Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
TRANSFER LEARNING FROM THE DOMAIN OF DIABETIC RETINOPATHY TO THE AUTOMATHIC DETECTION OF AGE-RELATED MACULAR DEGENERATION
Author Affiliations & Notes
  • Sara Crespo Millas
    Hospital Clinico Universitario de Valladolid, Valladolid, Castilla y León, Spain
  • Roberto Romero-Oraa
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • María Herrero
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • Roberto Hornero
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • Maria Isabel Lopez Galvez
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • Salvatore Di Lauro
    Hospital Clinico Universitario de Valladolid, Valladolid, Castilla y León, Spain
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • Maria Garcia
    Universidad de Valladolid, Valladolid, Castilla y León, Spain
  • Footnotes
    Commercial Relationships   Sara Crespo Millas None; Roberto Romero-Oraa None; María Herrero None; Roberto Hornero None; Maria Isabel Lopez Galvez None; Salvatore Di Lauro None; Maria Garcia None
  • Footnotes
    Support  none
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 3744. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Sara Crespo Millas, Roberto Romero-Oraa, María Herrero, Roberto Hornero, Maria Isabel Lopez Galvez, Salvatore Di Lauro, Maria Garcia; TRANSFER LEARNING FROM THE DOMAIN OF DIABETIC RETINOPATHY TO THE AUTOMATHIC DETECTION OF AGE-RELATED MACULAR DEGENERATION. Invest. Ophthalmol. Vis. Sci. 2024;65(7):3744.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To apply transfer learning from the domain of diabetic retinopathy (DR) to aid in the detection of AMD

Methods : The proposed model was based on the ResNet-RS architecture. Pre-training aimed at DR diagnosis was conducted using the Kaggle database (EyePACS) released for DR research, consisting of more than 80,000 fundus images but after eliminating those of por quality 52,973 images were finally used and divided into a training set of 52,073 images (13,099 with DR and 38,974 with no DR) and a validation set of 900 images (200 with DR and 700 with no DR).
A preprocessing stage for input normalization was introduced and after a deep CNN backbone was linked to a set of fully-connected layers.
Then, fine-tunning was performed using other public data set, the ADAM dataset that contains 1,200 fundus images provided by the Zhongshan Ophthalmic Center of the Sun Yat-sen University (China). Only a small dataset of 400 images from ADAM was considered in this work.
We carried out 3 experiments with different number of images , N = 50, 100 and 400 images, respectively, as the training set of the fine-tunning stage.

Results : As the main result, our method showed a much faster convergence than the corresponding models pre- trained on ImageNet. When analyzing the experiments with N=50, we could observe how our proposal surpasses the traditional approach in every metric except for SP. In particular, the value of AUC=0.88 is notably higher than the AUC=0.78. As for the experiments with N=100, the conclusion seems to be similar, but the computed metrics are closer among them.
When N=400, however, the obtained results are on the same line. That is, our approach does not imply better performance for this case. These comparisons show that the proposed approach is especially useful when scarce data in the destination domain is available.

Conclusions : The present work revealed that an appropriate source domain when applying transfer learning helps improve the model effectiveness and efficiency. In contrast to ImageNet pre-training, the use of a pre-trained network aimed at DR diagnosis allowed us to achieve a much faster convergence for AMD detection. Additionally, the proposed approach showed a higher performance when a reduced subset of images was available for fine-tunning purposes.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

×
×

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.

×