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

Intelligent image detection system and method for pulmonary nodule difficult sample

A technology for image detection and pulmonary nodules, applied in neural learning methods, image analysis, image data processing, etc., can solve problems such as insufficient rigor, difficulty in applying diagnostic model training and actual clinical analysis, poor interpretability, etc. Segmentation performance, improved encoder convolutional layers, improved detection rate

Pending Publication Date: 2022-04-12
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] For medical images, the construction of medical images by means of artificial generation has poor interpretability and lack of rigor in imaging, making it difficult to apply to diagnostic model training and actual clinical analysis

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
  • Intelligent image detection system and method for pulmonary nodule difficult sample
  • Intelligent image detection system and method for pulmonary nodule difficult sample
  • Intelligent image detection system and method for pulmonary nodule difficult sample

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] According to an intelligent image detection system for difficult samples of pulmonary nodules provided by the present invention, such as figure 1 As shown, including: using the improved 3D codec feature extraction network to perform lung nodule instance segmentation on 3D lung CT images;

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 provides an intelligent image detection system and method for a pulmonary nodule difficult sample. The method comprises the following steps: performing pulmonary nodule instance segmentation on a 3D lung CT image by using an improved 3D coding and decoding feature extraction network; the improved 3D coding and decoding feature extraction network is based on the 3D coding and decoding feature extraction network, and the false negative detection rate is improved or the false positive rate of detection is reduced through one or more of an extrusion excitation module, a 3D deformable average pooling module, a global attention up-sampling module and a positive anchor frame shape screening module.

Description

technical field [0001] The invention relates to the field of intelligent medical image diagnosis, in particular to an intelligent image detection method and system for difficult samples of pulmonary nodules. Background technique [0002] In the existing lung CT images, different doctors have certain differences in judging whether the lung lesions and tissues are nodules, and the shape of the nodule outline, making it difficult to detect these nodules through the generalization of general deep learning networks. High detection performance; in the medical field, medical images are constructed by artificial generation methods, which have poor interpretability and insufficient rigor in imaging, and are difficult to apply to diagnostic model training and actual clinical analysis. [0003] At present, artificial intelligence technology represented by deep learning is used in intelligent medical image detection, among which the automatic detection of pulmonary nodules is one of the...

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): G06T7/00G06T7/11G06V10/40G06V10/80G06V10/74G06V10/82G06N3/04G06N3/08
Inventor 阎威武王奕纬韩睿
Owner SHANGHAI JIAO TONG 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