2013
DOI: 10.1016/j.irbm.2013.01.010
|View full text |Cite
|
Sign up to set email alerts
|

TeleOphta: Machine learning and image processing methods for teleophthalmology

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
155
0
4

Year Published

2014
2014
2022
2022

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 393 publications
(182 citation statements)
references
References 10 publications
0
155
0
4
Order By: Relevance
“…DRIONS-DB contains retinal images for optic nerve head segmentation benchmarking (Carmona et al, 2008). Concerning retinal lesions, like microaneurysms and exudates, several databases are available such as DIARETDB0, DIARETDB1 (Kauppi et al, 2007), HEI-MED (Giancardo et al, 2012), ROC (Niemeijer et al, 2010) and e-ophtha (Decencière et al, 2013).…”
Section: Introductionmentioning
confidence: 99%
“…DRIONS-DB contains retinal images for optic nerve head segmentation benchmarking (Carmona et al, 2008). Concerning retinal lesions, like microaneurysms and exudates, several databases are available such as DIARETDB0, DIARETDB1 (Kauppi et al, 2007), HEI-MED (Giancardo et al, 2012), ROC (Niemeijer et al, 2010) and e-ophtha (Decencière et al, 2013).…”
Section: Introductionmentioning
confidence: 99%
“…The e-ophtha database contains 47 color fundus images with size ranging from 1440 × 960 to 2540 × 1690 pixels, which were segmented in order to find exudates by three ophthalmologists from the OPHDIAT Tele-medical network under the the French Research Agency (ANR) project, specially designed for scientific research in Diabetic Retinopathy (DR) [15]. The labelled patches dataset created of 48 × 48 pixels with exudate and healthy classes after the preprocessing steps: cropping and data augmentation was randomly split by images where an image could only belong to a group with the following datasets distribution: Training dataset with 8760 patches by each class, validation dataset has 328 by class and test dataset has 986 by class, representing 45%, 15% and 40% respectively.…”
Section: E-ophtha Datasetmentioning
confidence: 99%
“…Its main objective was to develop the tools for fundus image classification, in order to assist in the detection of retinal diseases, especially of diabetic retinopathy. Some research works developed by Decencière et al (2013) and Zhang et al (2012) and the publication of the E-OPHTHA fundus database were important results of this project.…”
Section: International Groupsmentioning
confidence: 92%
“…E-OPHTHA (Decencière et al, 2013) is a database of fundus images especially designed for diabetic retinopathy screening 1 . This public database is divided in two subsets depending on the lesion type: exudates and microaneurysms.…”
Section: E-ophthamentioning
confidence: 99%
See 1 more Smart Citation