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

A Pulmonary Nodule Sign Recognition Method Based on Hypergraph Hash Image Retrieval Based on Visual Features and Sign Labels

A visual feature and image retrieval technology, applied in the direction of character and pattern recognition, digital data information retrieval, special data processing applications, etc., can solve the problems of insufficient manual diagnosis power, reduce excessive dependence, facilitate the degree of benign and malignant, and ensure identification effect of effect

Active Publication Date: 2020-03-31
TAIYUAN UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, the power of manual diagnosis is seriously insufficient, and the powerful computing power of computers is urgently needed to help doctors make auxiliary diagnoses

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
  • A Pulmonary Nodule Sign Recognition Method Based on Hypergraph Hash Image Retrieval Based on Visual Features and Sign Labels
  • A Pulmonary Nodule Sign Recognition Method Based on Hypergraph Hash Image Retrieval Based on Visual Features and Sign Labels
  • A Pulmonary Nodule Sign Recognition Method Based on Hypergraph Hash Image Retrieval Based on Visual Features and Sign Labels

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention will be described in detail below in conjunction with specific embodiments.

[0052] refer to figure 1 , 2 , 3, the realization process of the inventive method is as follows:

[0053] A method for realizing pulmonary nodule sign recognition based on hypergraph hash image retrieval based on visual features and sign labels, comprising the following steps:

[0054] Step A, extract the region of interest of the pulmonary nodule, intercept the smallest circumscribed rectangular area centered on the ROI, extract the visual features expressing the sign information of the pulmonary nodule and retrieve similar pulmonary nodule images, and then identify the image represented by the query image Prepare for medical indications;

[0055] Step B, the construction of a multi-visual feature set, extracting a total of 199-dimensional reliable visual features from the three aspects of shape, grayscale, and texture;

[0056] Step C is used to realize similar pulm...

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 method for realizing pulmonary nodule sign recognition based on hypergraph hash image retrieval based on visual features and sign labels, and uses a two-layer structure to improve the retrieval accuracy of the pulmonary nodule image. In the first layer, the present invention respectively constructs a probability hypergraph from the visual information and label information of the pulmonary nodule image, and optimally divides the probability hypergraph to obtain a hash code. In the second layer, the hash function is trained using the visual features of the nodule image, the label features and the hash code obtained from the first layer. When retrieving, the image to be inspected is encoded with 0, 1 by the trained hash function, and the Hamming distance is compared with the image in the data set, and the similar nodule image is returned. The method of the present invention is based on the hypergraph hash image retrieval of visual features and sign labels, and then identifies the sign category represented by the image of the pulmonary nodule to be retrieved, which is convenient for doctors to judge the degree of benign and malignant pulmonary nodules, and reduces the doctor's excessive diagnostic experience. rely.

Description

technical field [0001] The invention relates to pulmonary nodule sign recognition, in particular to a method for realizing pulmonary nodule sign recognition based on hypergraph hash image retrieval based on visual features and sign labels. Background technique [0002] With the explosive growth of lung CT images, a large number of experienced, tireless and stable doctors are needed to complete the diagnosis. Otherwise, misdiagnosis and missed diagnosis will inevitably occur. However, at present, the power of manual diagnosis is seriously insufficient, and the powerful computing power of computers is urgently needed to help doctors make auxiliary diagnoses. Medical image retrieval not only reduces the workload of doctors and improves efficiency; on the other hand, it makes the diagnosis of medical images more objective and increases the accuracy of diagnosis. Contents of the invention [0003] Aiming at the deficiencies of the prior art, the present invention provides a m...

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 Patents(China)
IPC IPC(8): G06F16/583G06K9/32G06K9/46
CPCG06F16/5838G06V10/25G06V10/44G06V2201/03
Inventor 强彦宋云霞赵涓涓郝晓丽强薇
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