June 2020
Volume 61, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2020
A Deep Learning Model to Detect Center-Involved Diabetic Macular Edema from Fundus Images
Author Affiliations & Notes
  • Xinle Liu
    Google Health, Google LLC, Mountain View, California, United States
  • Preeti Singh
    Google Health, Google LLC, Mountain View, California, United States
  • Paisan Ruamviboonsuk
    Department of Ophthalmology, Rajavithi Hospital, Bangkok, Thailand
  • Peranut Chotcomwongse
    Department of Ophthalmology, Rajavithi Hospital, Bangkok, Thailand
  • Reena Chopra
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS, London, United Kingdom
  • Pearse A. Keane
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS, London, United Kingdom
  • Josef Christian Huemer
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS, London, United Kingdom
  • Jorge Cuadros
    EyePACS LLC, Santa Cruz, California, United States
  • Avinash V. Varadarajan
    Google Health, Google LLC, Mountain View, California, United States
  • Naama Hammel
    Google Health, Google LLC, Mountain View, California, United States
  • Siva Balasubramanian
    Work done at Google Health via Advanced Clinical, Deerfield, Illinois, United States
  • Tayyeba K. Ali
    Work done at Google Health via Advanced Clinical, Deerfield, Illinois, United States
  • Pinal Bavishi
    Google Health, Google LLC, Mountain View, California, United States
  • Footnotes
    Commercial Relationships   Xinle Liu, Google LLC (E); Preeti Singh, Google LLC (E); Paisan Ruamviboonsuk, None; Peranut Chotcomwongse, None; Reena Chopra, None; Pearse Keane, Google LLC (C); Josef Huemer, None; Jorge Cuadros, EyePACS LLC (E); Avinash Varadarajan, Google LLC (E); Naama Hammel, Google LLC (E); Siva Balasubramanian, Google LLC (C); Tayyeba Ali, Google LLC (C); Pinal Bavishi, Google LLC (E)
  • Footnotes
    Support  Google LLC
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 1619. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Xinle Liu, Preeti Singh, Paisan Ruamviboonsuk, Peranut Chotcomwongse, Reena Chopra, Pearse A. Keane, Josef Christian Huemer, Jorge Cuadros, Avinash V. Varadarajan, Naama Hammel, Siva Balasubramanian, Tayyeba K. Ali, Pinal Bavishi; A Deep Learning Model to Detect Center-Involved Diabetic Macular Edema from Fundus Images. Invest. Ophthalmol. Vis. Sci. 2020;61(7):1619.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning (DL) model to detect center-involved diabetic macular edema (ci-DME) from color fundus photographs (CFPs), assess its performance on multiple datasets and compare it with human graders, against a ground truth obtained from optical coherence tomography (OCT) scans.

Methods : We developed a DL model to detect ci-DME using a retrospective development dataset of 7341 CFPs from 4682 patients as input and the corresponding ci-DME grades based on retinal thicknesses from OCT macular scans as labels. Three validation datasets from three different countries were assessed by human graders for the presence of ci-DME, using the proxy criteria of presence of hard exudates within one optic disc diameter of the center of the macula (Thailand: 1033 CFPs, graded by 3 retina specialists; US: 1976 CFPs, graded by 1 certified grader; and UK: 1602 CFPs, graded by 1 certified grader). ci-DME from OCT was defined as eyes with ≥ 250 μm center point thickness in the Thailand dataset and ≥ 300 μm central subfield thickness in the US and UK datasets. We evaluated the model on these datasets and compared its performance to human graders, using ci-DME ground truth derived from OCT.

Results : As shown in Figure 1, on Thailand, US, and UK validation sets, the model achieved area under the curves (AUCs) of 0.880 (95% confidence interval (CI): [0.86,0.90]), 0.875 (95% CI: [0.83,0.92]) and 0.819 (95% CI: [0.78,0.85]) respectively. When matched with the sensitivities of approximately 85%, 40% and 93% with corresponding specificities of 45%, 94% and 32% of human graders, the model had specificities of 73%, 97% and 44% respectively (p < 0.01 for each comparison).

Conclusions : Our DL model achieved good performance in detecting ci-DME from CFPs in three validation sets from three different countries, with higher specificities when matching the sensitivities of human graders. Such a model could potentially be of clinical value in reducing both false positive referrals and false negative diagnoses for ci-DME in DR screening programs worldwide.

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1: Receiver operating characteristics (ROC) curves for the ci-DME model evaluated on Thailand, US and UK validation datasets, together with the AUCs and graders' performance.

Figure 1: Receiver operating characteristics (ROC) curves for the ci-DME model evaluated on Thailand, US and UK validation datasets, together with the AUCs and graders' performance.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×