June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Deep learning-based classification of diabetic retinopathy with or without macular ischemia using optical coherence tomography angiography images
Author Affiliations & Notes
  • Alexandra Miere
    Ophthalmology, Centre Hospitalier Intercommunal de Creteil, Creteil, Île-de-France, France
  • Jean-Baptiste Excoffier
    Kaduceo SAS, France
  • Carlotta Pallonne
    Ophthalmology, Centre Hospitalier Intercommunal de Creteil, Creteil, Île-de-France, France
  • Meryem Filali Ansary
    Ophthalmology, Centre Hospitalier Intercommunal de Creteil, Creteil, Île-de-France, France
  • Samuel Kerr
    Kaduceo SAS, France
  • Matthieu Ortala
    Kaduceo SAS, France
  • Eric Souied
    Ophthalmology, Centre Hospitalier Intercommunal de Creteil, Creteil, Île-de-France, France
  • Footnotes
    Commercial Relationships   Alexandra Miere None; Jean-Baptiste Excoffier None; Carlotta Pallonne None; Meryem Filali Ansary None; Samuel Kerr None; Matthieu Ortala None; Eric Souied None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 196 – F0043. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Alexandra Miere, Jean-Baptiste Excoffier, Carlotta Pallonne, Meryem Filali Ansary, Samuel Kerr, Matthieu Ortala, Eric Souied; Deep learning-based classification of diabetic retinopathy with or without macular ischemia using optical coherence tomography angiography images. Invest. Ophthalmol. Vis. Sci. 2022;63(7):196 – F0043.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To evaluate a deep learning classifier for the automated classification of optical coherence tomography angiography images from diabetic retinopathy (DR) eyes with and without macular ischemia (MI).

Methods : In this study, 241 3x3 mm superficial vascular complex (SVC) OCTA images of DR patients with and without MI, as well as healthy controls were used to train a multi-layer deep convolutional neural network (DenseNet121) to differentiate between healthy versus DR with and without MI. A two-class (DR versus healthy controls) and a three-class classification system (DR without MI, DR with MI, and healthy control) were implemented. In order to evaluate classification performances overall in the dataset, a 5-fold cross-validation method was used. Visualization of the output of the DL classifier on OCTA images was performed using two different methods: Smoothed Saliency Maps and GradCAM++.

Results : The accuracy of the binary classification (DR versus healthy controls) was 90.87%, along with a sensitivity of 88.96% and a precision of 96.48%. The three-class classification (DR with MI, without MI, and controls) showed an accuracy of 85.89%. Healthy controls and DR with MI obtained the highest sensitivity, of 94.25% and 93.98%, respectively.

Conclusions : This study describes the use of a deep learning-based model to automatically classify DR with/without MI on central 3x3mm OCTA images. Thus, this model may be a useful screening tool and help improve the clinical management of DR patients.

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

 

The area under the Receiver Operating Characteristic (AUC-ROC) and Precision-Recall (AUC-PR) Curves. For the binary classification, diabetic retinopathy versus healthy controls, the AUC-ROC Score is equal to 95.01% (A), while the AUC-PR is equal to 96.27%(B). When classifying DR with MI, without MI, and healthy controls, the highest AUC-ROC (C) is obtained by DR with MI (97.89%). D.The AUC-PR Score was also highest for DR with MI (95.96%).

The area under the Receiver Operating Characteristic (AUC-ROC) and Precision-Recall (AUC-PR) Curves. For the binary classification, diabetic retinopathy versus healthy controls, the AUC-ROC Score is equal to 95.01% (A), while the AUC-PR is equal to 96.27%(B). When classifying DR with MI, without MI, and healthy controls, the highest AUC-ROC (C) is obtained by DR with MI (97.89%). D.The AUC-PR Score was also highest for DR with MI (95.96%).

×
×

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.

×