June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Automatic Identification of Ancillary Features of Diabetic Macular Edema in Optical Coherence Tomography Using Deep Learning
Author Affiliations & Notes
  • Samantha Paul
    Department of Ophthalmology, University Hospitals, Cleveland, Ohio, United States
  • Ellie Zhou
    Department of Ophthalmology, University Hospitals, Cleveland, Ohio, United States
  • Ankur Mehra
    Department of Ophthalmology, University Hospitals, Cleveland, Ohio, United States
  • Ian Pan
    Department of Radiology, Brigham and Women's Hospital, Boston, Massachusetts, United States
  • Warren Sobol
    Department of Ophthalmology, University Hospitals, Cleveland, Ohio, United States
    Department of Ophthalmology, Case Western Reserve University, Cleveland, Ohio, United States
  • Footnotes
    Commercial Relationships   Samantha Paul None; Ellie Zhou None; Ankur Mehra None; Ian Pan MD.ai, Code C (Consultant/Contractor), Centaur Labs, Code C (Consultant/Contractor), Diagnosticos da America (Dasa), Code C (Consultant/Contractor); Warren Sobol None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 180 – F0027. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Samantha Paul, Ellie Zhou, Ankur Mehra, Ian Pan, Warren Sobol; Automatic Identification of Ancillary Features of Diabetic Macular Edema in Optical Coherence Tomography Using Deep Learning. Invest. Ophthalmol. Vis. Sci. 2022;63(7):180 – F0027.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. DME is frequently accompanied by other retinal abnormalities on two-dimensional optical coherence tomography (2D OCT). We trained and tested a CNN to identify various retinal features on 2D OCT images from patients with DME.

Methods : 1,896 2D OCT images through the fovea from 93 patients with DME were randomly sampled from a publicly available dataset of 108,316 2D OCT images. Each image was labeled with the following 5 features: hyperreflective foci, ellipzoid zone disruption, subretinal fluid, vitreoretinal interface abnormalities, and distortion of the foveal contour. An EfficientNet-B3 CNN was trained to identify these features. The training process was repeated 3 times with separate random seeds, resulting in an ensemble of 3 CNNs. Inference was subsequently performed on an independent test set of 250 B-scans from 167 patients with DME by taking the average prediction scores across the 3 CNNs. The area under the receiver operating characteristic curve (AUC) was calculated for each feature. The 95% confidence interval (95% CI) was calculated using the bootstrap method.

Results : The distribution of the 5 features in the training set was: hyperreflective foci (37.1%), ellipsoid zone disruption (23.8%), subretinal fluid (5.2%), vitreoretinal inferface abnormalities (62.3%), and distortion of the foveal contour (50.9%). Among the 5 features, performance (AUC, 95% CI) was highest for subretinal fluid, 0.947 (0.914, 0.974); hyperreflective foci, 0.918 (0.877, 0.954); and distortion of the foveal contour 0.887, (0.802, 0.957). AUCs for ellipzoid zone disruption and vitreoretinal inferface abnormalities were 0.757 (0.693, 0.819) and 0.738 (0.643, 0.824), respectively. Figures 1 and 2 depict class activation maps illustrating which areas of the image contributed most to the predicted features.

Conclusions : CNNs were effective in identifying ancillary DME features in 2D OCT images, particularly hyperreflective foci, subretinal fluid, and distortion of the foveal contour. This can allow for more nuanced assessment of DME severity and prognosis in settings where retina subspecialists are not readily available.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

Figure 1. Example class activation map for subretinal fluid.

Figure 1. Example class activation map for subretinal fluid.

 

Figure 2. Example class activation map for hyperreflective foci.

Figure 2. Example class activation map for hyperreflective foci.

×
×

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.

×