June 2013
Volume 54, Issue 15
Free
ARVO Annual Meeting Abstract  |   June 2013
Automatic Segmentation of OCT Datasets Using Superpixels-Classification
Author Affiliations & Notes
  • Pascal Dufour
    Ophthalmic Technologies ARTORG Center, University of Bern, Bern, Switzerland
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
  • Hannan Abdillahi
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
    Bern Photographic Reading Center, University Hospital Bern, Bern, Switzerland
  • Lala Ceklic
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
    Bern Photographic Reading Center, University Hospital Bern, Bern, Switzerland
  • Ute Wolf-Schnurrbusch
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
    Bern Photographic Reading Center, University Hospital Bern, Bern, Switzerland
  • Sebastian Wolf
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
  • Jens Kowal
    Ophthalmic Technologies ARTORG Center, University of Bern, Bern, Switzerland
    Department of Ophthalmology, University Hospital Bern, Bern, Switzerland
  • Footnotes
    Commercial Relationships Pascal Dufour, None; Hannan Abdillahi, None; Lala Ceklic, None; Ute Wolf-Schnurrbusch, None; Sebastian Wolf, Allergan (F), Allergan (C), Allergan (R), Bayer (F), Bayer (C), Bayer (R), Novartis (F), Novartis (C), Novartis (R), Heidelberg Engineering (C), Heidelberg Engineering (F), Hoya (F), Hoya (R), Optos (F), Optos (C), Optos (R), Euretina (S); Jens Kowal, None
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2013, Vol.54, 5509. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Pascal Dufour, Hannan Abdillahi, Lala Ceklic, Ute Wolf-Schnurrbusch, Sebastian Wolf, Jens Kowal; Automatic Segmentation of OCT Datasets Using Superpixels-Classification. Invest. Ophthalmol. Vis. Sci. 2013;54(15):5509.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose: Retinal cell layer segmentation of Optical Coherence Tomography (OCT) data is an important prerequisite for diagnostic purposes, clinical trials and research into pathologies of the eye. Most methods apply a layer-based segmentation scheme and try to detect cell layer boundaries. However, when the retinal cell layers are disrupted, these methods are incapable of providing a meaningful segmentation. To overcome that limitation, we propose a method that does not focus on finding the cell layer boundaries, but instead assigns each pixel in a B-scan to a retinal layer.

Methods: Using the Simple Linear Iterative Clustering (SLIC) algorithm, each B-scan is first divided into superpixels; small regions with homogeneous texture that can be assumed to lie on the same retinal cell layer. Various image filters are then applied in the proximity of each superpixel, providing a set of features descriptive of the neighborhood of that superpixel. Using these features, a trained Random Forest classifier computes the probability of each superpixel belonging to a specific retinal cell layer. Finally, a multi-label graph-cut algorithm aggregates the results from the classification. In this work, 1225 B-scans from 25 OCT volumes of healthy eyes were used to train the Random Forest. Each volume was first automatically segmented and then manually inspected and corrected. The following 7 regions in the volume were segmented: vitreous, NFL, combined GCL and IPL, combined INL and OPL, ONL, layers between IS/OS and BM, and choroid.

Results: 20 OCT volumes from 20 healthy subjects were used to evaluate the algorithm. From each volume, 5 B-scans were randomly chosen and manually segmented by two observers. The Dice coefficient was computed to test the accuracy of the automatic segmentation. A mean Dice coefficient of 0.945±0.0094 over all regions and B-scans was achieved, which is comparable to the inter-observer variability of a Dice coefficient of 0.947±0.0081.

Conclusions: The proposed method can distinguish the retinal layers in normal eyes with high accuracy, without assuming continuous cell layers. A next step will be the training of the classifier on OCT data with advanced-stage pathologies, where a layer-based segmentation cannot be applied. Initial tests on OCT data of patients with diagnosed Wet Age-Related Macular Degeneration show promising results.

Keywords: 549 image processing • 688 retina • 550 imaging/image analysis: clinical  
×
×

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.

×