June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Glaucoma detection based on a deep learning approach
Author Affiliations & Notes
  • Bo-I Kuo
    Ophthalmology, Taipei City Hospital, Taipei, Taiwan
  • I-Jong Wang
    Ophthalmology, National Taiwan University Hospital, Taiwan
  • Wen-Yi Chang
    National Center for High-Performance Computing, National Applied Research Laboratories, Taiwan
  • Footnotes
    Commercial Relationships   Bo-I Kuo, None; I-Jong Wang, None; Wen-Yi Chang, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 1624. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Bo-I Kuo, I-Jong Wang, Wen-Yi Chang; Glaucoma detection based on a deep learning approach. Invest. Ophthalmol. Vis. Sci. 2020;61(7):1624.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop a deep learning algorithm to detect glaucoma based on fundoscopy and try to validate it with visualization methods

Methods : We retrospectively collected color fundoscopic pictures from National Taiwan University Hospital. The inclusion criteria of the glaucoma group were defined as first-diagnosed POAG and PACG patients. Secondary glaucoma was excluded. The control group consisted of ocular hypertensive patients. A total of 67 patients and 56 patients were in glaucoma and control group, respectively. Besides, we also included 67 healthy color fundoscopic photos from the public dataset for training. After data augmentation, we adopted the modified Oxford VGG16 model for learning under 10-fold cross-validation. The automatic optic rim delineation was incorporated into the algorithm for increasing the accuracy of the model. The sensitivity, specificity, and area under receiver operating characteristic curve (AUROC) were calculated. For better explainability, we displayed the pixel-wise discriminative features and class-discriminative heat map of diopter images for visualization.

Results : A total of 207 glaucoma pictures and 200 normal pictures were collected from National Taiwan University Hospital and 67 normal pictures from the public database. After training for 1000 epoch, the convergence of accuracy and loss for training and validation datasets which showed no overfitting. The sensitivity, the specificity, and the AUROC were 0.90, 0.895 and 0.944, respectively. The pixel-wise discriminative features visualized by the guided backpropagation and the heat map of the prediction layer by the guided grad-CAM all showed the deep learning model focused on the optic nerve, which was corresponding to the diagnostic clues of the ophthalmologists. T

Conclusions : In this study, the CNN model had fair accuracy for glaucoma screening based on the color funduscopic images. The visualization mentioned in this study revealed the model focus on the proper region for diagnosis and made clinical explainability of deep learning more acceptable.

This is a 2020 ARVO Annual Meeting abstract.

 

The example of visualization of the CNN model. The left image was the original color fundoscopic photo. The middle one was the pixel-wise discriminative features that outlined the optic disc and vessels. The right one was the heat map method showed the model emphasized the optic disc region while making a classification.

The example of visualization of the CNN model. The left image was the original color fundoscopic photo. The middle one was the pixel-wise discriminative features that outlined the optic disc and vessels. The right one was the heat map method showed the model emphasized the optic disc region while making a classification.

×
×

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.

×