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

Pulmonary nodule detection method, electronic equipment and computer readable storage medium

A detection method, a technology of pulmonary nodules, applied in the field of computer vision, can solve the problem of low detection accuracy of pulmonary nodules

Pending Publication Date: 2022-07-12
HUNAN INSTITUTE OF ENGINEERING +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a pulmonary nodule detection method, electronic equipment and computer-readable storage medium, aiming to solve the technical problem of low pulmonary nodule detection accuracy in the prior art

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 detection method, electronic equipment and computer readable storage medium
  • Pulmonary nodule detection method, electronic equipment and computer readable storage medium
  • Pulmonary nodule detection method, electronic equipment and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] An embodiment of the present application provides a method for detecting pulmonary nodules, which is applied to the first federal participant. In the first embodiment of the method for detecting pulmonary nodules in the present application, refer to figure 1 , the pulmonary nodule detection method includes:

[0028] Step S10: Acquire a lung nodule image of the target to be detected, and perform lung nodule detection on the target to be detected according to the lung nodule image and a preset first lung nodule detection model to obtain a first lung nodule detection result;

[0029] Step S20, acquiring each historical pulmonary nodule image corresponding to the pulmonary nodule image, and generating pulmonary nodule time series data of the pulmonary nodule changing with time according to the pulmonary nodule image and each of the historical pulmonary nodule images;

[0030] Step S30, performing pulmonary nodule detection on the target to be detected according to the pulm...

Embodiment 2

[0040] Further, refer to figure 2 , based on the first embodiment of the present application, in another embodiment of the present application, for the same or similar content as the above-mentioned first embodiment, reference may be made to the above introduction, which will not be repeated in the following. On this basis, the preset first pulmonary nodule detection model includes a first feature extraction module and a first classification module, and the preset first pulmonary nodule detection model is based on the pulmonary nodule image and the preset first pulmonary nodule detection model. The described target to be detected is subjected to lung nodule detection, and the steps of obtaining the first lung nodule detection result include:

[0041] Step S11, according to the first feature extraction module, perform feature extraction on the lung nodule image to obtain lung nodule features, wherein the first feature extraction module is based on a true positive lung nodule s...

Embodiment 3

[0063] Further, refer to image 3 , based on the first embodiment of the present application, in another embodiment of the present application, for the same or similar content as the above-mentioned first embodiment, reference may be made to the above introduction, which will not be repeated in the following. On this basis, the preset second pulmonary nodule detection model includes a second feature extraction module and a second classification module,

[0064] The step of performing pulmonary nodule detection on the to-be-detected target according to the pulmonary nodule time series data and a preset second pulmonary nodule detection model, and obtaining a second pulmonary nodule detection result includes:

[0065] Step S31, according to the second feature extraction module, perform feature extraction on the pulmonary nodule time series data to obtain pulmonary nodule change characteristics, wherein the second feature extraction module is based on true positive pulmonary nodu...

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 detection method, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a pulmonary nodule image of a to-be-detected target, carrying out the pulmonary nodule detection of the to-be-detected target according to the pulmonary nodule image and a preset first pulmonary nodule detection model, and obtaining a first pulmonary nodule detection result; obtaining each historical pulmonary nodule image corresponding to the pulmonary nodule image, and according to the pulmonary nodule image and each historical pulmonary nodule image, generating time-varying pulmonary nodule time sequence data of the pulmonary nodule; according to the pulmonary nodule time sequence data and a preset second pulmonary nodule detection model, performing pulmonary nodule detection on the to-be-detected target to obtain a second pulmonary nodule detection result; and generating a target pulmonary nodule detection result according to the first pulmonary nodule detection result and the second pulmonary nodule detection result. The technical problem of low pulmonary nodule detection accuracy in the prior art is solved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular, to a method for detecting pulmonary nodules, an electronic device, and a computer-readable storage medium. Background technique [0002] With the continuous development of computer technology, the application of computer vision has become more and more extensive. At present, in the field of lung nodule detection, an image classification model can be constructed based on a large number of labeled samples, and the image classification model can be used to classify the lung images themselves. It is judged whether there are pulmonary nodules in the lung images, but the similarity between positive pulmonary nodule images and true positive pulmonary nodule images is usually high. A positive lung nodule image is determined as a true positive lung nodule image, thereby affecting the accuracy of lung nodule detection. SUMMARY OF THE INVENTION [0003] The main purpo...

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): G06T7/00G06V10/75G06V10/764G06V10/774G06K9/62
CPCG06T7/0014G06T2207/10081G06T2207/20076G06T2207/30064G06F18/2155G06F18/22G06F18/2415
Inventor 黄峰徐谦马海宏欧阳湘江
Owner HUNAN INSTITUTE OF ENGINEERING
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