دورية أكاديمية
أعرض في EDS

RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure.

التفاصيل البيبلوغرافية
العنوان: RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure.
المؤلفون: Datta S; Department of Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, 27708, USA., Mariottoni EB; Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke University, Durham, NC, 27705, USA., Dov D; Department of Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, 27708, USA., Jammal AA; Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke University, Durham, NC, 27705, USA., Carin L; Department of Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, 27708, USA., Medeiros FA; Department of Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, NC, 27708, USA. felipe.medeiros@duke.edu.; Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center, Duke University, Durham, NC, 27705, USA. felipe.medeiros@duke.edu.
المصدر: Scientific reports [Sci Rep] 2021 Jun 15; Vol. 11 (1), pp. 12562. Date of Electronic Publication: 2021 Jun 15.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
أسماء مطبوعة: Original Publication: London : Nature Publishing Group, copyright 2011-
مواضيع طبية MeSH: Tomography, Optical Coherence* , Visual Field Tests*, Glaucoma, Open-Angle/*diagnosis , Retina/*diagnostic imaging, Aged ; Deep Learning ; Glaucoma, Open-Angle/diagnostic imaging ; Glaucoma, Open-Angle/pathology ; Humans ; Intraocular Pressure/physiology ; Male ; Middle Aged ; Nerve Fibers/pathology ; Neural Networks, Computer ; Optic Disk/diagnostic imaging ; Optic Disk/pathology ; Retina/pathology ; Retinal Ganglion Cells/pathology ; Retinal Ganglion Cells/ultrastructure ; Visual Fields/physiology
مستخلص: Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test's innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the "floor effect" for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.
References: Sci Rep. 2019 Dec 6;9(1):18528. (PMID: 31811166)
Am J Ophthalmol. 2020 Feb;210:19-25. (PMID: 31715158)
PLoS One. 2020 Jul 6;15(7):e0234902. (PMID: 32628672)
Am J Ophthalmol. 2017 Mar;175:37-44. (PMID: 27914978)
Transl Vis Sci Technol. 2020 Mar 30;9(2):19. (PMID: 32818080)
Ophthalmology. 2000 Oct;107(10):1809-15. (PMID: 11013178)
Invest Ophthalmol Vis Sci. 2002 Aug;43(8):2654-9. (PMID: 12147599)
Ophthalmology. 2020 Mar;127(3):346-356. (PMID: 31718841)
JAMA. 2014 May 14;311(18):1901-11. (PMID: 24825645)
Invest Ophthalmol Vis Sci. 2010 Nov;51(11):5657-66. (PMID: 20505207)
Lancet. 2015 Apr 4;385(9975):1295-304. (PMID: 25533656)
Lancet. 2004 May 22;363(9422):1711-20. (PMID: 15158634)
Ophthalmology. 2016 Mar;123(3):552-7. (PMID: 26704883)
Ophthalmology. 2016 Jan;123(1):P41-P111. (PMID: 26581556)
Sci Rep. 2020 Jan 15;10(1):402. (PMID: 31941958)
Invest Ophthalmol Vis Sci. 2017 Aug 1;58(10):3975-3985. (PMID: 28796875)
Arch Ophthalmol. 2011 Sep;129(9):1167-74. (PMID: 21555599)
Br J Ophthalmol. 2006 Mar;90(3):262-7. (PMID: 16488940)
JAMA Ophthalmol. 2018 Apr 1;136(4):329-335. (PMID: 29450497)
Ophthalmology. 2021 Jan;128(1):48-57. (PMID: 32579892)
Ophthalmol Glaucoma. 2021 Jan-Feb;4(1):102-112. (PMID: 32826205)
Acta Ophthalmol Scand. 1997 Aug;75(4):368-75. (PMID: 9374242)
Proc Natl Acad Sci U S A. 2008 Dec 16;105(50):19690-5. (PMID: 19066221)
Ophthalmology. 2014 Jul;121(7):1359-69. (PMID: 24629617)
تواريخ الأحداث: Date Created: 20210616 Date Completed: 20211029 Latest Revision: 20211029
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC8206091
DOI: 10.1038/s41598-021-91493-9
PMID: 34131181
قاعدة البيانات: MEDLINE
الوصف
تدمد:2045-2322
DOI:10.1038/s41598-021-91493-9