Other Free Encyclopedias » Online Encyclopedia » Encyclopedia - Featured Articles » Contributed Topics from P-T

Semantic Medical Image Indexing

images regions retrieval research

Definition: Semantic information is useful and effective in medical image retrieval and indexing.

Medical images are an integral part in medical diagnosis, research, and teaching. Medical image analysis research has focused on image registration, measurement, and visualization. Besides being valuable for medical research and training, medical image retrieval systems can assist doctors in diagnosis by retrieving images with known pathologies that are similar to a patient’s image(s). In reality, pathology bearing regions tend to be highly localized. However, it has been recognized that pathology bearing regions cannot be segmented out automatically for many medical domains. Hence the detection-based Semantic Support Regions (SSRs) representation and indexing scheme described in the article Semantic Image Representation and Indexing provides a promising alternative for semantic medical image indexing and retrieval.

Based on 172 images (2%) of the 8725 CasImage collection used in the medical retrieval task of the ImageCLEF 2004 benchmark, 1170 image regions are cropped to train and validate 40 SSRs (names and numbers of cropped samples as listed in Figure 1) using support vector mechines. The Mean Average Precision over 26 query topics. The (as represented by the query images shown above) is 0.4156, an improvement over all the automatic runs submitted to ImageCLEF 2004. The average precisions at top 10, 20, and 30 retrieved images are 0.70, 0.65, and 0.60 respectively.

Semantic Visual Query and Retrieval [next] [back] Semantic Image Representation and Indexing -  

User Comments

Your email address will be altered so spam harvesting bots can't read it easily.
Hide my email completely instead?

Cancel or