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

Detection method of pulmonary nodules based on three-dimensional convolution neural network

A neural network and three-dimensional convolution technology, applied in the field of medical image processing, can solve the problems of affecting the detection recall rate and not utilizing the essence of CT data, so as to improve the recall rate and average accuracy rate and reduce the time overhead

Active Publication Date: 2018-12-28
NORTHWESTERN POLYTECHNICAL UNIV
View PDF8 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the problem that the traditional pulmonary nodule detection method based on 2D manual features does not take advantage of the fact that CT data is essentially a 3D structure, which affects the detection recall rate

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
  • Detection method of pulmonary nodules based on three-dimensional convolution neural network
  • Detection method of pulmonary nodules based on three-dimensional convolution neural network
  • Detection method of pulmonary nodules based on three-dimensional convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] Step 1: The origin and spacing in the image coordinate system are known during coordinate conversion, and the converted coordinates are calculated according to the following formula.

[0057]

[0058] Among them, center represents the position point to be converted, and center' represents the position point after conversion. Then, the threshold method and connected region labeling are used to obtain the labeled map of the lung parenchyma. Use morphological convex hull and expansion operations to repair the outer and inner contours of the lung parenchyma, obtain the mask of the lungs, and obtain the lung parenchyma area; then resample the data, and integrate the three surfaces in the patient coordinate system (cross-section , coronal plane, sagittal plane) were adjusted to 1 mm × 1 mm × 1 mm, and the value range of voxels was normalized to the range of 0-255 to obtain the preprocessing results of lung segmentation.

[0059] Step 2: Use the defined network structure t...

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 relates to a lung nodule detection method based on a three-dimensional convolution neural network, which adopts a network structure of a feature pyramid and an attention mechanism,. Themethod integrates features of low-level and high-resolution and high-level abstract features, and enables the network to concentrate attention on a target area. The method has the effects of using three-dimensional convolution neural network detection method, end-to-end detection of pulmonary nodules, and reducing the time overhead. Compared with the traditional methods, the method can improve therecall rate and average accuracy of nodule detection.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and relates to a method for detecting pulmonary nodules in lung slice data, in particular to a method for detecting pulmonary nodules based on a three-dimensional convolutional neural network. Background technique [0002] Cancer has been a serious threat to human life and health, and the death caused by lung cancer ranks first among all cancer morbidity and death. However, the survival rate of lung cancer is closely related to the timing of discovery. In the middle and advanced stage of lung cancer, the treatment cost is high and the effect is not good. Most of the early lung cancers are asymptomatic and often present in the form of pulmonary nodules. According to reports, if pulmonary nodules are detected and treated as early as possible, the survival rate of lung cancer will be greatly improved. Therefore, early detection and diagnosis of pulmonary nodules is the key to impr...

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): G06T7/00G06T7/13G06T7/155
CPCG06T7/0012G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30064G06T7/13G06T7/155
Inventor 李映曹莹刘凌毅汪亦文王鹏
Owner NORTHWESTERN POLYTECHNICAL 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