Exudate identification in retinal fundus images using precise textural verifications.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
17 02 2023
17 02 2023
Historique:
received:
11
07
2022
accepted:
13
02
2023
entrez:
22
2
2023
pubmed:
23
2
2023
medline:
25
2
2023
Statut:
epublish
Résumé
One of the most salient diseases of retina is Diabetic Retinopathy (DR) which may lead to irreparable damages to eye vision in the advanced phases. A large number of the people infected with diabetes experience DR. The early identification of DR signs facilitates the treatment process and prevents from blindness. Hard Exudates (HE) are bright lesions appeared in retinal fundus images of DR patients. Thus, the detection of HEs is an important task preventing the progress of DR. However, the detection of HEs is a challenging process due to their different appearance features. In this paper, an automatic method for the identification of HEs with various sizes and shapes is proposed. The method works based on a pixel-wise approach. It considers several semi-circular regions around each pixel. For each semi-circular region, the intensity changes around several directions and non-necessarily equal radiuses are computed. All pixels for which several semi-circular regions include considerable intensity changes are considered as the pixels located in HEs. In order to reduce false positives, an optic disc localization method is proposed in the post-processing phase. The performance of the proposed method has been evaluated on DIARETDB0 and DIARETDB1 datasets. The experimental results confirm the improved performance of the suggested method in term of accuracy.
Identifiants
pubmed: 36808177
doi: 10.1038/s41598-023-29916-y
pii: 10.1038/s41598-023-29916-y
pmc: PMC9938199
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2824Informations de copyright
© 2023. The Author(s).
Références
Sensors (Basel). 2020 Feb 13;20(4):
pubmed: 32069912
Comput Med Imaging Graph. 2017 Jan;55:78-86
pubmed: 27665058
Comput Biol Med. 2014 Feb;45:161-71
pubmed: 24480176
Sci Rep. 2021 Sep 14;11(1):18223
pubmed: 34521886
Comput Biol Med. 2019 Jan;104:62-69
pubmed: 30439600
Lancet Glob Health. 2013 Dec;1(6):e339-49
pubmed: 25104599
Comput Biol Med. 2015 Nov 1;66:47-65
pubmed: 26378502
Med Image Anal. 2020 Jan;59:101561
pubmed: 31671320
Sci Data. 2020 Nov 20;7(1):409
pubmed: 33219237
J Digit Imaging. 2022 Jun;35(3):496-513
pubmed: 35141807
IEEE Trans Med Imaging. 2002 Oct;21(10):1236-43
pubmed: 12585705
Sensors (Basel). 2020 Nov 16;20(22):
pubmed: 33207825
BMC Ophthalmol. 2018 Nov 6;18(1):288
pubmed: 30400869
IEEE Trans Biomed Eng. 2018 Mar;65(3):608-618
pubmed: 28541892
Med Image Anal. 2014 Oct;18(7):1026-43
pubmed: 24972380
J Med Syst. 2019 May 8;43(6):173
pubmed: 31069550
IEEE Trans Med Imaging. 2019 Jun;38(6):1501-1512
pubmed: 30530359
Eye (Lond). 2022 Aug;36(8):1681-1686
pubmed: 34345030
IEEE Trans Med Imaging. 2000 Mar;19(3):203-10
pubmed: 10875704
IEEE Rev Biomed Eng. 2010;3:169-208
pubmed: 22275207
J Med Syst. 2019 May 29;43(7):209
pubmed: 31144041
IEEE Trans Med Imaging. 2019 Oct;38(10):2434-2444
pubmed: 30908197
Comput Biol Med. 2014 Nov;54:156-71
pubmed: 25255154