July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
Automated detection of corneal nerves using deep learning
Author Affiliations & Notes
  • Hong Qi
    Ophthalmology department, Peking University Third Hospital, Beijing, China
    Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Beijing, China
  • Davide Borroni
    Department of Ophthalmology, Riga Stradins University, Riga, Latvia
  • Rongjun Liu
    Ophthalmology department, Peking University Third Hospital, Beijing, China
    Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Beijing, China
  • Bryan Williams
    Department of Eye and Vision Science, University of Liverpool, Liverpool, United Kingdom
  • Mike Beech
    St. Paul’s Eye Unit, Royal Liverpool University Hospital, Liverpool, United Kingdom
  • Yitian Zhao
    Cixi Institute of Biomedical Engineering, Ningbo Institute of Industrial Technology, Chinese Academy of Sciences, Ningbo, China
    Department of Eye and Vision Science, University of Liverpool, Liverpool, United Kingdom
  • Baikai Ma
    Ophthalmology department, Peking University Third Hospital, Beijing, China
    Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Beijing, China
  • Vito Romano
    St. Paul’s Eye Unit, Royal Liverpool University Hospital, Liverpool, United Kingdom
  • Uazman Alam
    Institute of Ageing & Chronic Disease, Clinical Sciences Centre, University Hospital Aintree, Liverpool, United Kingdom
  • Stephen B Kaye
    St. Paul’s Eye Unit, Royal Liverpool University Hospital, Liverpool, United Kingdom
    Department of Eye and Vision Science, University of Liverpool, Liverpool, United Kingdom
  • Yalin Zheng
    Department of Eye and Vision Science, University of Liverpool, Liverpool, United Kingdom
    St. Paul’s Eye Unit, Royal Liverpool University Hospital, Liverpool, United Kingdom
  • Footnotes
    Commercial Relationships   Hong Qi, None; Davide Borroni, None; Rongjun Liu, None; Bryan Williams, None; Mike Beech, None; Yitian Zhao, None; Baikai Ma, None; Vito Romano, None; Uazman Alam, None; Stephen Kaye, None; Yalin Zheng, None
  • Footnotes
    Support  National Natural Science Foundation of China (No. 30872813; No. 81570813)
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 5721. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Hong Qi, Davide Borroni, Rongjun Liu, Bryan Williams, Mike Beech, Yitian Zhao, Baikai Ma, Vito Romano, Uazman Alam, Stephen B Kaye, Yalin Zheng; Automated detection of corneal nerves using deep learning. Invest. Ophthalmol. Vis. Sci. 2018;59(9):5721.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : There has been increasing use of in-vivo confocal microscopy (IVCM) for the non-invasive examination of corneal nerves. This allows the study of nerve alterations in different ocular diseases, both before and after corneal surgery, and in systemic diseases such as diabetes. However, there has been no corresponding increase in the availability of software tools to support the automatic analysis of corneal nerves. We propose and evaluate a new computer aided detection model based on deep learning for the automatic detection of corneal nerves in IVCM images.

Methods : 584 IVCM images were acquired using the Heidelberg Retina Tomograph 3/Rostock Cornea Module (Heidelberg Engineering, Heidelberg, Germany) from healthy corneas and corneas with various corneal conditions. The corneal nerves in each image were manually traced by a clinical ophthalmologist (DB) to provide a ground truth. 437 (76%) randomly chosen images were used to train the deep learning model while the remaining 147 (24%) were reserved for testing the model. A convolutional neural network (CNN) was adopted here for the purpose of segmenting the corneal nerves, comprising 10 convolution layers and 9 pooling layers. The Dice Similarity Coefficient (DSC) was used as the cost function to train the network. Drop-out (ratio 0.2) was used in order to reduce the problem of overfitting during training. In order to improve performance, 81 patches of size 128x128 pixels per image were produced and used as input for the model. The model was trained for 200 iterations and performance of the trained model was evaluated using DSC.

Results : Excellent segmentation results were achieved. In terms of patches, the mean DSC values obtained were 0.916 for the validation set and 0.867 for the test set. Reconstructing the whole-image segmentations from the patches and comparing with expert annotations, we achieved a mean DSC of 0.856.

Conclusions : Our results have demonstrated that this deep learning based model can provide very encouraging localisation performance for the detection of corneal nerves. The developed model could be further refined and validated with large datasets in order to support the management of eye disease and systemic disease.

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

×
×

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.

×