Share Email Print

Proceedings Paper

Normalization of chest radiographs
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The clinical use of computer-aided diagnosis (CAD) systems is increasing. A possible limitation of CAD systems is that they are typically trained on data from a small number of sources and as a result, they may not perform optimally on data from different sources. In particular for chest radiographs, it is known that acquisition settings, detector technology, proprietary post-processing and, in the case of analog images, digitization, can all influence the appearance and statistical properties of the image. In this work we investigate if a simple energy normalization procedure is sufficient to increase the robustness of CAD in chest radiography. We evaluate the performance of a supervised lung segmentation algorithm, trained with data from one type of machine, on twenty images each from five different sources. The results, expressed in terms of Jaccard index, increase from 0.530 ± 0.290 to 0.914 ± 0.041 when energy normalization is omitted or applied, respectively. We conclude that energy normalization is an effective way to make the performance of lung segmentation satisfactory on data from different sources.

Paper Details

Date Published: 28 February 2013
PDF: 6 pages
Proc. SPIE 8670, Medical Imaging 2013: Computer-Aided Diagnosis, 86700G (28 February 2013); doi: 10.1117/12.2008238
Show Author Affiliations
R.H.H.M. Philipsen, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
P. Maduskar, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
L. Hogeweg, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)
B. van Ginneken, Radboud Univ. Nijmegen Medical Ctr. (Netherlands)

Published in SPIE Proceedings Vol. 8670:
Medical Imaging 2013: Computer-Aided Diagnosis
Carol L. Novak; Stephen Aylward, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?