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

Craniocerebral nuclear magnetic resonance image quality control method and system

A technology of nuclear magnetic resonance images and quality control methods, applied in image analysis, image data processing, instruments, etc., can solve problems such as image quality degradation, incomplete image identification, missed diagnosis, etc., achieve fast and accurate learning, save manpower, improve The effect of predicting the effect

Pending Publication Date: 2022-04-15
SHAN DONG MSUN HEALTH TECH GRP CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are a series of problems in the shooting of cranial MRI images, which directly affect the image quality and the development of imaging technology.
The current cranial MRI images of the radiology department have the following problems: (1) The image identification is incomplete
In clinical practice, the patient information, hospital information and other image identifications of craniocerebral MRI images of many patients are incomplete and do not meet the national image quality standards
(2) Incomplete scanning parameters
At work, in order to complete the workload within the corresponding time, the technician will reduce the scanning sequence of brain MRI images and adjust the scanning parameters of the corresponding sequence, which will lead to a decrease in image quality and even miss some subtle lesions, leading to missed diagnosis
(3) There are artifacts such as breathing, movement, and metal in the image

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
  • Craniocerebral nuclear magnetic resonance image quality control method and system
  • Craniocerebral nuclear magnetic resonance image quality control method and system
  • Craniocerebral nuclear magnetic resonance image quality control method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] Embodiment 1 of the present invention proposes a method for controlling the quality of craniocerebral MRI images, which does not require manual quality control of the image quality, and the whole process is automatically quality controlled, saving manpower.

[0042] like figure 1 It is a flowchart of a cranial MRI image quality control method according to Embodiment 1 of the present invention;

[0043] In step S101 , a cranial MRI image is acquired, a data set of the cranial MRI image is constructed, and images containing artifacts and images without artifacts in the data set are respectively marked.

[0044] The cranial brain image is taken by the MRI plain scan equipment, and the server interface is set up on each NMR plain scan equipment, connected to the server, and the received patient's cranial MRI image is compared with the set rule base; the received image The identification (year, month, day, hour, minute, second, examination number, hospital name, left and ri...

Embodiment 2

[0063] Based on the method for controlling the quality of craniocerebral MRI images proposed in Embodiment 1 of the present invention, Embodiment 2 of the present invention also proposes a quality control system for cranial MRI images, such as Figure 4 It is a schematic diagram of a brain MRI image quality control system according to Embodiment 2 of the present invention, and the system includes a construction module, a labeling module and a prediction module;

[0064] The construction module is used to obtain cranial magnetic resonance images, construct a data set of the cranial magnetic resonance images, and mark images containing artifacts and images without artifacts in the data set respectively;

[0065] The labeling module is used to divide the labeled data set into a training set and a test set according to a preset ratio; the labeled data set is first preprocessed before training;

[0066] The prediction module is used to adopt the ResNet network to train the training...

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 a craniocerebral nuclear magnetic resonance image quality control method and system, and the method comprises the following steps: obtaining a craniocerebral nuclear magnetic resonance image, constructing a data set of the craniocerebral nuclear magnetic resonance image, and respectively marking images containing artifacts and images without artifacts in the data set; dividing the labeled data set into a training set and a test set according to a preset proportion; the method comprises the following steps: firstly, preprocessing a marked data set before training; training the training set data by adopting a ResNet network, and verifying through a test set to obtain a predicted quality control image; and comparing the predicted quality control image with the marked data set, and outputting a result of quality control of the craniocerebral nuclear magnetic resonance image. Based on the method, the invention further provides a brain nuclear magnetic resonance image quality control system. According to the invention, the artificial intelligence technology is utilized to carry out quality control on the image so as to improve the image quality and meet the requirements of clinical diagnosis, scientific research and teaching.

Description

technical field [0001] The invention belongs to the technical field of image quality control, and in particular relates to a method and system for controlling the quality of cranial nuclear magnetic resonance images. Background technique [0002] In recent years, with the rapid development of medical imaging technology, the Department of Radiology has shown new vigor in the medical field and has played an increasingly important role in the diagnosis and treatment process. Clinicians need to use imaging technology to make a clear diagnosis and assist diagnosis in judging many diseases. With the advancement of medical technology, people have put forward higher requirements for medical level, and the quality of imaging will directly affect the accuracy of medical diagnosis results, which in turn will affect the rationality of treatment plans. Cranial magnetic resonance images are used as an auxiliary diagnostic tool for common diseases, and the control of their image quality i...

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): G06T7/00
Inventor 窦穹穹吴军张杨鞠海涛樊昭磊陈冲王长壮
Owner SHAN DONG MSUN HEALTH TECH GRP CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com