Multimodal medical case retrieval using Bayesian networks and the Dezert-Smarandache theory

Abstract : 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.
Document type :
Journal articles
5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2008, pp.245-248. <10.1109/ISBI.2008.4540978>
Liste complète des métadonnées


http://www.hal.inserm.fr/inserm-00331189
Contributor : Gwénolé Quellec <>
Submitted on : Wednesday, October 15, 2008 - 4:03:27 PM
Last modification on : Monday, March 23, 2009 - 3:13:55 PM
Document(s) archivé(s) le : Tuesday, October 9, 2012 - 1:51:16 PM

Files

GQuellec_ISBI2008.pdf
Files produced by the author(s)

Identifiers

Citation

Gwénolé Quellec, Mathieu Lamard, Lynda Bekri, Guy Cazuguel, Christian Roux, et al.. Multimodal medical case retrieval using Bayesian networks and the Dezert-Smarandache theory. 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2008, pp.245-248. <10.1109/ISBI.2008.4540978>. <inserm-00331189>

Share

Metrics

Record views

312

Document downloads

255