September 2016
Volume 57, Issue 12
Open Access
ARVO Annual Meeting Abstract  |   September 2016
Automatic versus manual segmentation of choroidal neovascularization lesions using optical coherence tomography
Author Affiliations & Notes
  • Ruhella Rashid Hossain
    Ophthalmology, East Kent Hospitals University NHS Foundation Trust, London, England, United Kingdom
  • Aishath Rizma Moosa
    Ophthalmology, East Kent Hospitals University NHS Foundation Trust, London, England, United Kingdom
  • Nishal Patel
    Ophthalmology, East Kent Hospitals University NHS Foundation Trust, London, England, United Kingdom
  • Footnotes
    Commercial Relationships   Ruhella Hossain, None; Aishath Moosa, None; Nishal Patel, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science September 2016, Vol.57, 1616. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Ruhella Rashid Hossain, Aishath Rizma Moosa, Nishal Patel; Automatic versus manual segmentation of choroidal neovascularization lesions using optical coherence tomography. Invest. Ophthalmol. Vis. Sci. 2016;57(12):1616.

      Download citation file:


      © 2017 Association for Research in Vision and Ophthalmology.

      ×
  • Supplements
Abstract

Purpose : Although fluorescein angiography is the current gold standard for diagnosing choroidal neovascularization (CNV), optical coherence tomography (OCT) segmentation software can identify the boundaries of the retinal pigment epithelium (RPE) changes and calculate the size of the CNV lesion. We hypothesize that 1) using surface area and volume as biomarkers for CNV lesions, OCT automatic segmentation is less accurate than manual segmentation both at diagnosis and after the third anti-VEGF, Lucentis, injection; and 2) OCT automatic segmentation is an accurate diagnostic tool for measuring CNV lesions.

Methods : Retrospective study of 10 macular degeneration patients diagnosed with CNV. Blinded observers, trained to detect RPE changes, manually delineated boundaries of CNV lesions using SDOCT (Topcon 2000) with drusen analysis before and after Lucentis injections. Caliber measurements were compared to automatic segmentation values. Statistical analysis was performed, taking into account inter-observer variability.

Results : Automatic and manual segmentation measurements are similar in 1) retinal area and fovea center values both pre-and post-injection; and 2) retinal volume post-injection. Retinal volume pre-injection was 1) similar between the two blinded observers; 2) varied between automatic measurements and observers in some patients; 3) underestimated for all patients in the automatic measurements. Overall, automatic segmentation detects a general reduction in CNV lesion size.

Conclusions : OCT software detects CNV lesions and reports size reduction after the third Lucentis injection. OCT automatic segmentation using Topcon drusen analysis in this small cohort is an accurate diagnostic tool to measure CNV surface area and volume.

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

 

OCT automatic segmentation versus manual segmentation of two blinded observers. Pre-injection measurements of A) Retinal area, B) Retinal volume, C) Centre of fovea. Post-injection measurements of D) Retinal area, E) Retinal volume, F) Centre of fovea.

OCT automatic segmentation versus manual segmentation of two blinded observers. Pre-injection measurements of A) Retinal area, B) Retinal volume, C) Centre of fovea. Post-injection measurements of D) Retinal area, E) Retinal volume, F) Centre of fovea.

×
×

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.

×