Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Unsupervised localization of heart and lung regions in EIT images: a validation study
 

Summary: Unsupervised localization of heart and lung
regions in EIT images: a validation study
Damien Ferrario1
, Andy Adler1,2
, Josesp SolÓ1
, Stephan B÷hm1
and Marc Bodenstein3
1
CSEM - Centre Suisse d'Electronique et de Microtechnique, Switzerland
2
Systems and Computer Engineering, Carleton University, Ottawa, Canada
3
Department of Anesthesiology, Johannes Gutenberg-University Mainz, Germany
Abstract: We describe an algorithm for automatic detection of heart and lung regions in a time
series of EIT images. Candidate regions are identified in the frequency domain and image based
classification techniques applied. The algorithm was validated on a set of simultaneously
recorded EIT and CT data in pigs. In 20 of 21 cases, identified regions in EIT images
corresponded to those manually segmented in the matched CT image. Results confirm the
accuracy of anatomical features in EIT images, as long as morphologically accurate information
is used in EIT reconstruction.

  

Source: Adler, Andy - Department of Systems and Computer Engineering, Carleton University

 

Collections: Computer Technologies and Information Sciences