July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
Automated Analysis of In Vivo Confocal Microscopy Corneal Images Using Deep Learning
Author Affiliations & Notes
  • Jonathan D Oakley
    Voxeleron LLC, Pleasanton, California, United States
  • Daniel B Russakoff
    Voxeleron LLC, Pleasanton, California, United States
  • Rachel Weinberg
    Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
  • Megan McCarron
    Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
  • Samuel Brill
    Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
  • Stuti Misra
    Department of Ophthalmology, The University of Auckland, Auckland, New Zealand
  • Charles N McGhee
    Department of Ophthalmology, The University of Auckland, Auckland, New Zealand
  • Joseph Mankowski
    Department of Molecular and Comparative Pathobiology, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
  • Footnotes
    Commercial Relationships   Jonathan Oakley, Voxeleron LLC (E); Daniel Russakoff, Voxeleron LLC (E); Rachel Weinberg, None; Megan McCarron, None; Samuel Brill, None; Stuti Misra, None; Charles McGhee, None; Joseph Mankowski, None
  • Footnotes
    Support  NIH Grant R01NS097221, Blaustein Pain Research Fund
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 1799. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Jonathan D Oakley, Daniel B Russakoff, Rachel Weinberg, Megan McCarron, Samuel Brill, Stuti Misra, Charles N McGhee, Joseph Mankowski; Automated Analysis of In Vivo Confocal Microscopy Corneal Images Using Deep Learning. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1799.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : In vivo confocal microscopy (IVCM) allows for non-invasive, cellular level imaging of the cornea. This facilitates detailed corneal nerve assessment offering objective biomarkers that have clinical relevance in a number of diseases. With variability in IVCM image quality, automated algorithms remain less accurate than expert assessment by manual tracing. In this study, we address such deficiencies using a novel deep learning approach in automated assessment of variant quality images.

Methods : IVCM images were acquired from 29 macaques using the Heidelberg HRT-3 and Rostock Cornea Module. Macaque corneal images were of lower quality than human images because of the smaller radius of curvature and the need to manually position animals for confocal scanning under general anesthesia. To maintain a strong correlation to expert readers we replaced our previously reported detection mechanism with a deep convolutional neural network (CNN), trained to recognize pixels of nerves or background (Fig. 1). The same pre- and post-processing components were kept for their effective noise reduction and creation of continuous nerve images, respectively. For training, 40 images were used. 46 separate images were traced by 3 experts using ImageJ (NeuronJ plugin) and used for testing. Total nerve density was compared across readers.

Results : Algorithm agreement was good to excellent relative to all readers (Pearson coefficients of 0.80, 0.86, 0.89), similar to that between readers (0.83, 0.86, 0.91). Bland-Altman plots demonstrated inter-observer reproducibility showing tight limits of agreement (LOA) across the dynamic range of densities (Fig. 2). This is a marked improvement over our previous automated analysis method.

Conclusions : Deep learning based approaches to object recognition and analysis are state of the art. Book-ended by effective pre- and post-processing, we have advanced our previous automated analysis of IVCM images. With good accuracy and sensitivity in challenging data, this approach also facilitates the evaluation of higher order morphological features of nerves such as tortuosity and branching, adding additional value to IVCM analyses.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

 

Fig. 1. Example input image and output prediction class probabilities from the CNN.

Fig. 1. Example input image and output prediction class probabilities from the CNN.

 

Fig. 2. Bland Altman (LOA are 0.0051 and -0.0033) and scatter plot of total nerve fiber density (algorithm vs average reader).

Fig. 2. Bland Altman (LOA are 0.0051 and -0.0033) and scatter plot of total nerve fiber density (algorithm vs average reader).

×
×

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.

×