March 2012
Volume 53, Issue 14
Free
ARVO Annual Meeting Abstract  |   March 2012
Automatic Segmentation of Cysts in Retinal SDOCT Images using Graph Theory and Dynamic Programming
Author Affiliations & Notes
  • Stephanie J. Chiu
    Biomedical Engineering, Duke University, Durham, North Carolina
  • Priyatham S. Mettu
    Ophthalmology, Duke University Eye Center, Durham, North Carolina
  • Glenn J. Jaffe
    Ophthalmology, Duke University Eye Center, Durham, North Carolina
  • Cynthia A. Toth
    Ophthalmology, Duke University Eye Center, Durham, North Carolina
  • Joseph A. Izatt
    Biomedical Engineering, Duke University, Durham, North Carolina
  • Sina Farsiu
    Ophthalmology, Duke University Eye Center, Durham, North Carolina
  • Footnotes
    Commercial Relationships  Stephanie J. Chiu, Unlicensed (P); Priyatham S. Mettu, None; Glenn J. Jaffe, Heidelberg (C); Cynthia A. Toth, Alcon, Bioptigen, Unlicensed (P), Bioptigen, Genentech (F), Physical Sciences Incorporated (C); Joseph A. Izatt, Bioptigen (I, S), Bioptigen, Unlicensed (P); Sina Farsiu, Unlicensed (P)
  • Footnotes
    Support  American Heath Assistance; Andrew Family Foundation; The Hartwell Foundation; Research to Prevent Blindness Physician-Scientist Award; NIH: 1UL1 RR024128-01, P30 EY-005722; John Chambers Fellowship
Investigative Ophthalmology & Visual Science March 2012, Vol.53, 4093. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Stephanie J. Chiu, Priyatham S. Mettu, Glenn J. Jaffe, Cynthia A. Toth, Joseph A. Izatt, Sina Farsiu; Automatic Segmentation of Cysts in Retinal SDOCT Images using Graph Theory and Dynamic Programming. Invest. Ophthalmol. Vis. Sci. 2012;53(14):4093.

      Download citation file:


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

      ×
  • Supplements
Abstract
 
Purpose:
 

Fast, accurate, and objective detection of disease imaging biomarkers is crucial for the study and diagnosis of ophthalmic diseases. Chiu et al. previously developed a generalized framework based on graph theory and dynamic programming (GTDP) to segment layered structures in ocular SDOCT images. However, aside from layered structures, there is a need for automatically segmenting closed-contour features in ophthalmic images such as cysts. In this work, we extend the application of our GTDP technique to segment cysts seen on retinal SDOCT images.

 
Methods:
 

Our method is an extension of the GTDP technique previously introduced for segmenting layered (line) structures. Our algorithm is based on the observation that with the appropriate transform, closed-contour features in the Cartesian domain can be represented as lines in a pseudo-polar domain. This novel transform allows us to use our previous GTDP method to segment the object as if it were a layered structure. We have utilized this method to segment retinal cysts on SDOCT images of pediatric and diabetic macular edema patients.

 
Results:
 

The fully automated segmentation efficiently isolated large and small cystoid structures with irregular contours in complex pathologies. In Fig.1, we demonstrate the effectiveness of this method in retinal SDOCT images of a) a premature infant eye with macular edema and b) an eye with diabetic macular edema.

 
Conclusions:
 

The preliminary results in Fig. 1 using our automatic GTDP technique for cyst segmentation demonstrate the extensibility of our framework to segment not only layered, but also closed-contour structures, in ocular images. This is highly encouraging for reducing the time and manpower required to segment cysts and other closed features in ophthalmic studies.  

 
Keywords: image processing • retina 
×
×

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.

×