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

Pulmonary nodule diagnosis method based on local receptive field and semi-supervised depth self coding

A diagnostic method and receptive field technology, applied to radiological diagnostic instruments, diagnostics, computer components, etc., can solve problems such as missed diagnosis and misdiagnosis, and achieve the effect of improving accuracy, increasing accuracy rate, and increasing precision

Active Publication Date: 2017-10-20
TAIYUAN UNIV OF TECH
View PDF3 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, doctors mainly diagnose diseases based on experience, and the diagnosis results are subjective to a certain extent, and misdiagnosis and missed diagnosis often occur.

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 nodule diagnosis method based on local receptive field and semi-supervised depth self coding
  • Pulmonary nodule diagnosis method based on local receptive field and semi-supervised depth self coding
  • Pulmonary nodule diagnosis method based on local receptive field and semi-supervised depth self coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The technical solution of the present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0060] The overall detection process diagram of lung nodules is as follows figure 1 As shown, the present invention uses local receptive fields to extract hierarchically different types of features hidden in lung parenchymal CT images, and then uses an improved stacked sparse auto-encoding network that incorporates medically relevant lung disease information. The label's semi-supervised feature extraction depth model is trained to find higher-level features from the CT feature images that have been feature-classified, replace the top-level output layer with a logistic regression classifier, and use the training optimized features as the output vector. Finally, a variety of clinical information is integrated to achieve accurate detection of lung nodules.

[0061] A. Multi-feature learning based on local receptive fields

[0062...

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 nodule diagnosis method based on a local receptive field and semi-supervised depth self coding. Firstly, the local receptive field is adopted to carry out multilevel feature extraction on a pulmonary nodule image; then, semi-supervised sparse self coding is used to autonomously learn nodule features in a pulmonary image; and finally, multiple pieces of clinical information are fused to realize accurate detection on the pulmonary nodule. The recognition accuracy is high, the inputted CT image can be subjected to feature multiple classification and then self coding learning, the network diagnosis is more accurate, and an important role in auxiliary diagnosis is played for a doctor.

Description

Technical field [0001] The invention relates to the auxiliary diagnosis of lung nodules in medical images, in particular to a method for diagnosis of lung nodules with local receptive fields and semi-supervised deep self-encoding. Background technique [0002] As the best imaging method for detecting lung diseases, CT imaging plays an important role in the diagnosis of doctors. However, doctors mainly diagnose diseases based on their experience, and the diagnosis results are subjective, and misdiagnosis and missed diagnosis often occur. As a feature learning method, deep learning establishes a similar simple and non-linear deep hierarchical model structure by simulating the human brain nervous system with rich hierarchical structure, while filtering out the interference of irrelevant factors from the features of layer-by-layer learning, The input data is extracted layer by layer, and the original data is transformed into a higher-level abstract expression. [0003] The lowest-lev...

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): G06K9/62A61B6/03A61B6/00
CPCA61B6/03A61B6/5217G06V2201/031G06F18/253G06F18/24G06F18/214
Inventor 强彦赵鑫赵涓涓强薇王华赵文婷高慧明
Owner TAIYUAN UNIV OF TECH
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