Longitudinal deep network for consistent OCT layer segmentation.


Journal

Biomedical optics express
ISSN: 2156-7085
Titre abrégé: Biomed Opt Express
Pays: United States
ID NLM: 101540630

Informations de publication

Date de publication:
01 May 2023
Historique:
received: 10 02 2023
revised: 11 03 2023
accepted: 17 03 2023
medline: 19 5 2023
pubmed: 19 5 2023
entrez: 19 5 2023
Statut: epublish

Résumé

Retinal layer thickness is an important bio-marker for people with multiple sclerosis (PwMS). In clinical practice, retinal layer thickness changes in optical coherence tomography (OCT) are widely used for monitoring multiple sclerosis (MS) progression. Recent developments in automated retinal layer segmentation algorithms allow cohort-level retina thinning to be observed in a large study of PwMS. However, variability in these results make it difficult to identify patient-level trends; this prevents patient specific disease monitoring and treatment planning using OCT. Deep learning based retinal layer segmentation algorithms have achieved state-of-the-art accuracy, but the segmentation is performed on each individual scan without utilizing longitudinal information, which can be important in reducing segmentation error and reveal subtle changes in retinal layers. In this paper, we propose a longitudinal OCT segmentation network which achieves more accurate and consistent layer thickness measurements for PwMS.

Identifiants

pubmed: 37206119
doi: 10.1364/BOE.487518
pii: 487518
pmc: PMC10191669
doi:

Types de publication

Journal Article

Langues

eng

Pagination

1874-1893

Subventions

Organisme : NEI NIH HHS
ID : R01 EY024655
Pays : United States
Organisme : NEI NIH HHS
ID : R01 EY032284
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS082347
Pays : United States

Informations de copyright

© 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

Déclaration de conflit d'intérêts

The authors declare that there are no conflicts of interest related to this article.

Références

Biomed Opt Express. 2022 May 05;13(6):3195-3210
pubmed: 35781941
Biomed Opt Express. 2014 Jun 11;5(7):2196-214
pubmed: 25071959
Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9784:
pubmed: 27231406
Mult Scler. 2021 Oct;27(11):1738-1748
pubmed: 33307967
J Biophotonics. 2016 May;9(5):478-89
pubmed: 27159849
Med Image Anal. 2020 Oct;65:101759
pubmed: 32623277
Biomed Opt Express. 2018 May 16;9(6):2681-2698
pubmed: 30258683
Med Image Comput Comput Assist Interv. 2014;17(Pt 1):739-46
pubmed: 25333185
Invest Ophthalmol Vis Sci. 2016 Jul 1;57(9):OCT621-OCT630
pubmed: 27936264
Opt Express. 2010 Sep 27;18(20):21293-307
pubmed: 20941025
IEEE Trans Med Imaging. 2017 Jun;36(6):1276-1286
pubmed: 28186886
Med Image Comput Comput Assist Interv. 2019 Oct;11764:120-128
pubmed: 31853524
Biomed Opt Express. 2019 Feb 04;10(3):1064-1080
pubmed: 30891330
Proc SPIE Int Soc Opt Eng. 2017 Feb 11;10137:
pubmed: 28781413
Comput Biol Med. 2019 Nov;114:103445
pubmed: 31561100
Opt Express. 2010 Aug 30;18(18):19413-28
pubmed: 20940837
Biomed Opt Express. 2017 Apr 27;8(5):2732-2744
pubmed: 28663902
Biomed Opt Express. 2019 Apr 30;10(5):2639-2656
pubmed: 31149385
IEEE Trans Med Imaging. 2000 Mar;19(3):153-65
pubmed: 10875700
Curr Eye Res. 2018 Mar;43(3):415-423
pubmed: 29240464
Biomed Opt Express. 2018 Oct 26;9(11):5759-5777
pubmed: 30460160
Proc SPIE Int Soc Opt Eng. 2014;9034:
pubmed: 27773959
Neuroimage Clin. 2016 Feb 16;11:264-275
pubmed: 26958465
Med Image Anal. 2021 Feb;68:101856
pubmed: 33260113
Biomed Opt Express. 2019 Feb 07;10(3):1126-1135
pubmed: 30891334
Fetal Infant Ophthalmic Med Image Anal (2017). 2017 Sep;10554:202-209
pubmed: 31355372
Biomed Opt Express. 2014 Mar 04;5(4):1062-74
pubmed: 24761289
Mult Scler Int. 2015;2015:136295
pubmed: 26090228
Proc SPIE Int Soc Opt Eng. 2015;9413:
pubmed: 26023248
Med Image Anal. 2015 Dec;26(1):146-58
pubmed: 26401595
Proc IEEE Int Symp Biomed Imaging. 2018 Apr;2018:1445-1448
pubmed: 31853331
Int J Ophthalmol. 2019 Jun 18;12(6):1012-1020
pubmed: 31236362
Proc IEEE Int Symp Biomed Imaging. 2013 Dec 31;2013:476-479
pubmed: 24443687
IEEE Trans Med Imaging. 2009 Sep;28(9):1436-47
pubmed: 19278927
Biomed Opt Express. 2013 Jun 14;4(7):1133-52
pubmed: 23847738
IEEE Trans Neural Netw Learn Syst. 2022 Mar 07;PP:
pubmed: 35254993
Neurology. 2017 Feb 7;88(6):525-532
pubmed: 28077493
Data Brief. 2018 Dec 28;22:601-604
pubmed: 30671506
Biomed Opt Express. 2019 Sep 12;10(10):5042-5058
pubmed: 31646029
Neurology. 2013 Jan 1;80(1):47-54
pubmed: 23267030
Ann Neurol. 2010 Jun;67(6):749-60
pubmed: 20517936
IEEE Trans Med Imaging. 2019 May;38(5):1207-1215
pubmed: 30452352
Neuroimage. 2006 Apr 1;30(2):388-99
pubmed: 16275137
Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9784:
pubmed: 27199502
J Neuroophthalmol. 2022 Mar 1;42(1):e40-e47
pubmed: 34108402

Auteurs

Yufan He (Y)

Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Aaron Carass (A)

Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Yihao Liu (Y)

Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Peter A Calabresi (PA)

Dept. of Neurology, The Johns Hopkins University School of Medicine, MD 21287, USA.

Shiv Saidha (S)

Dept. of Neurology, The Johns Hopkins University School of Medicine, MD 21287, USA.

Jerry L Prince (JL)

Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Classifications MeSH