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

Pulmonary tuberculosis recognition system based on pre-training model

A recognition system, a technology for pulmonary tuberculosis, applied in the field of deep learning, can solve problems such as inability to use image enhancement, occupying space, and increasing training costs, avoiding gradient disappearance or explosion problems, and achieving feature reuse and good classification.

Pending Publication Date: 2021-08-13
YANGZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The first method is extremely low in training costs, because it simply extracts a feature and does not involve training; the disadvantage is that saving the extracted features takes up a certain amount of space, and image enhancement cannot be used (and image enhancement is important to prevent overfitting of small data sets. fit is very important)
The second way can use image enhancement, but the training cost will also increase significantly

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
  • Pulmonary tuberculosis recognition system based on pre-training model
  • Pulmonary tuberculosis recognition system based on pre-training model
  • Pulmonary tuberculosis recognition system based on pre-training model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] like figure 1 A kind of pulmonary tuberculosis identification system based on pre-training model shown, is characterized in that, comprises:

[0032] The image acquisition module is used to acquire CT images of human chest;

[0033] The image preprocessing module is used to preprocess the collected CT pictures; including:

[0034] The picture size adaptation module is used to adjust the picture size;

[0035] The image color...

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 pulmonary tuberculosis recognition system based on a pre-training model, and the system comprises an image collection module which is used for collecting a CT image of the chest of a human body; an image preprocessing module which is used for preprocessing the acquired CT images; a feature extraction module which is used for performing feature extraction and dimension reduction on the preprocessed picture; and a classification module which is used for classifying the pictures subjected to dimension reduction to obtain an identification result, richer and more abstract feature expressions can be obtained, and the prediction precision is improved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a pulmonary tuberculosis identification system. Background technique [0002] Tuberculosis is a chronic infectious disease caused by Mycobacterium tuberculosis, which can invade many organs, with pulmonary tuberculosis infection being the most common. If not detected in the early stages, it can be life-threatening. If timely diagnosis and reasonable treatment are given, most of them can be clinically cured. Pulmonary tuberculosis is divided into primary pulmonary tuberculosis, hematogenously disseminated pulmonary tuberculosis, and secondary pulmonary tuberculosis, and secondary pulmonary tuberculosis is further divided into infiltrative pulmonary tuberculosis and chronic fibrous cavitary tuberculosis. The pulmonary CT manifestations of primary pulmonary tuberculosis are mainly hilar and mediastinal lymph node enlargement, and the pulmonary CT manifestations of hematogeno...

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): G06T7/00G06T5/40G06K9/46G06K9/62G06N3/04G06N3/08G06N20/20
CPCG06T7/0012G06T5/40G06N3/08G06N20/20G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30061G06V10/44G06N3/047G06N3/045G06F18/2415G06F18/241G06F18/214
Inventor 曹永忠芮扬郝亚蒙薛杰
Owner YANGZHOU 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