Towards an hybrid system for annotating brain MRI images

Ammar Mechouche 1, * Christine Golbreich 2 Bernard Gibaud 1
* Corresponding author
1 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : This paper describes a method combining symbolic and numerical techniques for annotating brain Magnetic Resonance images. The goal is to assist existing automatic labelling methods which are mostly statistical in nature and do not work very well in certain situations such as the presence of lesions. The system uses existing statistical methods for generating ABox facts that constitute a set of initial information sufficient for fruitful reasoning. The reasoning is supported by an OWL ontology extended with rules, and the facts extracted by the statistical component
Document type :
Conference papers
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-00140857
Contributor : Aurore Quentin <>
Submitted on : Friday, May 4, 2007 - 10:37:54 AM
Last modification on : Monday, March 4, 2019 - 2:08:01 PM
Long-term archiving on : Tuesday, April 6, 2010 - 11:50:49 PM

Identifiers

  • HAL Id : inserm-00140857, version 1

Citation

Ammar Mechouche, Christine Golbreich, Bernard Gibaud. Towards an hybrid system for annotating brain MRI images. Workshop on OWL Experiences and Directions, 2006, Athens, United States. ⟨inserm-00140857⟩

Share

Metrics

Record views

344

Files downloads

167