June 2020
Volume 61, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2020
Understanding Deep Learning Decision for Glaucoma Detection using 3D Volumes
Author Affiliations & Notes
  • Yasmeen Mourice George
    IBM Research Australia, Melbourne, Victoria, Australia
  • Bhavna J. Antony
    IBM Research Australia, Melbourne, Victoria, Australia
  • Hiroshi Ishikawa
    Department of Ophthalmology, NYU Langone Health, New York, United States
  • Gadi Wollstein
    Department of Ophthalmology, NYU Langone Health, New York, United States
  • Joel S Schuman
    Department of Ophthalmology, NYU Langone Health, New York, United States
    Department of Biomedical Engineering, NYU Tandon School of Engineering, New York, United States
  • Rahil Garnavi
    IBM Research Australia, Melbourne, Victoria, Australia
  • Footnotes
    Commercial Relationships   Yasmeen George, IBM Research Australia (E); Bhavna Antony, IBM Research Australia (E); Hiroshi Ishikawa, Zeiss (P); Gadi Wollstein, Zeiss (P); Joel Schuman, Zeiss (P); Rahil Garnavi, IBM Research Australia (E)
  • Footnotes
    Support  NIH R01EY013178, Unrestricted grant by Research to Prevent Blindness
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 2022. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Yasmeen Mourice George, Bhavna J. Antony, Hiroshi Ishikawa, Gadi Wollstein, Joel S Schuman, Rahil Garnavi; Understanding Deep Learning Decision for Glaucoma Detection using 3D Volumes. Invest. Ophthalmol. Vis. Sci. 2020;61(7):2022.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Gradient class activation maps (grad-CAM) generated by convolutional neural networks (CNN) have qualitatively indicated that these networks are able to identify important regions in OCT scans. Here, we quantitatively analyse these regions to improve our understanding of the CNN decision making process when detecting glaucoma in OCT volumes.

Methods : A total of 1110 OCT (Cirrus HD-OCT, Zeiss, Dublin, Ca) scans from both eyes of 624 subjects (139 healthy and 485 glaucomatous patients (POAG)). An end-to-end 3D-CNN network was trained directly on 3D-volumes for glaucoma detection. Grad-CAM was implemented to highlight structures in the volumes that the network relied on. Grad-CAM heatmaps were generated for 3 different convolutional layers and quantitatively validated by occluding the regions with the highest grad-CAM weights (12.5% of original input volumes) and then evaluating the performance drop. Further, 8-retinal layers segmentation method was used to compute the average heatmap weights for each segmented layer separately, and used to identify the layers that were deemed as important for the task.

Results : The model achieved an AUC of 0.97 for the test set (110 scans). Occlusion resulted in a 40% drop in performance (Fig.1). The RNFL and photoreceptors showed the highest median weights for grad-CAM heatmaps (0.1 and 0.2, respectively). The retinal pigment epithelium (RPE) and photoreceptors showed higher weights in the glaucomatous scans (Fig.2-a). RNFL had wider range of weights in healthy cases versus POAG ones. Analysis of the B-scans showed that central part around the optic disc (# 85-135) had the highest contribution to the network decision and the heatmap weights were much higher in glaucoma cases than healthy ones across all B-scans (Fig.2-b).

Conclusions : The occlusion experiment indicates that the regions identified by the grad-CAMs are in fact pertinent to the glaucoma detection task. The increased emphasis on the photoreceptors in the glaucoma cases may be attributed to the atrophy in the superficial layers which in turn increased the brightness of this structure. This technique can be used to identify new biomarkers learned for other ocular diseases.

This is a 2020 ARVO Annual Meeting abstract.

 

Visualization of grad-CAM highest heatmap weights for glaucoma detection using 3D scans for both enface and B-scan views

Visualization of grad-CAM highest heatmap weights for glaucoma detection using 3D scans for both enface and B-scan views

 

Contribution of different OCT structures for glaucoma detection using 3D-CNN. a) Retinal layers and b) B-scans

Contribution of different OCT structures for glaucoma detection using 3D-CNN. a) Retinal layers and b) B-scans

×
×

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.

×