You are here

Local Concept-Based Medical Image Retrieval With Correlation-Enhanced Similarity Matching Based On Global Analysis

Printer-friendly versionPrinter-friendly version
Rahman MM, Antani SK, Thoma GR
IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA10) in conjunction with IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2010. June 2010:87-94
Abstract: 

A correlation-enhanced similarity matching framework for medical image retrieval is presented in a local conceptbased feature space. In this framework, images are presented by vectors of concepts that comprise of local color and texture patches of image regions in a multi-dimensional feature space. To generate the concept vocabularies and represent the images, statistical models are built using a probabilistic multi-class support vector machine (SVM). For the similarity search, the concept correlations in the collection as a whole are analyzed as a global thesauruslike structure and incorporated in a similarity matching function. The proposed scheme overcomes some limitations of the 'bag of concepts' model, such as the assumption of feature independence. A systematic evaluation of image retrieval on a biomedical image collection of different modalities demonstrates the advantages of the proposed retrieval framework in terms of precision-recall.

Rahman MM, Antani SK, Thoma GR. Local Concept-Based Medical Image Retrieval With Correlation-Enhanced Similarity Matching Based On Global Analysis IEEE Computer Society Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA10) in conjunction with IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2010. June 2010:87-94