KWSim: Concepts Similarity Measure

The comparison of manually annotated medical images can be done using the comparison of keywords in a lexical way or using the existing medical thesauri to calculate semantic similarity. In this paper, first we introduce the KWSim measure, a fully automated technique of measuring semantic similarity by mapping concepts(keywords) to different medical thesauri and examining the "is-a" relation type. A keyword vector similarity is also presented, based on the KWSim measure. Our approach is implemented using MeSH, ICD-10 and SNOMED CT thesauri and compared with two other existing approaches. We illustrate our method with a real time online annotation assistant. RESUME. La comparaison des images medicales annotees manuellement peut etre realisee grâce a une comparaison lexicale entre des mots-cles ou en utilisant des thesaurus medicaux existants pour calculer une similarite semantique entre ces mots. Dans cet article, nous presentons tout d'abord la mesure KWSim, une technique entierement automatisee pour le calcul de la similarite semantique en mappant des concepts (mots-cles) aux differents thesaurus medicaux et en examinant le type de relation « is-a ». Une similarite entre les vecteurs de mots-cles est egalement presentee, basee sur la mesure KWSim. Notre approche est implementee en utilisant MeSH, ICD-10 et SNOMED CT thesaurus et comparee avec deux autres approches existantes. Nous illustrons notre methode avec un assistant d'annotation en ligne et en temps reel.

[1]  Stavros Christodoulakis,et al.  The OntoNL Semantic Relatedness Measure for OWL ontologies , 2007, 2007 2nd International Conference on Digital Information Management.

[2]  Tony Veale,et al.  An Intrinsic Information Content Metric for Semantic Similarity in WordNet , 2004, ECAI.

[3]  Christiane Fellbaum,et al.  Combining Local Context and Wordnet Similarity for Word Sense Identification , 1998 .

[4]  Euripides G. M. Petrakis,et al.  Design and Evaluation of Semantic Similarity Measures for Concepts Stemming from the Same or Different Ontologies , 1998 .

[5]  Carole A. Goble,et al.  Investigating Semantic Similarity Measures Across the Gene Ontology: The Relationship Between Sequence and Annotation , 2003, Bioinform..

[6]  Martha Palmer,et al.  Verb Semantics and Lexical Selection , 1994, ACL.

[7]  Martin Chodorow,et al.  Combining local context and wordnet similarity for word sense identification , 1998 .

[8]  A. Tversky.  Features of Similarity , 1977 .

[9]  Philip Resnik,et al.  Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language , 1999, J. Artif. Intell. Res..

[10]  Elöd Egyed-Zsigmond,et al.  i Concurrent Use in an Image Management System , 2006, ISPE CE.

[11]  Elöd Egyed-Zsigmond,et al.  User centered image management system for digital libraries , 2006, Second International Conference on Document Image Analysis for Libraries (DIAL'06).

[12]  Max J. Egenhofer,et al.  Determining Semantic Similarity among Entity Classes from Different Ontologies , 2003, IEEE Trans. Knowl. Data Eng..

[13]  Roy Rada,et al.  Development and application of a metric on semantic nets , 1989, IEEE Trans. Syst. Man Cybern..

[14]  David McLean,et al.  An Approach for Measuring Semantic Similarity between Words Using Multiple Information Sources , 2003, IEEE Trans. Knowl. Data Eng..