TeleOphta: Machine learning and image processing methods for teleophthalmology - 09/04/13

Doi : 10.1016/j.irbm.2013.01.010

E. Decencière ^a, G. Cazuguel ^d,^f, X. Zhang ^a,^⁎ , G. Thibault ^a, J.-C. Klein ^a, F. Meyer ^a, B. Marcotegui ^a, G. Quellec ^d, M. Lamard ^d,^g, R. Danno ^e, D. Elie ^e, P. Massin ^b, Z. Viktor ^b, A. Erginay ^b, B. Laÿ ^e, A. Chabouis ^c
^a Center for mathematical morphology, systems and mathematics department, MINES ParisTech, 35, rue St-Honoré, 77300 Fontainebleau, France
^b Service d’ophtalmologie, hôpital Lariboisière, AP–HP, 2, rue Ambroise-Paré, 75475 Paris cedex 10, France
^c Direction de la politique médicale, parcours des patients et organisations médicales innovantes – télémédecine, Assistance publique–Hôpitaux de Paris, 3, avenue Victoria, 75184 Paris cedex 04, France
^d Inserm UMR 1101 LaTIM, bâtiment I, CHRU Morvan, 29200 Brest, France
^e ADCIS, 3, rue Martin-Luther-King, 14280 Saint-Contest, France
^f Télécom Bretagne, Institut Mines-Télécom, ITI Department, 29200 Brest, France
^g Université de Brest, Inserm UMR 1101 LaTIM, SFR ScInBioS, 29200 Brest, France

Corresponding author.

Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.

Abbonarsi

pagine	8
Iconografia	8
Video	0
Altro	0

Abstract

A complete prototype for the automatic detection of normal examinations on a teleophthalmology network for diabetic retinopathy screening is presented. The system combines pathological pattern mining methods, with specific lesion detection methods, to extract information from the images. This information, plus patient and other contextual data, is used by a classifier to compute an abnormality risk. Such a system should reduce the burden on readers on teleophthalmology networks.

Il testo completo di questo articolo è disponibile in PDF.

Mappa

Introduction

General strategy

Databases

Mining pathological patterns in images

Specific lesion detection methods

Preprocessing

Anatomic structures detection

Lesions detection

Classifying patient records

Lesion-based pathological score

Heterogeneous information fusion

Integration and preliminary results

Conclusion

Esportazione

Vol 34 - N° 2

P. 196-203 - aprile 2013 Ritorno al numero

Articolo precedente

Combined finite element model of human proximal femur behaviour considering remodeling and fracture
R. Hambli, C.-L. Benhamou, R. Jennane, E. Lespessailles, W. Skalli, S. Laporte, J.-D. Laredo, V. Bousson, J. Zarka

Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.

Abbonarsi

Già abbonato a @@106933@@ rivista ?

connettersi o creare un account

TeleOphta: Machine learning and image processing methods for teleophthalmology - 09/04/13

Abstract

Mappa

Citazioni Export

File

Contenuto

Il mio account

Aide & support

Dichiarazione CNIL