May 2006
Volume 47, Issue 13
Free
ARVO Annual Meeting Abstract  |   May 2006
Automatic Segmentation of Drusen in Fundus Image Using Non–Negative Matrix Factorization
Author Affiliations & Notes
  • S. Du
    Columbia University, New York, NY
    Department of Biomedical Engineering,
  • P. Sajda
    Columbia University, New York, NY
    Department of Biomedical Engineering,
  • J. Koniarek
    Columbia University, New York, NY
    Department of Ophthalmology,
  • R.T. Smith
    Columbia University, New York, NY
    Department of Ophthalmology,
  • Footnotes
    Commercial Relationships  S. Du, None; P. Sajda, None; J. Koniarek, None; R.T. Smith, None.
  • Footnotes
    Support  NIH EY015520 HIGHWIRE EXLINK_ID="47:5:5730:1" VALUE="EY015520" TYPEGUESS="GEN" /HIGHWIRE –01
Investigative Ophthalmology & Visual Science May 2006, Vol.47, 5730. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      S. Du, P. Sajda, J. Koniarek, R.T. Smith; Automatic Segmentation of Drusen in Fundus Image Using Non–Negative Matrix Factorization . Invest. Ophthalmol. Vis. Sci. 2006;47(13):5730.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose: : The segmentation and quantitation of drusen is important for diagnosis and monitoring of retinal disease, particularly age–related macular degeneration (AMD). Many approaches to drusen segmentation have been based on heuristics, such as morphological analysis, image thresholding, etc. and require significant parameter tuning. Here we describe an unsupervised method for segmenting drusen in fundus images.

Methods: : Color fundus images were acquired using the Topcon50EX fundus camera and digitized on the Nikon 2000 Coolscan. Two sets of images were considered a) leveled (using a published quadratic and spline model of green (G) channel background (R. T. Smith, Arch. Ophthalmol., 2005; 123:200–6.)) and b) unleveled. A "gold–standard" was constructed by manual segmentation of the drusen by a retinal specialist. Data from the three channels (R,G,B) were processed using non–negative matrix factorization (NMF, D. Lee, NIPS, 2001; 13:556–62). NMF decomposes a multi–variant data set (X) into two matrices: a matrix of spectral signatures (S) and their corresponding spatial distribution (A). The spatial distribution matrix (A) was analyzed using K–means clustering to label all pixels in the image into one of three classes. The entire method is unsupervised and does not require manual intervention. This method has been previously demonstrated for use in NMR based metabolomics (S. Du, Proc. EMBS, Sept., 2005).

Results: : Visual inspection of the labellings produced by the algorithm tended to correspond to drusen, blood vessels and normal retinal tissue. Comparison of segmentation with the manually defined gold standard showed a range of sensitivity for detection of drusen (leveled data 51%–88%, unleveled 70–75%), with a specificity of (leveled data 78–97%, unleveled 71–97%) across four cases. Interestingly, in many cases false negatives produced by the algorithm were along the borders of the gold–standard defined drusen, indicating that individual drusen were detected by the algorithm, though their size was underestimated.

Conclusions: : The NMF method is able to recover spectral signatures of drusen, as well as other anatomical structures in the retina, using only the three bands in color fundus images. Related work of our group is exploring the use of hyperspectral imaging which provides richer spectral signatures and is in fact even better suited for an NMF–based decomposition/segmentation.

Keywords: image processing • age-related macular degeneration • drusen 
×
×

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.

×