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

CT image pulmonary nodule detection system based on 3D full-connection convolution neural network

A convolutional neural network, CT image technology, applied in biological neural network model, image enhancement, image analysis and other directions, can solve the problems of difficult training, too small lung nodule target, unbalanced samples, etc., to eliminate false detection. Effect

Active Publication Date: 2017-07-11
杭州健培科技有限公司
View PDF3 Cites 106 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is no public 3D convolutional classification network for CT images. Moreover, the target of pulmonary nodules is too small, the samples are extremely unbalanced, and it is difficult to train. As a result, there is no 3D full convolutional network applied to CT image diagnosis.

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
  • CT image pulmonary nodule detection system based on 3D full-connection convolution neural network
  • CT image pulmonary nodule detection system based on 3D full-connection convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The inventive concept of the present invention is: adopt full convolutional segmentation network to perform pixel-level detection and positioning, and use convolutional classification network to suppress false positive targets. The present invention will be further described below in conjunction with the accompanying drawings and implementation examples. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the invention can be carried out in many other ways than those described herein and thus the invention is not limited to the specific implementations disclosed below. figure 1 It is a flow chart of the CT image pulmonary nodule detection system based on the 3D fully connected convolutional neural network of the present invention.

[0023] Including: step S01 training data set construction. Including: data preprocessing, training area selection, data enhancement, etc. 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 discloses a CT image pulmonary nodule detection system based on 3D full-connection convolution neural network. The detection system comprises the following five steps: constructing a training set data; performing 3D convolution neural network classification network training; performing 3D convolution neural network segmentation network training; carrying out false-positive suppression in which the trained segmentation network and the false-positive are utilized to inhibit the network; and detecting the pulmonary nodule. The technical schemes of the invention can realize the full automatic detection without any human intervention. At the same time, the recall rate of pulmonary nodule detection can be increased effectively; the false-positive focus of infection is reduced considerably; and a pixel level positioning quantitative and qualitative result for the focus-of-infection area of the pulmonary nodule can be obtained.

Description

technical field [0001] The invention relates to the technical field of computer-aided diagnosis of medical imaging, in particular to a CT image pulmonary nodule detection system based on a 3D fully connected convolutional neural network. Background technique [0002] Lung cancer is the cancer with the highest prevalence rate and the largest number of deaths in the world. Early screening and treatment of lung cancer can greatly improve the 5-year survival rate of patients after surgery. In the early stage of lung cancer, most of them are nodular lesions, so the detection of pulmonary nodules is very important for the early screening of lung cancer. However, CT images have high resolution, low cost, and no harm to patients, and have become the main means of lung screening. Existing CT image pulmonary nodule detection methods can be divided into traditional methods, deep learning methods, and methods combining traditional and deep learning. Traditional methods mainly use cla...

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): G06N3/08G06T7/136G06T7/187
CPCG06N3/08G06T2207/10081G06T2207/20081G06T2207/30064
Inventor 程国华陈波季红丽
Owner 杭州健培科技有限公司
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