June 2020
Volume 61, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2020
AUTOMATED QUALITY ASSESSMENT OF OPTIC DISC PHOTOGRAPHS WITH DEEP LEARNING
Author Affiliations & Notes
  • Diana Salazar
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Esteban Morales
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Alon Oyler-Yaniv
    QCBio Collaboratory, UCLA, Los Angeles, California, United States
    Chemistry & Biochemistry, UCLA, Los Angeles, California, United States
  • Agustina de Gainza
    Jules Stein Eye Institute, Los Angeles, California, United States
  • vahid mohammadzadeh
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Golnoush Mahmoudi
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Kouros Nouri-Mahdavi
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Joseph Caprioli
    Jules Stein Eye Institute, Los Angeles, California, United States
  • Footnotes
    Commercial Relationships   Diana Salazar, Payden Glaucoma Research Fund (F), RPB (F), Simms-Mann Family foundation (F); Esteban Morales, None; Alon Oyler-Yaniv, None; Agustina de Gainza, None; vahid mohammadzadeh, None; Golnoush Mahmoudi, None; Kouros Nouri-Mahdavi, None; Joseph Caprioli, None
  • Footnotes
    Support  RPB, Simms/Mann Family Foundation, Payden Glaucoma Research Fund
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 4534. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Diana Salazar, Esteban Morales, Alon Oyler-Yaniv, Agustina de Gainza, vahid mohammadzadeh, Golnoush Mahmoudi, Kouros Nouri-Mahdavi, Joseph Caprioli; AUTOMATED QUALITY ASSESSMENT OF OPTIC DISC PHOTOGRAPHS WITH DEEP LEARNING. Invest. Ophthalmol. Vis. Sci. 2020;61(7):4534.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To generate and test the performance of a deep convolutional neural network (CNN) with transfer learning for automated assessment of optic disc photograph quality.

Methods : From a large database at a glaucoma tertiary center, the quality of 1741 randomly selected optic disc photos were manually assessed by two clinicians independently. Three levels of quality based on reference images were defined: good, acceptable and poor. This was a heterogeneous database that consisted of both digitized and digital photographs. Preprocessing of each labeled image was performed with a 2400×2400-pixel crop around the optic disc and resizing to 128×128 pixels. Next, we applied seven different image transformations for data augmentation. An optimal three-layer CNN was developed based on a fine-tuned pre-trained VGG-16 network[1]. After image preprocessing, images were split into 80% as a training dataset, while 20% were used as validation dataset. Accuracy, recall, F1-score and a normalized confusion matrix were used to asses model performance. A separate test set of 100 optic disc photographs were used for external validation.


[1] Simonyan, K. and Zisserman, A. (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. The 3rd International Conference on Learning Representations (ICLR2015).

Results : From the augmented dataset of 13968 images, 7040 (50.5%) were classified as good, 5728 (41.1%) as acceptable, and 1160 (8.4%) as bad quality. The pretrained model showed a weighted accuracy of 91% in the validation set for correct quality classification (Table 1). Per-classes sensitivity was 92% for good quality, 93% for acceptable quality and 81% for poor quality (Figure 1). In the external test set the weighted accuracy was 80% with a weighted recall of 79%.

Conclusions : We propose a CNN with good performance for automatic assessment of the quality of optic disc photographs. This is clinically relevant since evaluation of optic disc photographs for detection of glaucoma is impacted by its quality level, therefore, implementation of an automatic quality assessment could improve the acquisition of these images and ultimately aid in the diagnosis of the disease.

This is a 2020 ARVO Annual Meeting abstract.

 

Classification report per-class, model average and model accuracy.

Classification report per-class, model average and model accuracy.

 

Confusion matrix for performance of the CNN for automatic detection of disc photograph quality. Diagonal squares show the correct proportion of classified images per -class (sensitivity).

Confusion matrix for performance of the CNN for automatic detection of disc photograph quality. Diagonal squares show the correct proportion of classified images per -class (sensitivity).

×
×

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.

×