13
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Deep Learning for Predicting Refractive Error From Retinal Fundus Images

      Read this article at

      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

          We evaluate how deep learning can be applied to extract novel information such as refractive error from retinal fundus imaging.

          Related collections

          Most cited references19

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

          Automated Identification of Diabetic Retinopathy Using Deep Learning

          Diabetic retinopathy (DR) is one of the leading causes of preventable blindness globally. Performing retinal screening examinations on all diabetic patients is an unmet need, and there are many undiagnosed and untreated cases of DR. The objective of this study was to develop robust diagnostic technology to automate DR screening. Referral of eyes with DR to an ophthalmologist for further evaluation and treatment would aid in reducing the rate of vision loss, enabling timely and accurate diagnoses.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            Identity Mappings in Deep Residual Networks

            , , (2016)
            Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which further makes training easy and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62% error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/resnet-1k-layers.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Shape of the retinal surface in emmetropia and myopia.

              To determine and compare the shapes of the retinas of emmetropic and myopic eyes. Nonrotationally symmetrical ellipsoids were mathematically fitted to the retinal surfaces of 21 emmetropic and 66 myopic eyes (up to -12 D) of participants aged 18 to 36 years (mean, 25.5) using transverse axial and sagittal images derived from magnetic resonance imaging. The shapes of the ellipsoids varied considerably between subjects with similar refractive errors. The shapes were oblate (steepening toward the equator) in most of the emmetropic eyes (i.e., the axial dimensions of the ellipsoids were smaller than both the vertical and horizontal dimensions). As myopia increased, all ellipsoid dimensions increased with the axial dimension increasing more than the vertical dimension, which in turn increased more than the horizontal dimension (increases in approximate ratios 3:2:1). The relative difference in the increase of these dimensions meant that as the degree of myopia increased the retinal shape decreased in oblateness. However, few myopic eyes were prolate (flattening toward the equator). Independent of myopia, the ellipsoids were tilted about the vertical axis by 11 degrees +/- 13 degrees , and ellipsoid centers were decentered horizontally by 0.5 +/- 0.4 mm nasally and 0.2 +/- 0.5 mm inferiorly, relative to the fovea. In general both emmetropic and myopic retinas are oblate in shape, although myopic eyes less so. This finding may be relevant to theories implicating the peripheral retina in the development of myopia.
                Bookmark

                Author and article information

                Journal
                Investigative Opthalmology & Visual Science
                Invest. Ophthalmol. Vis. Sci.
                Association for Research in Vision and Ophthalmology (ARVO)
                1552-5783
                June 01 2018
                June 04 2018
                : 59
                : 7
                : 2861
                Affiliations
                [1 ]Google Research, Google, Inc., Mountain View, California, United States
                [2 ]Google DeepMind, Google, Inc., London, United Kingdom
                [3 ]NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
                Article
                10.1167/iovs.18-23887
                30025129
                90978994-004a-416b-94b3-c99a1102af27
                © 2018

                http://creativecommons.org/licenses/by-nc-nd/4.0/

                History

                Comments

                Comment on this article