Bi-Modal Conceptual Indexing for Medical Image Retrieval

Abstract : To facilitate the automatic indexing and retrieval of large medical image databases, images and associated texts are indexed us- ing concepts from the Unified Medical Language System (UMLS) meta- thesaurus.We propose a structured learning framework for learning med- ical semantics from images. Two complementary global and local visual indexing approaches are presented. Two fusion approaches are also used to improve textual retrieval using the UMLS-based image indexing: a simple post-query fusion and a visual modality filtering to remove visu- ally aberrant images according to the query modality concepts. Using the ImageCLEFmed database, we demonstrate that our framework is superior when compared to the automatic runs evaluated in 2005 on the same Medical Image Retrieval task.
Type de document :
Communication dans un congrès
The 14th International Multimedia Modeling Conference MMM2008, 2008, Kyoto, Japan. 2008
Liste complète des métadonnées

https://hal.inria.fr/hal-00953863
Contributeur : Marie-Christine Fauvet <>
Soumis le : vendredi 28 février 2014 - 16:02:38
Dernière modification le : jeudi 11 octobre 2018 - 08:48:04

Identifiants

  • HAL Id : hal-00953863, version 1

Collections

Citation

Joo-Hwee Lim, Jean-Pierre Chevallet, Thi Hoang Diem Le, Hanlin Goh. Bi-Modal Conceptual Indexing for Medical Image Retrieval. The 14th International Multimedia Modeling Conference MMM2008, 2008, Kyoto, Japan. 2008. 〈hal-00953863〉

Partager

Métriques

Consultations de la notice

272