Fully Automated Colorimetric Analysis of the Optic Nerve Aided by Deep Learning and Its Association with Perimetry and OCT for the Study of Glaucoma.
deep learning
glaucoma
optic nerve
perimetry
Journal
Journal of clinical medicine
ISSN: 2077-0383
Titre abrégé: J Clin Med
Pays: Switzerland
ID NLM: 101606588
Informations de publication
Date de publication:
22 Jul 2021
22 Jul 2021
Historique:
received:
06
07
2021
revised:
14
07
2021
accepted:
20
07
2021
entrez:
7
8
2021
pubmed:
8
8
2021
medline:
8
8
2021
Statut:
epublish
Résumé
Laguna-ONhE is an application for the colorimetric analysis of optic nerve images, which topographically assesses the cup and the presence of haemoglobin. Its latest version has been fully automated with five deep learning models. In this paper, perimetry in combination with Laguna-ONhE or Cirrus-OCT was evaluated. The morphology and perfusion estimated by Laguna ONhE were compiled into a "Globin Distribution Function" (GDF). Visual field irregularity was measured with the usual pattern standard deviation (PSD) and the threshold coefficient of variation (TCV), which analyses its harmony without taking into account age-corrected values. In total, 477 normal eyes, 235 confirmed, and 98 suspected glaucoma cases were examined with Cirrus-OCT and different fundus cameras and perimeters. The best Receiver Operating Characteristic (ROC) analysis results for confirmed and suspected glaucoma were obtained with the combination of GDF and TCV (AUC: 0.995 and 0.935, respectively. Sensitivities: 94.5% and 45.9%, respectively, for 99% specificity). The best combination of OCT and perimetry was obtained with the vertical cup/disc ratio and PSD (AUC: 0.988 and 0.847, respectively. Sensitivities: 84.7% and 18.4%, respectively, for 99% specificity). Using Laguna ONhE, morphology, perfusion, and function can be mutually enhanced with the methods described for the purpose of glaucoma assessment, providing early sensitivity.
Sections du résumé
BACKGROUND
BACKGROUND
Laguna-ONhE is an application for the colorimetric analysis of optic nerve images, which topographically assesses the cup and the presence of haemoglobin. Its latest version has been fully automated with five deep learning models. In this paper, perimetry in combination with Laguna-ONhE or Cirrus-OCT was evaluated.
METHODS
METHODS
The morphology and perfusion estimated by Laguna ONhE were compiled into a "Globin Distribution Function" (GDF). Visual field irregularity was measured with the usual pattern standard deviation (PSD) and the threshold coefficient of variation (TCV), which analyses its harmony without taking into account age-corrected values. In total, 477 normal eyes, 235 confirmed, and 98 suspected glaucoma cases were examined with Cirrus-OCT and different fundus cameras and perimeters.
RESULTS
RESULTS
The best Receiver Operating Characteristic (ROC) analysis results for confirmed and suspected glaucoma were obtained with the combination of GDF and TCV (AUC: 0.995 and 0.935, respectively. Sensitivities: 94.5% and 45.9%, respectively, for 99% specificity). The best combination of OCT and perimetry was obtained with the vertical cup/disc ratio and PSD (AUC: 0.988 and 0.847, respectively. Sensitivities: 84.7% and 18.4%, respectively, for 99% specificity).
CONCLUSION
CONCLUSIONS
Using Laguna ONhE, morphology, perfusion, and function can be mutually enhanced with the methods described for the purpose of glaucoma assessment, providing early sensitivity.
Identifiants
pubmed: 34362014
pii: jcm10153231
doi: 10.3390/jcm10153231
pmc: PMC8347493
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
J Pediatr Ophthalmol Strabismus. 2017 Nov 1;54(6):387-394
pubmed: 28850641
J Ophthalmol. 2017;2017:2340236
pubmed: 28660077
Biomed Opt Express. 2012 Dec 1;3(12):3127-37
pubmed: 23243564
Eur J Ophthalmol. 2018 Sep;28(5):590-597
pubmed: 29623722
N Engl J Med. 1978 Oct 26;299(17):926-30
pubmed: 692598
Am J Ophthalmol. 2019 May;201:9-18
pubmed: 30689990
Ophthalmology. 2018 Aug;125(8):1199-1206
pubmed: 29506863
Ophthalmology. 2014 Nov;121(11):2081-90
pubmed: 24974815
Clin Exp Ophthalmol. 2019 Jan;47(1):128-139
pubmed: 30155978
Eur J Ophthalmol. 2009 May-Jun;19(3):416-24
pubmed: 19396788
IEEE Trans Med Imaging. 2016 May;35(5):1285-98
pubmed: 26886976
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
JAMA Ophthalmol. 2019 Dec 1;137(12):1353-1360
pubmed: 31513266
Jpn J Ophthalmol. 2019 May;63(3):276-283
pubmed: 30798379
Invest Ophthalmol. 1973 Nov;12(11):814-29
pubmed: 4752920
Sci Rep. 2018 Nov 12;8(1):16685
pubmed: 30420630
Curr Eye Res. 2016 Jun;41(6):798-805
pubmed: 26397129
Acta Ophthalmol. 2016 Nov;94(7):697-704
pubmed: 27130650
Invest Ophthalmol Vis Sci. 2013 Jan 17;54(1):482-9
pubmed: 23221075
Invest Ophthalmol Vis Sci. 2015 Feb 10;56(3):1562-8
pubmed: 25670490
Br J Ophthalmol. 2009 Sep;93(9):1195-9
pubmed: 19493858
Sci Rep. 2018 Oct 2;8(1):14665
pubmed: 30279554
J Glaucoma. 2013 Apr-May;22(4):284-9
pubmed: 23059476
Surv Ophthalmol. 2019 Mar - Apr;64(2):233-240
pubmed: 30248307
J Glaucoma. 2016 Apr;25(4):348-54
pubmed: 25350818
Br J Ophthalmol. 2021 Jul;105(7):957-963
pubmed: 32703781
Int J Ophthalmol. 2018 Sep 18;11(9):1555-1561
pubmed: 30225234
Clin Exp Ophthalmol. 2012 May-Jun;40(4):369-80
pubmed: 22339936
Arch Soc Esp Oftalmol. 2015 May;90(5):212-9
pubmed: 25443462