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

Neural fiber extraction method, system and device for region of interest and storage medium

A region of interest and nerve fiber technology, applied in the field of medical image processing, can solve the problems of low efficiency and complicated process of nerve fiber tracking, and achieve the effect of improving tracking efficiency

Pending Publication Date: 2020-05-01
SHANGHAI UNITED IMAGING HEALTHCARE
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art, the process of obtaining the region of interest of the DTI image by manual drawing is relatively cumbersome, which leads to low efficiency of nerve fiber tracking in the region of interest

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
  • Neural fiber extraction method, system and device for region of interest and storage medium
  • Neural fiber extraction method, system and device for region of interest and storage medium
  • Neural fiber extraction method, system and device for region of interest and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a flow chart of a method for extracting nerve fibers in a region of interest provided by Embodiment 1 of the present invention. This embodiment is applicable to automatically extracting a region of interest and performing nerve fiber tracking based on the automatically extracted region of interest. The method can be implemented by a system for extracting nerve fibers in a region of interest, wherein the device can be realized by software and / or hardware, and generally integrated in a device for extracting nerve fibers in a region of interest. Specifically include the following steps:

[0028] S110. Acquire the anatomical image and the diffusion tensor image of the currently detected part.

[0029] Wherein, the current detection site may be the head, the chest, or other sites. Optionally, the head is used as the current detection site for introduction in this embodiment.

[0030] Diffusion tensor image is a kind of magnetic resonance image obtained by co...

Embodiment 2

[0042] figure 2It is a schematic flowchart of a method for extracting nerve fibers in a region of interest provided in Embodiment 2 of the present invention. The technical solution of this embodiment is refined on the basis of the above embodiments. Optionally, the ROI mask based on the anatomical phase data, the diffusion data, and the pre-stored current detection part data, extracting at least one region of interest of the diffusion tensor image, comprising: registering the diffusion data and the anatomical phase data to obtain a registration matrix of the diffusion data and the anatomical phase data; Registering the anatomical phase data with the ROI mask data of the current detected part to obtain a first mapping relationship between the anatomical phase data and the ROI mask data; based on the registration Matrix and the first mapping relationship, determine the second mapping relationship between the mask data of the region of interest of the current detected part and ...

Embodiment 3

[0056] image 3 It is a schematic flowchart of a method for extracting nerve fibers in a region of interest provided in Embodiment 3 of the present invention. The technical solution of this embodiment extracts at least one region of interest of the diffusion tensor image based on deep learning. Optionally, extracting at least one region of interest of the diffusion tensor image includes: inputting the anatomical phase data into The trained second extraction model obtains at least one region of interest of the anatomical image; wherein, the second extraction model obtains the region of interest of the multiple historical anatomical images and the anatomy of the multiple historical anatomical images obtained by manually dividing The phase data is obtained by training the second original neural network model; the anatomical image is registered with the diffusion tensor image, and at least one region of interest of the diffusion tensor image is determined. For details, see imag...

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 nerve fiber extraction method, system and device for a region of interest and a storage medium. The method comprises the steps of obtaining an anatomical image and a diffusion tensor image of a current detection part; the mapping relation or the mapping matrix of any two types of data can be established based on the anatomical phase data, the diffusion data and the pre-stored region-of-interest masking data of the current detection part; obtaining a corresponding relationship between the diffusion data and the region-of-interest mask data; at least one region of interest of the diffusion tensor image can be automatically determined; tracking target nerve fibers passing through at least one region of interest of the diffusion tensor image by adopting a preset tracking algorithm; the problem that in the prior art, due to the fact that the process of obtaining the region of interest is tedious due to the manual drawing mode, the nerve fiber tracking efficiency ofthe region of interest is low is solved, and the effect of improving the nerve fiber tracking efficiency of the region of interest is achieved.

Description

technical field [0001] Embodiments of the present invention relate to medical image processing technology, and in particular to a method, system, device and storage medium for extracting nerve fibers in a region of interest. Background technique [0002] Diffusion tensor imaging (DTI for short) is an advanced MRI (Magnetic Resonance Imaging, MRI) technique that can non-invasively observe the macroscopic and microscopic anatomical structures of brain white matter fibers. Probe the microstructure of brain tissue, mainly using the perception of Brownian motion of water molecules for imaging. [0003] When the DTI imaging method is performed in the prior art, DTI processing software is usually used to track to obtain the nerve fibers of the brain. The doctor manually draws the region of interest on the DTI image according to the anatomical phase data, and then the nerve fibers of the manually drawn region of interest Perform tracking to obtain the tracking results of nerve fibe...

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): G06T7/00G06T7/33G06T7/246G06K9/32G06V10/25
CPCG06T7/0012G06T7/33G06T7/246G06T2207/10092G06T2207/30016G06V10/25G06T7/174G06T7/136G06T2207/20084G06T2207/20156G06T7/12G06T7/181G06T2207/10084A61B90/36A61B2090/364G06T7/11G06T2207/10072
Inventor 龚震寰
Owner SHANGHAI UNITED IMAGING HEALTHCARE
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