Pulmonary nodule segmentation method based on combination of residual ECA channel attention UNet and TRW-S

A technology of attention and pulmonary nodules, which is applied in neural learning methods, image analysis, image enhancement, etc., can solve problems such as blurred edges and inconsistencies in the internal segmentation of lesion areas, and achieves fast convergence, reduced gradient explosion, and reduced The effect of loss of information

Pending Publication Date: 2022-06-28
CHINA THREE GORGES UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the technical problems of using UNet and its existing UNet improved network to segment pulmonary nodules, such as fuzzy edge delimitation and inconsistent internal segmentation of lesion regions.

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 segmentation method based on combination of residual ECA channel attention UNet and TRW-S
  • Pulmonary nodule segmentation method based on combination of residual ECA channel attention UNet and TRW-S
  • Pulmonary nodule segmentation method based on combination of residual ECA channel attention UNet and TRW-S

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] like Figure 1 to Figure 2 As shown, a lung nodule segmentation method, which includes the following steps:

[0032] 1. Read lung CT images in dcm format in LIDC-IDRI dataset

[0033] 2. Adjust the window level of the CT image to 1600 and the window width to 450

[0034] 3. Read the XML annotation file, cut out the part with lung nodules in the CT image through the annotation information, read the XML annotation file with a size of 64*64, and generate a mask image corresponding to the lung nodule through the edge segmentation information;

[0035] 4. Divide the image captured in step 3 into the dataset

[0036] 5. Build residual ECA channel attention UNet deep learning network

[0037] 6. Input the training set and validation set divided in step 5 into the network constructed in step 6 for training

[0038] 7. Input the test set into the network trained in step 7 to obtain the prediction map

[0039] 8. Input the output graph in step 7 into the Markov random field-...

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

A pulmonary nodule segmentation method based on combination of residual ECA channel attention UNet and TRW-S. The method comprises the following steps: step 1, reading a lung CT image, and preprocessing the image; 2, cutting a pulmonary nodule picture and generating a corresponding mask; 3, performing data set division on the obtained pulmonary nodule pictures and the corresponding masks to obtain a training set, a verification set and a test set; step 4, constructing a residual ECA channel attention UNet deep learning network; 5, inputting the obtained training set and verification set into the constructed deep learning network for training; 6, inputting the obtained test set into the trained network to obtain a prediction map; step 7, inputting the prediction map into a sequential tree weighted information transfer algorithm (TRW-S) based on a Markov random field to perform edge smoothing; and step 8, outputting a prediction image.

Description

technical field [0001] The invention belongs to the technical field of image segmentation, and in particular relates to a lung nodule segmentation method combined with a residual attention UNet network and a sequential tree re-weighted information propagation (TRW-S) algorithm. Background technique [0002] Lung cancer is the most common cancer in the world today, accounting for 11.6% of all cancers. In 2019, lung cancer ranked first among Chinese men. Smoking is the most important cause of lung cancer. Malignant pulmonary nodules are the harbingers of lung tumors. The features on CT images are high-density white shadows or ground-glass phantoms in the lungs with a diameter of less than 3 cm. Using segmentation algorithms to segment pulmonary nodules will lead to Assist doctors in judging the condition. Further classification of benign and malignant lesions can also be performed by segmented lesions. Early detection, identification, tracking, and removal of malignant pulmo...

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): G06V10/26G06V10/34G06V10/82G06V10/84G06T7/12G06T7/143G06N3/04G06N3/08G06K9/62
CPCG06T7/12G06T7/143G06N3/08G06T2207/10081G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/20192G06T2207/30064G06N3/047G06N3/048G06N3/045G06F18/295
Inventor 夏平张光一彭程雷帮军唐庭龙徐光柱
Owner CHINA THREE GORGES UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap