s'authentifier
version française rss feed
Multimodal medical case retrieval using Bayesian networks and the Dezert-Smarandache theory
Quellec G., Lamard M., Bekri L., Cazuguel G., Roux C., Cochener B.
5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 14-17 (2008) 245-248 - http://www.hal.inserm.fr/inserm-00331189
Multimodal medical case retrieval using Bayesian networks and the Dezert-Smarandache theory
Gwénolé Quellec1, 2, Mathieu Lamard () 1, Lynda Bekri1, 3, Guy Cazuguel1, 2, Christian Roux1, 2, Béatrice Cochener1, 3
1 :  LATIM - Laboratoire de Traitement de l'Information Medicale
INSERM : U650 – Université de Bretagne Occidentale [UBO] – Institut Mines-Télécom – Télécom Bretagne – CHU Brest – PRES Université Européenne de Bretagne [UEB]
Hopital Morvan, 5 Avenue Foch, 29609 Brest Cedex
France
2 :  Télécom Bretagne - Brest
http://www.telecom-bretagne.eu/
Télécom Bretagne
Technopôle Brest-Iroise - CS 83818 - 29238 Brest Cedex 3
France
3 :  Service d'ophtalmologie
CHU Brest – Université de Bretagne Occidentale [UBO]
29200 Brest
France
Most medical images are now digitized and stored with semantic information, leading to medical case databases. They may be used for aid to diagnosis, by retrieving similar cases to those in examination. But the information are often incomplete, uncertain and sometimes conflicting, so difficult to use. In this paper, we present a Case Based Reasoning (CBR) system for medical case retrieval, derived from the Dezert-Smarandache theory, which is well suited to handle those problems. We introduce a case retrieval specific frame of discernment theta, which associates each element of theta with a case in the database; we take advantage of the flexibility offered by the DSmT's hybrid models to finely model the database. The system is designed so that heterogeneous sources of information can be integrated in the system: in particular images, indexed by their digital content, and symbolic information. The method is evaluated on two classified databases: one for diabetic retinopathy follow-up (DRD) and one for screening mammography (DDSM). On these databases, results are promising: the retrieval precision at five reaches 81.8% on DRD and 84.8% on DDSM.
Sciences du Vivant/Ingénierie biomédicale
Anglais
1557-170X

Articles dans des revues avec comité de lecture
10.1109/ISBI.2008.4540978
5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro
internationale
05/2008
14-17
245-248

Bayesian networks – Case based reasoning – Dezert-Smarandache theory – Diabetic Retinopathy – Image indexing
Liste des fichiers attachés à ce document : 
PDF
GQuellec_ISBI2008.pdf(400.1 KB)
inserm-00331189_edited.pdf(1.7 MB)

tous les articles de la base du CCSd...