August 2019
Volume 60, Issue 11
Open Access
ARVO Imaging in the Eye Conference Abstract  |   August 2019
Identification of clinically relevant glaucoma biomarkers on fundus images using deep learning
Author Affiliations & Notes
  • Mohammad Norouzifard
    School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand
  • Ali Nemati
    School of Engineering and Technology, University of Washington, Tacoma, Washington, United States
  • Reinhard Klette
    EEE, Auckland University of Technology , Auckland, New Zealand
  • Hamid GholamHossieni
    School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand
  • Kouros Nouri-Mahdavi
    Department of Ophthalmology, University of California Los Angeles, Los Angeles, California, United States
  • Siamak Yousefi
    Department of Ophthalmology, University of Tennessee Health Science Center, Tennessee, United States
  • Footnotes
    Commercial Relationships   Mohammad Norouzifard, None; Ali Nemati, None; Reinhard Klette, None; Hamid GholamHossieni, None; Kouros Nouri-Mahdavi, None; Siamak Yousefi, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science August 2019, Vol.60, PB090. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Mohammad Norouzifard, Ali Nemati, Reinhard Klette, Hamid GholamHossieni, Kouros Nouri-Mahdavi, Siamak Yousefi; Identification of clinically relevant glaucoma biomarkers on fundus images using deep learning. Invest. Ophthalmol. Vis. Sci. 2019;60(11):PB090.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning framework that can automatically identify clinically relevant features on glaucoma fundus images.

Methods : Fundus photographs from 267 normal eyes and 160 eyes with glaucoma were included. We developed a deep learning model based on the pre-trained NASNet and used heat map technique to assess parts of the fundus image that were driving the classification, thus allowing localization of clinically relevant objects on retinal fundus images. After training the model, all 427 fundus images were used as input to the proposed model (based on a deep pre-trained classifier) consisting of the region of interest on fundus photographs. The clinical diagnosis labels of fundus images were validated by a glaucoma specialist and the outcome of deep learning was assessed by experts to assure clinical relevance.

Results : The accuracy of the method in discriminating normal eyes from eyes with glaucoma was 92%. The validation accuracy on an independent dataset of 455 images was 90%. Among fundus images that had been classified to glaucoma group, we observed that deep learning had identified significant features mostly in the superior/inferior peripapillary regions, within the optic nerve head, as well as in their pattern of large blood vessel structure.

Conclusions : We developed a deep learning model based on pre-trained parameters that was able to detect clinically relevant glaucoma features from fundus images with high accuracy. This approach could be useful in glaucoma clinics as well as in general practice settings as an assistive tool for screening glaucoma in the absence of glaucoma clinicians. Validation of our findings in an independent cohort with larger number of fundus images is required.

This abstract was presented at the 2019 ARVO Imaging in the Eye Conference, held in Vancouver, Canada, April 26-27, 2019.

 

Figure 1. The utility of optic nerve head structure region in detecting glaucoma. Left: Optic nerve head structures identified as a significant feature for detection of glaucoma based on the proposed deep learning model, Right: A sample input fundus image overlaid on the optic nerve head structure in the left panel.

Figure 1. The utility of optic nerve head structure region in detecting glaucoma. Left: Optic nerve head structures identified as a significant feature for detection of glaucoma based on the proposed deep learning model, Right: A sample input fundus image overlaid on the optic nerve head structure in the left panel.

 

Figure 2. The utility of blood vessel structure feature in detecting glaucoma. Left: Blood vessels structure identified as a significant feature for detection of glaucoma. Right: The input fundus image overlaid on the blood vessel structure in the left panel.

Figure 2. The utility of blood vessel structure feature in detecting glaucoma. Left: Blood vessels structure identified as a significant feature for detection of glaucoma. Right: The input fundus image overlaid on the blood vessel structure in the left panel.

×
×

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.

×