Recognizing Emphysema - A Neural Network Approach

O. Friman, M. Borga, M. Lundberg, U. Tyl�Á�n, H. Knutsson
ICPR'02
Proceedings of 16th International Conference on Pattern Recognition
Pages 1-4
August, 2002

Download full paper

Abstract

An accurate and fully automatic method for detecting and quantifying emphysema in CT-images is presented. The method is based on an image preprocessing step followed by a neural network classifier tra ined to separate true emphysema from artifacts. The proposed approach is shown to be superior to an established method when applied on real patient data.

Regions detected before and after the classifier step in an emphysematous lung and in a normal lung with some artifacts.

Reference

Friman O, Borga M, Lundberg M, Tyl�Á�n U, Knutsson H. Recognizing emphysema - A neural network approach. In Proceedings of 16th International Conference on Pattern Recognition. 2002;1-4.

Bibtex entry

@InProceedings{frimanICPR02,
  author         = {O. Friman and M. Borga and M. Lundberg and U.              
                   Tyl�Á�n and H. Knutsson },                     
  title          = {Recognizing Emphysema - {A} Neural Network Approach},      
  booktitle      = {Proceedings of 16th International Conference on Pattern    
                   Recognition},                                               
  year           = {2002},                                                     
  pages          = {1--4},                                                     
  month          = {August}
}

Research area

CT