HAL : hal-00655386, version 1

DOI : 10.1007/s10916-009-9296-3

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

Journal of Medical Systems 34, 5 (2010) 815-828

3D Image Analysis and Artificial Intelligence for Bone Disease Classification

Abdurrahim Akgundogdu 1, Rachid Jennane (  Auteur correspondant ) 2, Gabriel Aufort 2, Claude-Laurent Benhamou 3, Osman Nuri Ucan 1

(10/2010)

In order to prevent bone fractures due to disease and ageing of the population, and to detect problems while still in their early stages, 3D bone micro architecture needs to be investigated and characterized. Here, we have developed various image processing and simulation techniques to investigate bone micro architecture and its mechanical stiffness. We have evaluated morphological, topological and mechanical bone features using artificial intelligence methods. A clinical study is carried out on two populations of arthritic and osteoporotic bone samples. The performances of Adaptive Neuro Fuzzy Inference System (ANFIS), Support Vector Machines (SVM) and Genetic Algorithm (GA) in classifying the different samples have been compared. Results show that the best separation success (100 %) is achieved with Genetic Algorithm.

1 :	Department of Electrical and Electronics Eng
	Istanbul University
2 :	Laboratoire PRISME (PRISME)
	Université d'Orléans : EA4229 – ENSI Bourges
3 :	Caractérisation du tissu osseux par imagerie : techniques et applications
	INSERM : U658 – CHR Orléans – Université d'Orléans

Équipe de recherche : Istanbul University IRAuS Ludia Inc. INSERM U658 Dept. of Electrical Electronics Engineering (Istanbul Aydin University)

Domaine

:

Sciences de l'ingénieur/Traitement du signal et de l'image Informatique/Traitement du signal et de l'image

Mots Clés : Trabecular bone – Hybrid Skeleton Graph Analysis – SVM – GA – ANFIS

hal-00655386, version 1

http://hal.archives-ouvertes.fr/hal-00655386

oai:hal.archives-ouvertes.fr:hal-00655386

Contributeur : Rachid Jennane <>

Soumis le : Dimanche 1 Janvier 2012, 23:45:03

Dernière modification le : Lundi 18 Mars 2013, 16:00:31