September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
Automated Optic Disk (OD) Localization in The Neonatal Fundus Image
Author Affiliations & Notes
  • Daniel Ernest Worrall
    Computer Science, University College London, London, United Kingdom
  • Gabriel Brostow
    Computer Science, University College London, London, United Kingdom
  • Clare Wilson
    Computer Science, University College London, London, United Kingdom
  • Footnotes
    Commercial Relationships   Daniel Worrall, Fight for Sight (F); Gabriel Brostow, Fight for Sight (F); Clare Wilson, Fight for Sight (F)
  • Footnotes
    Support  Fight for Sight Studentship
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 5939. doi:
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Daniel Ernest Worrall, Gabriel Brostow, Clare Wilson; Automated Optic Disk (OD) Localization in The Neonatal Fundus Image. Invest. Ophthalmol. Vis. Sci. 2016;57(12):5939.

      Download citation file:

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

  • Supplements

Purpose : Accurate OD localization algorithms abound for adult fundus images. These same algorithms fail dismally on the neonatal fundus, which contains high levels of imaging artifacts, due to: equipment and procedural artifacts (e.g. reflections and blurring), and inter-subject and over time intra-subject morphological differences. We address this lacuna in the space of registration algorithms, building an accurate automated OD localization algorithm for neonatal fundus images, robust to high inter-image variation.

Methods : We approached the problem from a machine learning viewpoint. Images are first high pass filtered to remove intra- and inter-image illumination and color variation. These images are then input to an off-the-shelf pretrained implementation of a convolutional neural network (CNN), projecting the images into a rich, multi-scale feature space representation. These CNN feature maps are resized in their two spatial-dimensions and stacked into a 1376-dimensional deep per-pixel feature vector or `hypercolumn’ (HC). For memory reasons, HC patches are then subsampled to form a 8x8x400-dimensional feature descriptor and then fed into a Hough Forest, a statistical model, regressing the offset of the OD center from the specific region of the fundus, collocated with the HC patch. The Hough Forest was trained on a balanced set of 40000 randomly selected patches from 100 training images with marked OD centers and its hyperparameters were tuned using cross-validation on a set of 200 validation images, new hyperparameters proposed by an off-the-shelf hyperparameter optimizer.

Results : The system was tested on a separate test set of 1464 retinal images, successfully localizing 1417 (96.6%) images and failing on 47 (3.3%). A successful localization is measured as estimating the center to lie within the perimeter of the OD. The test set displays moderate levels of covariate shift from the training and validation sets, indicating high robustness to inter-subject differences in retinal appearance.

Conclusions : This algorithm performs successful OD localization in the neonatal fundus image, robust to high inter-image variation. A statistical machine learning-based approach permits the localization of the OD in the neonatal fundus. This is the first step in automated vessel analysis for vascular retinopathies.

This is an abstract that was submitted for the 2016 ARVO Annual Meeting, held in Seattle, Wash., May 1-5, 2016.


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.