Skip to main navigation Skip to search Skip to main content

Lung segmentation on x-ray images with neural validation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

Lung segmentation on x-ray images is an important part in the process of feature extraction for recognition purposes. Using it we can extract specific data from the input image. Segmentation allows to remove unnecessary elements such as bones and spine, leaving in the image only the lungs. This solution reduces the area of the image subjected to further analysis in terms of disease detection. In this paper, segmentation technique based on graphics processing methods and swarm algorithm was presented. A swarm methodology was used for extraction of particular portions of the information for which we have applied convolutional neural network as a detector. For the composed method we have performed tests to show and discuss the results.

Original languageEnglish
Title of host publication2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-7
Number of pages7
ISBN (Electronic)9781538627259
DOIs
Publication statusPublished - 1 Jul 2017
Event2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Honolulu, United States
Duration: 27 Nov 20171 Dec 2017

Publication series

Name2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
Volume2018-January

Conference

Conference2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017
Country/TerritoryUnited States
CityHonolulu
Period27/11/171/12/17

Keywords

  • convolutional neural network
  • image segmentation
  • medical image processing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Lung segmentation on x-ray images with neural validation'. Together they form a unique fingerprint.

Cite this