For Publishers
DiscoveryMetadataPeer reviewHostingPublishing
For Researchers
JoinPublishReviewCollect
Register
Blog
About
Search
Advanced search
My ScienceOpen
Search
For Publishers
For Researchers
Blog
About
4
views
22
references
 Top references
cited by
22
    
0 reviews
 Review
0
comments
 Comment
0
recommends
+1 Recommend
0 collections
    0
    shares
      1,259
      similar
       All similar
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Machine learning helps improve diagnostic ability of subclinical keratoconus using Scheimpflug and OCT imaging modalities

      research-article

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Purpose

          To develop an automated classification system using a machine learning classifier to distinguish clinically unaffected eyes in patients with keratoconus from a normal control population based on a combination of Scheimpflug camera images and ultra-high-resolution optical coherence tomography (UHR-OCT) imaging data.

          Methods

          A total of 121 eyes from 121 participants were classified by 2 cornea experts into 3 groups: normal (50 eyes), with keratoconus (38 eyes) or with subclinical keratoconus (33 eyes). All eyes were imaged with a Scheimpflug camera and UHR-OCT. Corneal morphological features were extracted from the imaging data. A neural network was used to train a model based on these features to distinguish the eyes with subclinical keratoconus from normal eyes. Fisher’s score was used to rank the differentiable power of each feature. The receiver operating characteristic (ROC) curves were calculated to obtain the area under the ROC curves (AUCs).

          Results

          The developed classification model used to combine all features from the Scheimpflug camera and UHR-OCT dramatically improved the differentiable power to discriminate between normal eyes and eyes with subclinical keratoconus (AUC = 0.93). The variation in the thickness profile within each individual in the corneal epithelium extracted from UHR-OCT imaging ranked the highest in differentiating eyes with subclinical keratoconus from normal eyes.

          Conclusion

          The automated classification system using machine learning based on the combination of Scheimpflug camera data and UHR-OCT imaging data showed excellent performance in discriminating eyes with subclinical keratoconus from normal eyes. The epithelial features extracted from the OCT images were the most valuable in the discrimination process. This classification system has the potential to improve the differentiable power of subclinical keratoconus and the efficiency of keratoconus screening.

          Related collections

          Most cited references22

          • Record: found
          • Abstract: found
          • Article: not found

          Long-term results of riboflavin ultraviolet a corneal collagen cross-linking for keratoconus in Italy: the Siena eye cross study.

          Aldo Caporossi, Cosimo Mazzotta, Stefano Baiocchi … (2010)
          To report the long-term results of 44 keratoconic eyes treated by combined riboflavin ultraviolet A collagen cross-linking in the first Italian open, nonrandomized phase II clinical trial, the Siena Eye Cross Study. Perspective, nonrandomized, open trial. After Siena University Institutional Review Board approval, from September 2004 through September 2008, 363 eyes with progressive keratoconus were treated with riboflavin ultraviolet A collagen cross-linking. Forty-four eyes with a minimum follow-up of 48 months (mean, 52.4 months; range, 48 to 60 months) were evaluated before and after surgery. Examinations comprised uncorrected visual acuity, best spectacle-corrected visual acuity, spherical spectacle-corrected visual acuity, endothelial cells count (I Konan, Non Con Robo; Konan Medical, Inc., Hyogo, Japan), optical (Visante OCT; Zeiss, Jena, Germany) and ultrasound (DGH; Pachette, Exton, Pennsylvania, USA) pachymetry, corneal topography and surface aberrometry (CSO EyeTop, Florence, Italy), tomography (Orbscan IIz; Bausch & Lomb Inc., Rochester, New York, USA), posterior segment optical coherence tomography (Stratus OCT; Zeiss, Jena, Germany), and in vivo confocal microscopy (HRT II; Heidelberg Engineering, Rostock, Germany). Keratoconus stability was detected in 44 eyes after 48 months of minimum follow-up; fellow eyes showed a mean progression of 1.5 diopters in more than 65% after 24 months, then were treated. The mean K value was reduced by a mean of 2 diopters, and coma aberration reduction with corneal symmetry improvement was observed in more than 85%. The mean best spectacle-corrected visual acuity improved by 1.9 Snellen lines, and the uncorrected visual acuity improved by 2.7 Snellen lines. The results of the Siena Eye Cross Study showed a long-term stability of keratoconus after cross-linking without relevant side effects. The uncorrected visual acuity and best spectacle-corrected visual acuity improvements were supported by clinical, topographic, and wavefront modifications induced by the treatment. Copyright 2010 Elsevier Inc. All rights reserved.
          Article 0 comments Cited 185 times – based on 0 reviews     Review now
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found
            Is Open Access

            Anterior segment optical coherence tomography

            Marcus Ang, Mani Baskaran, René Werkmeister … (2018)
            Optical coherence tomography (OCT) provides non-contact, rapid in vivo imaging of ocular structures, and has become a key part of evaluating the anterior segment of the eye. Over the years, improvements to technology have increased the speed of capture and resolution of images, leading to the increasing impact of anterior segment OCT imaging on clinical practice. In this review, we summarize the historical development of anterior segment OCT, and provide an update on the research and clinical applications of imaging the ocular surface, cornea, anterior chamber structures, aqueous outflow system, and most recently anterior segment vessels. We also describe advancements in anterior segment OCT technology that have improved understanding with greater detail, such as tear film in dry eye disease evaluation, intra-operative real-time imaging for anterior segment surgery, and aqueous outflow with angle assessment for glaucoma. Improvements to image processing and software have also improved the ease and utility of interpreting anterior segment OCT images in everyday clinical practice. Future developments include refinement of assessing vascular networks for the anterior segment, in vivo ultra-high resolution anterior segment optical coherence tomography with histology-like detail, en-face image with 3-dimensional reconstruction as well as functional extensions of the technique.
            Article 0 comments Cited 133 times – based on 0 reviews     Review now
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data.

              Maria Clara Arbelaez, Francesco Versaci, Gabriele Vestri … (2012)
              To define a new classification method for the diagnosis of keratoconus based on corneal measurements provided by a Scheimpflug camera combined with Placido corneal topography (Sirius, CSO, Florence, Italy).
              Article 0 comments Cited 72 times – based on 0 reviews     Review now
                Bookmark
                All references

                Author and article information

                Contributors
                Fan Lu: lufan62@mail.eye.ac.cn
                Meixiao Shen:
                ORCID: http://orcid.org/0000-0002-4297-962X
                smx77@sohu.com
                Journal
                Journal ID (nlm-ta): Eye Vis (Lond)
                Journal ID (iso-abbrev): Eye Vis (Lond)
                Title: Eye and Vision
                Publisher: BioMed Central (London )
                ISSN (Electronic): 2326-0254
                Publication date (Electronic): 10 September 2020
                Publication date PMC-release: 10 September 2020
                Publication date Collection: 2020
                Volume: 7
                Electronic Location Identifier: 48
                Affiliations
                [1 ]GRID grid.268099.c, ISNI 0000 0001 0348 3990, School of Ophthalmology and Optometry, , Wenzhou Medical University, ; 270 Xueyuan Road, Wenzhou, Zhejiang, 325027 China
                [2 ]GRID grid.469325.f, ISNI 0000 0004 1761 325X, College of Computer Science and Technology, , Zhejiang University of Technology, ; Hangzhou, Zhejiang 12624 China
                Author information
                http://orcid.org/0000-0002-4297-962X
                Article
                Publisher ID: 213
                DOI: 10.1186/s40662-020-00213-3
                PMC ID: 7507244
                PubMed ID: 32974414
                SO-VID: 55089297-48d4-40eb-84ec-d6bc564ca48c
                Copyright © © The Author(s) 2020
                License:

                Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

                History
                Date received : 20 December 2019
                Date accepted : 19 August 2020
                Categories
                Subject: Research
                Custom metadata
                issue-copyright-statement © The Author(s) 2020

                Keywords: subclinical keratoconus,machine learning,combined-devices,ultra-high resolution optical coherence tomography,scheimpflug camera
                Data availability:
                Keywords: subclinical keratoconus, machine learning, combined-devices, ultra-high resolution optical coherence tomography, scheimpflug camera

                Comments

                Comment on this article

                scite_

                Similar content1,259

                See all similar

                Cited by22

                See all cited by

                Most referenced authors351

                See all reference authors