Pneumothorax detection in chest radiographs using local and global texture signatures

Ofer Geva, Gali Zimmerman-Moreno, Sivan Lieberman, Eli Konen, Hayit Greenspan

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

15 Scopus citations

Abstract

A novel framework for automatic detection of pneumothorax abnormality in chest radiographs is presented. The suggested method is based on a texture analysis approach combined with supervised learning techniques. The proposed framework consists of two main steps: at first, a texture analysis process is performed for detection of local abnormalities. Labeled image patches are extracted in the texture analysis procedure following which local analysis values are incorporated into a novel global image representation. The global representation is used for training and detection of the abnormality at the image level. The presented global representation is designed based on the distinctive shape of the lung, taking into account the characteristics of typical pneumothorax abnormalities. A supervised learning process was performed on both the local and global data, leading to trained detection system. The system was tested on a dataset of 108 upright chest radiographs. Several state of the art texture feature sets were experimented with (Local Binary Patterns, Maximum Response filters). The optimal configuration yielded sensitivity of 81% with specificity of 87%. The results of the evaluation are promising, establishing the current framework as a basis for additional improvements and extensions.

Original languageEnglish
Title of host publicationMedical Imaging 2015
Subtitle of host publicationComputer-Aided Diagnosis
EditorsLubomir M. Hadjiiski, Georgia D. Tourassi
PublisherSPIE
ISBN (Electronic)9781628415049
DOIs
StatePublished - 2015
Externally publishedYes
EventSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis - Orlando, United States
Duration: 22 Feb 201525 Feb 2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9414
ISSN (Print)1605-7422

Conference

ConferenceSPIE Medical Imaging Symposium 2015: Computer-Aided Diagnosis
Country/TerritoryUnited States
CityOrlando
Period22/02/1525/02/15

Bibliographical note

Publisher Copyright:
© 2015 SPIE.

Keywords

  • Chest radiography
  • Computer-aided diagnosis
  • Pneumothorax
  • Supervised classifier
  • Texture
  • X-ray

Fingerprint

Dive into the research topics of 'Pneumothorax detection in chest radiographs using local and global texture signatures'. Together they form a unique fingerprint.

Cite this