July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
Automated cone identification in adaptive optics retinal images of Choroideremia using a convolutional neural network
Author Affiliations & Notes
  • Jessica Ijams Wolfing Morgan
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
    Center for Advanced Retinal and Ocular Therapeutics, Ophthalmology, Philadelphia, Pennsylvania, United States
  • Min Chen
    Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
  • Grace Vergilio
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
  • Andrew M. Huang
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
  • Jean Bennett
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
    Center for Advanced Retinal and Ocular Therapeutics, Ophthalmology, Philadelphia, Pennsylvania, United States
  • Albert M. Maguire
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
    Center for Advanced Retinal and Ocular Therapeutics, Ophthalmology, Philadelphia, Pennsylvania, United States
  • Tomas S Aleman
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
    Center for Advanced Retinal and Ocular Therapeutics, Ophthalmology, Philadelphia, Pennsylvania, United States
  • Robert F Cooper
    Scheie Eye Institute, Ophthalmology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
    Psychology, University of Pennsylvania, Philadelphia, Pennsylvania, United States
  • Footnotes
    Commercial Relationships   Jessica Morgan, AGTC (F), US Patent 8226236 (P); Min Chen, None; Grace Vergilio, None; Andrew Huang, None; Jean Bennett, Biogen (F), Gensight Biologics (S), Limelight (F), Spark Therapeutics (S), Spark Therapeutics (P); Albert Maguire, Spark Therapeutics (F); Tomas Aleman, None; Robert Cooper, Four Pi Innovations (P), Medical College of Wisconsin (C)
  • Footnotes
    Support  NIH R01EY028601, NIH U01EY025477, NIH P30EY001583, NEI K12EY015398, Research to Prevent Blindness, Foundation Fighting Blindness, the F. M. Kirby Foundation, and the Paul and Evanina Mackall Foundation Trust.
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1431. doi:https://doi.org/
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jessica Ijams Wolfing Morgan, Min Chen, Grace Vergilio, Andrew M. Huang, Jean Bennett, Albert M. Maguire, Tomas S Aleman, Robert F Cooper; Automated cone identification in adaptive optics retinal images of Choroideremia using a convolutional neural network. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1431. doi: https://doi.org/.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Adaptive optics (AO) retinal imaging has enabled noninvasive observation and quantification of the photoreceptor mosaic both in health and disease. We have previously shown that the reliability of manual cone identifications is reduced in patients with retinal disease compared to normal sighted controls. Thus, there remains a need for accurate, automated cone identification in AO images of retinal disease. Here, we assess the use of a convolutional neural network (CNN) for automatically detecting cone locations in AO images from patients with Choroideremia (CHM), an X-linked retinal degeneration.

Methods : Split-detection AO image sequences of the photoreceptor mosaic from 17 CHM patients were acquired at retinal locations surrounding the fovea and along all four meridians using an AO scanning light ophthalmoscope. Images were montaged, regions of interest (ROIs) were cropped, and cones were manually identified in each ROI using custom software. Cones in ROIs were also identified automatically using an open source CNN pre-trained on a normative population (‘normal-trained’) (Cunefare et al, Scientific Reports, 2017). True positive and false positive rates for cone identifications were determined and Dice’s coefficient was calculated for each ROI using the manual identifications as ground truth. Using a leave-one-subject-out approach, the CNN was then retrained and validated with the CHM images and manual identifications (‘CHM-trained’). Again, true positive, false positive, and Dice’s coefficient were found for each ROI in comparison to the manual identifications.

Results : The CHM-trained CNN cone identifications had a higher mean Dice coefficient than the normal-trained CNN (mean±stdev, CHM-trained: 0.821±0.100; normal-trained: 0.711±0.214). The mean true positive rate was higher for the CHM-trained CNN identifications (0.884±0.141; normal-trained: 0.642±0.260). However, the mean false discovery rate was also higher (CHM-trained: 0.201±0.128; normal-trained: 0.082± 0.075), particularly at higher eccentricities (>0.7mm) where rods were visible.

Conclusions : CNNs hold promise for automated detection of cone locations within AO images. However, CNN performance is tied closely to its training data, and performs best when operating on images in a similar domain. Our results also suggest that CNN performance will improve by training the network to consider retinal eccentricity.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

×
×

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.

×