RadioGraphics
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
QUICK SEARCH:   [advanced]


     

DOI: 10.1148/rg.253045071
This Article
Right arrow Abstract Freely available
Right arrow Full Text
Right arrow Full Text (PDF)
Right arrow Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when eLetters are posted
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Müller, H.
Right arrow Articles by Geissbuhler, A.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Müller, H.
Right arrow Articles by Geissbuhler, A.
Related Collections
Right arrow Informatics

Benefits of Content-based Visual Data Access in Radiology1

Henning Müller, PhD, Antoine Rosset, MD, Arnaud Garcia, Jean-Paul Vallée, PhD, MD and Antoine Geissbuhler, MD

1 From the Service of Medical Informatics, University and University Hospitals of Geneva, 24 Rue Michelidu-Crest, 1211 Geneva 14, Switzerland. Presented as an infoRAD exhibit at the 2003 RSNA Scientific Assembly. Received April 12, 2004; revision requested July 1; final revision received January 13, 2005; accepted January 20. All authors have no financial relationships to disclose.


View larger version (69K):

[in a new window]
  		Figure 1.  Content-based image retrieval as a diagnostic aid with use of medGift and the casimage database. The query image (left) shows emphysematous lesions with multiple confluent centrilobular and paraseptal areas of low attenuation without visible walls. The search results show six images, including five cases of emphysema (right), with each image accompanied by a link to the complete case description. One image demonstrates unilateral emphysema (MacLeod [Swyer-James] syndrome), and two images show a small area of consolidation in the pulmonary parenchyma (cryptogenic organized pneumonia [COP] and pulmonary embolism). The typical pattern of pulmonary parenchyma destruction seen on these five images strongly suggests the diagnosis of emphysema for the query image.

 


View larger version (70K):

[in a new window]
  		Figure 2.  Partly failed retrieval due to insufficient information in the query image (top left) with respect to varying gray-level changes or strong textures. There is no sharply lined object in the query image, which would have made retrieval easier.

 


View larger version (160K):

[in a new window]
  		Figure 3.  Extraction of local image features. The image is first partitioned into four equal regions (red lines), and this process is repeated for each successive subregion (blue, green, and yellow lines) to extract local image characteristics.

 


View larger version (48K):

[in a new window]
  		Figure 4.  Screen shows the interface of medGIFT and casimage. Clicking on an image in the medGIFT interface brings up the corresponding textual case description.

 




HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
RADIOGRAPHICS RADIOLOGY RSNA JOURNALS ONLINE
Copyright © 2005 by the Radiological Society of North America.