Show simple item record

dc.contributor.authorSandhu, Harpal Singh.
dc.contributor.authorEltanboly, Ahmed
dc.contributor.authorShalaby, Ahmed
dc.contributor.authorKeynton, Robert S.
dc.contributor.authorSchaal, Schlomit
dc.contributor.authorEl-Baz, Ayman
dc.date2022-08-11T08:09:50.000
dc.date.accessioned2022-08-23T16:45:28Z
dc.date.available2022-08-23T16:45:28Z
dc.date.issued2018-06-01
dc.date.submitted2018-08-02
dc.identifier.citation<p>Invest Ophthalmol Vis Sci. 2018 Jun 1;59(7):3155-3160. doi: 10.1167/iovs.17-23677. <a href="https://doi.org/10.1167/iovs.17-23677">Link to article on publisher's site</a></p>
dc.identifier.issn0146-0404 (Linking)
dc.identifier.doi10.1167/iovs.17-23677
dc.identifier.pmid30029278
dc.identifier.urihttp://hdl.handle.net/20.500.14038/40690
dc.description.abstractPurpose: We determine the feasibility and accuracy of a computer-assisted diagnostic (CAD) system to diagnose and grade nonproliferative diabetic retinopathy (NPDR) from optical coherence tomography (OCT) images. Methods: A cross-sectional, single-center study was done of type II diabetics who presented for routine screening and/or monitoring exams. Inclusion criteria were age 18 or older, diagnosis of diabetes mellitus type II, and clear media allowing for OCT imaging. Exclusion criteria were inability to image the macula, posterior staphylomas, proliferative diabetic retinopathy, and concurrent retinovascular disease. All patients underwent a full dilated eye exam and spectral-domain OCT of a 6 x 6 mm area of the macula in both eyes. These images then were analyzed by a novel CAD system that segments the retina into 12 layers; quantifies the reflectivity, curvature, and thickness of each layer; and ultimately uses this information to train a neural network that classifies images as either normal or having NPDR, and then further grades the level of retinopathy. A first dataset was tested by "leave-one-subject-out" (LOSO) methods and by 2- and 4-fold cross-validation. The system then was tested on a second, independent dataset. Results: Using LOSO experiments on a dataset of images from 80 patients, the proposed CAD system distinguished normal from NPDR subjects with 93.8% accuracy (sensitivity = 92.5%, specificity = 95%) and achieved 97.4% correct classification between subclinical and mild/moderate DR. When tested on an independent dataset of 40 patients, the proposed system distinguished between normal and NPDR subjects with 92.5% accuracy and between subclinical and mild/moderate NPDR with 95% accuracy. Conclusions: A CAD system for automated diagnosis of NPDR based on macular OCT images from type II diabetics is feasible, reliable, and accurate.
dc.language.isoen_US
dc.relation<p><a href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=pubmed&cmd=Retrieve&list_uids=30029278&dopt=Abstract">Link to Article in PubMed</a></p>
dc.rightsCopyright 2018 The Authors. This work is licensed under a Creative Commons Attribution 4.0 International License.
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectEye Diseases
dc.subjectOphthalmology
dc.titleAutomated Diagnosis and Grading of Diabetic Retinopathy Using Optical Coherence Tomography
dc.typeJournal Article
dc.source.journaltitleInvestigative ophthalmology and visual science
dc.source.volume59
dc.source.issue7
dc.identifier.legacyfulltexthttps://escholarship.umassmed.edu/cgi/viewcontent.cgi?article=4504&amp;context=oapubs&amp;unstamped=1
dc.identifier.legacycoverpagehttps://escholarship.umassmed.edu/oapubs/3493
dc.identifier.contextkey12592206
refterms.dateFOA2022-08-23T16:45:28Z
html.description.abstract<p>Purpose: We determine the feasibility and accuracy of a computer-assisted diagnostic (CAD) system to diagnose and grade nonproliferative diabetic retinopathy (NPDR) from optical coherence tomography (OCT) images.</p> <p>Methods: A cross-sectional, single-center study was done of type II diabetics who presented for routine screening and/or monitoring exams. Inclusion criteria were age 18 or older, diagnosis of diabetes mellitus type II, and clear media allowing for OCT imaging. Exclusion criteria were inability to image the macula, posterior staphylomas, proliferative diabetic retinopathy, and concurrent retinovascular disease. All patients underwent a full dilated eye exam and spectral-domain OCT of a 6 x 6 mm area of the macula in both eyes. These images then were analyzed by a novel CAD system that segments the retina into 12 layers; quantifies the reflectivity, curvature, and thickness of each layer; and ultimately uses this information to train a neural network that classifies images as either normal or having NPDR, and then further grades the level of retinopathy. A first dataset was tested by "leave-one-subject-out" (LOSO) methods and by 2- and 4-fold cross-validation. The system then was tested on a second, independent dataset.</p> <p>Results: Using LOSO experiments on a dataset of images from 80 patients, the proposed CAD system distinguished normal from NPDR subjects with 93.8% accuracy (sensitivity = 92.5%, specificity = 95%) and achieved 97.4% correct classification between subclinical and mild/moderate DR. When tested on an independent dataset of 40 patients, the proposed system distinguished between normal and NPDR subjects with 92.5% accuracy and between subclinical and mild/moderate NPDR with 95% accuracy.</p> <p>Conclusions: A CAD system for automated diagnosis of NPDR based on macular OCT images from type II diabetics is feasible, reliable, and accurate.</p>
dc.identifier.submissionpathoapubs/3493
dc.contributor.departmentDepartment of Ophthalmology and Visual Sciences
dc.source.pages3155-3160


Files in this item

Thumbnail
Name:
i1552_5783_59_7_3155.pdf
Size:
528.9Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

Copyright 2018 The Authors. This work is licensed under a Creative Commons Attribution 4.0 International License.
Except where otherwise noted, this item's license is described as Copyright 2018 The Authors. This work is licensed under a Creative Commons Attribution 4.0 International License.