Automated Diagnosis of Optical Coherence Tomography Angiography (OCTA) Based on Machine Learning Techniques.
convolutional neural networks (CNN)
diabetic retinopathy (DR)
image encryption
optical coherence tomography angiography (OCTA)
security analysis
Journal
Sensors (Basel, Switzerland)
ISSN: 1424-8220
Titre abrégé: Sensors (Basel)
Pays: Switzerland
ID NLM: 101204366
Informations de publication
Date de publication:
18 Mar 2022
18 Mar 2022
Historique:
received:
04
01
2022
revised:
11
03
2022
accepted:
14
03
2022
entrez:
26
3
2022
pubmed:
27
3
2022
medline:
31
3
2022
Statut:
epublish
Résumé
Diabetic retinopathy (DR) refers to the ophthalmological complications of diabetes mellitus. It is primarily a disease of the retinal vasculature that can lead to vision loss. Optical coherence tomography angiography (OCTA) demonstrates the ability to detect the changes in the retinal vascular system, which can help in the early detection of DR. In this paper, we describe a novel framework that can detect DR from OCTA based on capturing the appearance and morphological markers of the retinal vascular system. This new framework consists of the following main steps: (1) extracting retinal vascular system from OCTA images based on using joint Markov-Gibbs Random Field (MGRF) model to model the appearance of OCTA images and (2) estimating the distance map inside the extracted vascular system to be used as imaging markers that describe the morphology of the retinal vascular (RV) system. The OCTA images, extracted vascular system, and the RV-estimated distance map is then composed into a three-dimensional matrix to be used as an input to a convolutional neural network (CNN). The main motivation for using this data representation is that it combines the low-level data as well as high-level processed data to allow the CNN to capture significant features to increase its ability to distinguish DR from the normal retina. This has been applied on multi-scale levels to include the original full dimension images as well as sub-images extracted from the original OCTA images. The proposed approach was tested on in-vivo data using about 91 patients, which were qualitatively graded by retinal experts. In addition, it was quantitatively validated using datasets based on three metrics: sensitivity, specificity, and overall accuracy. Results showed the capability of the proposed approach, outperforming the current deep learning as well as features-based detecting DR approaches.
Identifiants
pubmed: 35336513
pii: s22062342
doi: 10.3390/s22062342
pmc: PMC8952189
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : ASPIRE Award for Research Excellence 2019
ID : Advanced Technology Research Council - ASPIRE.
Références
JAMA. 2017 Dec 12;318(22):2211-2223
pubmed: 29234807
N Engl J Med. 2020 Apr 30;382(18):1687-1695
pubmed: 32286748
Curr Diab Rep. 2017 Aug 8;17(10):82
pubmed: 28791532
Transl Vis Sci Technol. 2020 Apr 13;9(2):20
pubmed: 32818081
Invest Ophthalmol Vis Sci. 2012 Jan 05;53(1):85-92
pubmed: 22125275
Eye Vis (Lond). 2019 Nov 18;6:37
pubmed: 31832448
Retina. 2020 Mar;40(3):412-420
pubmed: 30576300
Clin Ophthalmol. 2013;7:389-94
pubmed: 23458976
PLoS One. 2019 Nov 7;14(11):e0223965
pubmed: 31697697
Int J Retina Vitreous. 2015 Apr 15;1:5
pubmed: 27847598
Graefes Arch Clin Exp Ophthalmol. 2021 Aug;259(8):2103-2111
pubmed: 33528650
Comput Biol Med. 2017 Oct 1;89:150-161
pubmed: 28806613
J Clin Med. 2019 Apr 05;8(4):
pubmed: 30959798
BMC Ophthalmol. 2018 May 8;18(1):113
pubmed: 29739379
PLoS One. 2019 Feb 22;14(2):e0212364
pubmed: 30794594
J Diabetes Res. 2016;2016:2156273
pubmed: 27761468
Radiology. 2017 Aug;284(2):574-582
pubmed: 28436741
Ophthalmology. 2018 Oct;125(10):1608-1622
pubmed: 29776671
Ophthalmology. 2019 Nov;126(11):1533-1540
pubmed: 31358385
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Ophthalmic Res. 2019;62(4):196-202
pubmed: 31362288
Biomed Opt Express. 2020 Aug 25;11(9):5249-5257
pubmed: 33014612
Asia Pac J Ophthalmol (Phila). 2019 May-Jun;8(3):264-272
pubmed: 31149787
PLoS One. 2020 Oct 22;15(10):e0240064
pubmed: 33091032
Can J Ophthalmol. 2008 Dec;43(6):678-82
pubmed: 19020634
Int J Mol Sci. 2018 Jun 20;19(6):
pubmed: 29925789
IEEE Trans Image Process. 2006 Nov;15(11):3440-51
pubmed: 17076403
Invest Ophthalmol Vis Sci. 2015 Aug;56(9):5229-37
pubmed: 26244299
Transl Vis Sci Technol. 2020 Jul 02;9(2):35
pubmed: 32855839
Lancet Digit Health. 2019 Aug;1(4):e172-e182
pubmed: 33323187
ISRN Ophthalmol. 2013 Jan 15;2013:343560
pubmed: 24563789
Diabetes. 2005 Jun;54(6):1615-25
pubmed: 15919781
JAMA Ophthalmol. 2015 Jan;133(1):45-50
pubmed: 25317632