June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Robust classification of eye disease from fundus images using deep learning on multiple public datasets
Author Affiliations & Notes
  • Jovi Wong
    University of British Columbia, Vancouver, British Columbia, Canada
  • Prashant Pandey
    University of British Columbia, Vancouver, British Columbia, Canada
  • Footnotes
    Commercial Relationships   Jovi Wong, None; Prashant Pandey, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 2014. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jovi Wong, Prashant Pandey; Robust classification of eye disease from fundus images using deep learning on multiple public datasets. Invest. Ophthalmol. Vis. Sci. 2020;61(7):2014.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Glaucoma, diabetic retinopathy (DR) and age-related macular degeneration (AMD) are leading causes of blindness. Computer-assisted automated screening of colour fundus photographs could be a method by which early diagnosis and treatment to prevent blindness can be achieved on a population level. While previous studies have trained convolutional neural networks to detect individual eye diseases, a fit-for-purpose classifier must be capable of screening for multiple diseases. To address this, we trained a network to classify colour fundus photographs between healthy, glaucoma, DR and AMD by leveraging several existing public datasets.

Methods : We amalgamated 10 public datasets (DiaretDB, Drishti-GS, DRIVE, HRF, IDRiD, 39Kaggle, MESSIDOR, ORIGA-light, REFUGE, STARE) to create a multi-disease fundus dataset containing 4205 images, with approximately 58%, 9%, 32%, 1% images labeled as healthy, glaucoma, DR and AMD respectively. To train our classifier, we fine-tuned all layers of an ‘Inception v3’ neural network model, pretrained on ImageNet, on 80% of the dataset using data augmentation (horizontal mirroring, random scaling and cropping) and weighted cross-entropy loss to tackle the class imbalance.

Results : Validating on the remaining 20% of the images, we found a mean area under the curve (AUC) of 95.6% (healthy: 92.7%, glaucoma: 93.4%, DR: 96.5%, AMD: 99.5%). Our model stabilized within 20 epochs, and required approximately 30 minutes to train on a single graphics processing unit (GPU).

Conclusions : We designed an accurate eye disease classification model for healthy, glaucoma, DR and AMD fundus images, despite the modest dataset size. To our knowledge, this is the first reported multi-disease classifier for colour fundus images. We also created a user-friendly pilot interface for clinicians to access the classifier, and test their own images for research purposes (link provided on poster).

This is a 2020 ARVO Annual Meeting abstract.

 

Figure 1. Representative colour fundus images classified as healthy, glaucoma, diabetic retinopathy and age-related macular degeneration, taken from 10 public datasets, after data augmentation and pixel intensity normalization.

Figure 1. Representative colour fundus images classified as healthy, glaucoma, diabetic retinopathy and age-related macular degeneration, taken from 10 public datasets, after data augmentation and pixel intensity normalization.

 

Figure 2. Receiver Operating Characteristic curve for our network, when classifying between healthy and diseased (glaucoma, DR, AMD) colour fundus images, with an area under the curve of 92.7%.

Figure 2. Receiver Operating Characteristic curve for our network, when classifying between healthy and diseased (glaucoma, DR, AMD) colour fundus images, with an area under the curve of 92.7%.

×
×

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.

×