and most of the existing technologies are single-organ models, that is, running a model can only predict the corresponding single organ area, so if you need to outline multiple organs, you need to run multiple organs For the corresponding single-organ model, running the single-organ model corresponding to multiple organs at the same time will consume a lot of video memory, and running the single-organ model in batches will take longer.

[0079] Convolutional neural network (CNN) in deep learning is a common method for interpreting images, and has a large number of example applications in the fields of image classification, semantic segmentation, object detection, and image understanding. U-shaped CNN (or UNeT) extracts abstract features through multi-layer downsampling of CT images, and then upsamples back to the original size to realize the delineation of organ regions. The convolutional neural network for synchro...

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 multi-organ sketching method and device, which relate to the field of medical instruments. The method comprises the steps of constructing a multi-classification training setcomprising the historical data of a plurality of patients, and enabling the historical data of each patient to comprise the historical three-dimensional CT image data of the patient and the corresponding multi-organ sketching data, training a convolutional neural network used for synchronously sketching multiple organs by using the multi-classification training set containing historical data of multiple patients to obtain a trained convolutional neural network used for synchronously sketching multiple organs, and performing multi-organ synchronous sketching processing on the three-dimensionalCT image data to be sketched by using the trained convolutional neural network for synchronously sketching the multiple organs to obtain a three-dimensional CT image containing the sketched multiple organs. Based on the constructed multi-classification training set containing historical three-dimensional CT image data of multiple patients and corresponding multi-organ sketching data, the convolutional neural network used for synchronously sketching multiple organs is trained, then the trained convolutional neural network used for synchronously sketching the multiple organs is used for carryingout multi-organ synchronous sketching processing, not only is the accuracy of the organ sketching result higher, but also the organ sketching speed is higher, and the radiotherapy treatment efficiency can be greatly improved.

Description

technical field [0001] The invention relates to the field of medical devices, in particular to a method and device for delineating multiple organs. Background technique [0002] Radiation therapy is a powerful means of treating cancer. CT images are often used by doctors to make careful radiotherapy plans due to their fast imaging and high resolution. In order to ensure the curative effect of radiotherapy and avoid radiation damage to normal tissues and organs, doctors need to accurately delineate the organs at risk in CT images. However, it takes 3-4 hours to manually delineate a set of CT, resulting in extremely low efficiency of radiotherapy. Contents of the invention [0003] The main purpose of the embodiments of the present invention is a multi-organ delineation method and device, aiming to quickly and accurately delineate multiple organs in CT images. [0004] In order to achieve the above purpose, an embodiment of the present invention provides a multi-organ delin...

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): G16H30/40G06T11/20G06N3/04
CPCG16H30/40G06T11/203G06N3/045
Inventor 朱程谢梦妮葛迦
Owner 海创时代(深圳)医疗科技有限公司