دورية أكاديمية
أعرض في EDS

Deep learning-based analysis of macaque corneal sub-basal nerve fibers in confocal microscopy images.

التفاصيل البيبلوغرافية
العنوان: Deep learning-based analysis of macaque corneal sub-basal nerve fibers in confocal microscopy images.
المؤلفون: Oakley JD; Voxeleron LLC, San Francisco, CA USA., Russakoff DB; Voxeleron LLC, San Francisco, CA USA., McCarron ME; 2Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, MD USA., Weinberg RL; 2Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, MD USA., Izzi JM; 2Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, MD USA., Misra SL; 3Department of Ophthalmology, Faculty of Medical and Health Sciences, New Zealand National Eye Centre, University of Auckland, Auckland, New Zealand., McGhee CN; 3Department of Ophthalmology, Faculty of Medical and Health Sciences, New Zealand National Eye Centre, University of Auckland, Auckland, New Zealand., Mankowski JL; 2Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, MD USA.
المصدر: Eye and vision (London, England) [Eye Vis (Lond)] 2020 May 08; Vol. 7, pp. 27. Date of Electronic Publication: 2020 May 08 (Print Publication: 2020).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: BioMed Central Country of Publication: England NLM ID: 101664982 Publication Model: eCollection Cited Medium: Print ISSN: 2326-0254 (Print) Linking ISSN: 23260254 NLM ISO Abbreviation: Eye Vis (Lond) Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: London : BioMed Central, [2014]-
مستخلص: Background: To develop and validate a deep learning-based approach to the fully-automated analysis of macaque corneal sub-basal nerves using in vivo confocal microscopy (IVCM).
Methods: IVCM was used to collect 108 images from 35 macaques. 58 of the images from 22 macaques were used to evaluate different deep convolutional neural network (CNN) architectures for the automatic analysis of sub-basal nerves relative to manual tracings. The remaining images were used to independently assess correlations and inter-observer performance relative to three readers.
Results: Correlation scores using the coefficient of determination between readers and the best CNN averaged 0.80. For inter-observer comparison, inter-correlation coefficients (ICCs) between the three expert readers and the automated approach were 0.75, 0.85 and 0.92. The ICC between all four observers was 0.84, the same as the average between the CNN and individual readers.
Conclusions: Deep learning-based segmentation of sub-basal nerves in IVCM images shows high to very high correlation to manual segmentations in macaque data and is indistinguishable across readers. As quantitative measurements of corneal sub-basal nerves are important biomarkers for disease screening and management, the reported work offers utility to a variety of research and clinical studies using IVCM.
Competing Interests: Competing interestsThe authors declare that they have no competing interests.
(© The Author(s) 2020.)
References: J Neuropathol Exp Neurol. 2015 Nov;74(11):1053-60. (PMID: 26426267)
Med Image Anal. 2011 Oct;15(5):738-47. (PMID: 21719344)
Invest Ophthalmol Vis Sci. 2008 Nov;49(11):4801-7. (PMID: 18614801)
Invest Ophthalmol Vis Sci. 2013 Oct 29;54(10):7091-102. (PMID: 24084094)
Invest Ophthalmol Vis Sci. 2018 Feb 1;59(2):1113-1118. (PMID: 29490348)
Cytometry A. 2004 Apr;58(2):167-76. (PMID: 15057970)
IEEE Trans Biomed Eng. 2017 Apr;64(4):786-794. (PMID: 27295646)
Invest Ophthalmol Vis Sci. 2015 Aug;56(9):5060-5. (PMID: 26241393)
Invest Ophthalmol Vis Sci. 2014 Apr 03;55(4):2071-8. (PMID: 24569580)
IEEE Trans Pattern Anal Mach Intell. 2017 Dec;39(12):2481-2495. (PMID: 28060704)
Cornea. 2013 May;32(5):e83-9. (PMID: 23172119)
Diabetes. 1989 Nov;38(11):1365-70. (PMID: 2695371)
J Neuropathol Exp Neurol. 2007 Jan;66(1):26-34. (PMID: 17204934)
J Comp Neurol. 2007 Apr 1;501(4):543-67. (PMID: 17278131)
Med Image Anal. 2016 Aug;32:216-32. (PMID: 27136674)
Diabetes Care. 2015 Jun;38(6):1138-44. (PMID: 25795415)
Invest Ophthalmol Vis Sci. 2017 Jul 1;58(9):3677-3681. (PMID: 28727882)
JAMA Ophthalmol. 2017 Jul 1;135(7):795-800. (PMID: 28594979)
Mult Scler. 2017 Dec;23(14):1847-1853. (PMID: 27811337)
Med Image Comput Comput Assist Interv. 2010;13(Pt 1):300-7. (PMID: 20879244)
Am J Pathol. 2011 Nov;179(5):2337-45. (PMID: 21924225)
Transl Vis Sci Technol. 2016 Sep 30;5(5):7. (PMID: 27730007)
Diabetologia. 2020 Feb;63(2):419-430. (PMID: 31720728)
J Clin Neurosci. 2017 May;39:53-58. (PMID: 28268149)
Am J Pathol. 2014 Jun;184(6):1652-9. (PMID: 24828391)
معلومات مُعتمدة: R01 NS055651 United States NS NINDS NIH HHS; R01 NS097221 United States NS NINDS NIH HHS; U42 OD013117 United States OD NIH HHS
فهرسة مساهمة: Keywords: Cornea; Deep learning; In vivo confocal microscopy; Macaque; Sensory nerves
تواريخ الأحداث: Date Created: 20200519 Latest Revision: 20240328
رمز التحديث: 20240329
مُعرف محوري في PubMed: PMC7206808
DOI: 10.1186/s40662-020-00192-5
PMID: 32420401
قاعدة البيانات: MEDLINE
الوصف
تدمد:2326-0254
DOI:10.1186/s40662-020-00192-5