Investigative Ophthalmology & Visual Science Cover Image for Volume 61, Issue 9
July 2020
Volume 61, Issue 9
Free
ARVO Imaging in the Eye Conference Abstract  |   July 2020
Deep learning algorithm validation for diabetic retinopathy lecture in a diabetes mellitus population.
Author Affiliations & Notes
  • Maria Esther Santos Blanco
    Hospital Sant Joan reus, Cambrils, Spain
  • Pere Romero Aroca
    Hospital Sant Joan reus, Cambrils, Spain
  • Aida Valls
    Hospital Sant Joan reus, Cambrils, Spain
  • Antonio Moreno
    Hospital Sant Joan reus, Cambrils, Spain
  • Raquel Verges
    Hospital Sant Joan reus, Cambrils, Spain
  • Naiara Relaño
    Hospital Sant Joan reus, Cambrils, Spain
  • Raul Navarro
    Hospital Sant Joan reus, Cambrils, Spain
  • Marc Baget
    Hospital Sant Joan reus, Cambrils, Spain
  • Ramon Sagarra
    Urv, Spain
  • Joan Vendrell
    Urv, Spain
  • Josep Basora
    Urv, Spain
  • Footnotes
    Commercial Relationships   Maria Esther Santos Blanco, None; Pere Romero Aroca, None; Aida Valls, None; Antonio Moreno, None; Raquel Verges, None; Naiara Relaño, None; Raul Navarro, None; Marc Baget, None; Ramon Sagarra, None; Joan Vendrell, None; Josep Basora, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2020, Vol.61, PB001. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Maria Esther Santos Blanco, Pere Romero Aroca, Aida Valls, Antonio Moreno, Raquel Verges, Naiara Relaño, Raul Navarro, Marc Baget, Ramon Sagarra, Joan Vendrell, Josep Basora; Deep learning algorithm validation for diabetic retinopathy lecture in a diabetes mellitus population.. Invest. Ophthalmol. Vis. Sci. 2020;61(9):PB001.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Interpretability is the key factor in automatic classification in medical diagnosis design. The deep Learning (DL) methodology, and its subfield Convolutional neural networks (CNN), takes in an input image, identifies some aspects in the picture, wich are important to define it, and using parametric models classificate and differenciate it from others . The novelty of this desing from the previous is its ability to learn theese filters with the experience.
Diabetic Retinopathy (DR) is a leading disabling chronic disease and one of the main causes of blindness and visual impairment in developed countries. It is reported that a 90% of the cases DR can be prevented through early detection and treatment. It is developed an automated learning algorithm model for the DR to assist physiscian in DR screening.

Methods : We validated our algorithm of automated learning diabetic retinopathy (ALDR-algorithm), made by CNN for the imaging interpretation. It was tried on 56.088 database images, and It was tested in 1.748 retinographies from Messidor-2 database. ALDR-algorithm was also tried on 38.319 images from our own population and it was tested in 5000 of these retinographies. The screening was made by a single retinography from both eyes acording EURODIAB recomendations. To test the algorithm concordance with the experts, the images were read by our ALDR-ALGORITHM and by four masked retinologists. Retinopathy was graded according to MESSIDOR in four levels. The agreement, sensitivity and specificity between both methods was determined.

Results : The agreement between both models was a QWK index of 0,918.
The ALDR-algorithm statistical results of the images with any DR were: sensitivity =0.985, specificity =0.853, positive predictive value =0.980, negative predictive value =0.980, false positive rate or error type I = 0,147, false negative rate or error type II=0,015.
The results for referable DR images (moderate, severe or proliferative DR) were: sensitivity =0.991, specificity =0,850, positive predictive value =0,987, negative predictive value =0,888, false positive rate or error type I = 0,150, false negative rate or error type II=0,009.

Conclusions : It has been developed an ALDR-algorithm able to read retinographies of diabetic patients with a great agreement, and it would be useful in DR screening.

This is a 2020 Imaging in the Eye Conference abstract.

×
×

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.

×