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

Severe tumor image recognition system and method

A tumor imaging and recognition system technology, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of automatic tumor classification, grading and localization systems, and normal image discarding, and achieve automatic processing. The effect of high level, reduced workload and improved diagnosis speed

Active Publication Date: 2020-12-15
WEST CHINA HOSPITAL SICHUAN UNIV
View PDF14 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although many studies have applied deep learning methods to the diagnosis of brain tumors, there is no complete automatic tumor classification, grading and localization system based on big data.
Furthermore, the accuracy of integrating tumor classification, grading, and localization in a single diagnostic system remains an open challenge
In a single system, having a brain tumor detection stage before tumor localization causes normal images to be discarded during the localization stage

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
  • Severe tumor image recognition system and method
  • Severe tumor image recognition system and method
  • Severe tumor image recognition system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be further elaborated below in conjunction with embodiment.

[0027]Step 1: Dataset collection and labeling. The present invention shares two data sets: classification data set and positioning data set. The present invention collects 957 magnetic resonance brain imaging images of different categories and levels from historical diagnostic case data, and divides them into 1) meningeal tumors (184 pictures) and 2) brain gliomas according to the manual diagnosis results of doctors Grade 1 (112 photos), 3) Glial Tumor Grade 2 (130 photos), 4) Glial Tumor Grade 3 (157 photos), 5) Glial Tumor Grade 4 (149 photos), 6) Anencephaly Tumors (225 photos), a total of 6 categories, were placed in the corresponding 6 folders, as the classification data set used in the first stage.

[0028] The image annotation tool Labelimg is used to annotate the tumor area in the images with tumors. The area where the tumor is located in each image is marked with a rectan...

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 relates to a severe tumor image recognition system and method, in particular to a magnetic resonance image two-stage multi-model automatic brain tumor diagnosis system based on brain tumor image big data. The technical problem to be solved by the invention is to provide a set of magnetic resonance image two-stage multi-model automatic brain tumor diagnosis system based on a convolutional neural network, which is used for high-accuracy computer-assisted brain image data analysis by performing information mining, feature extraction and experience learning from historical diagnosisbig data. Diagnosis accuracy is independent of experience of doctors, and meanwhile diagnosis speed is increased.

Description

technical field [0001] This application relates to a severe tumor image recognition system and method, especially a two-stage multi-model automatic brain tumor diagnosis system based on big data for brain tumor imaging magnetic resonance images. Background technique [0002] A brain tumor is a serious disease that disrupts normal brain function due to abnormal growth of tissue inside the brain. In the past 30 years, the number of deaths due to brain tumors in my country has been gradually increasing every year. Rapid and accurate brain tumor diagnosis techniques are necessary. In the past, manual diagnosis by physicians based on experience and visual observation, the accuracy varies with the experience of doctors, and it is very time-consuming. [0003] Magnetic resonance imaging is an advanced medical imaging technique that can provide a wealth of data and information about the anatomy of human soft tissues. The purpose of automated brain tumor detection using magnetic r...

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): G06K9/62G06K9/32G06N3/04G06N3/08G16H10/60G16H50/20G16H50/70
CPCG16H50/20G16H50/70G16H10/60G06N3/08G06V10/25G06N3/045G06F18/2415G06F18/214
Inventor 刘秀吉克夫格吴孝文
Owner WEST CHINA HOSPITAL SICHUAN UNIV
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