June 2017
Volume 58, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2017
The utility of the opacity suppression (OS) filter tool with automated retinal analysis software and manual reading for detection of DR in DM Type 1
Author Affiliations & Notes
  • Sumana Kommana
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Nicole Mendez
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Lesley Wu
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Pooja Padgaonkar
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Bernard Szirth
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Albert S Khouri
    Ophthalmology, Rutgers New Jersey Medical School, Newark, New Jersey, United States
  • Footnotes
    Commercial Relationships   Sumana Kommana, None; Nicole Mendez, None; Lesley Wu, None; Pooja Padgaonkar, None; Bernard Szirth, None; Albert Khouri, None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2017, Vol.58, 663. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Sumana Kommana, Nicole Mendez, Lesley Wu, Pooja Padgaonkar, Bernard Szirth, Albert S Khouri; The utility of the opacity suppression (OS) filter tool with automated retinal analysis software and manual reading for detection of DR in DM Type 1. Invest. Ophthalmol. Vis. Sci. 2017;58(8):663.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To assess the utility of the OS filter with automated software and manual reading for detection of DR in Type 1 DM.

Methods : We collected 20 images obtained over 10 visits from a 21 y/o Hispanic male with type 1 DM for 17 years. Color fundus images of both eyes were captured in non-mydriatic mode at a 45° angle and a flash setting of 100 watt second using a Canon CR-DGi (12 Mp) and CR2 Plus AF retinal camera with an 18 Mp CMOS censor. The images were subsequently enhanced with the OS filter, a novel technique by Canon USA which entails of color correction by emphasizing blue color and contrast adjustment by increasing edge sharpness. The 2 sets of images were digitally analyzed using EyeArt™ (Eyenuk, Inc., Los Angeles, CA) automated DR screening software, which recommends “refer” when it detects moderate NPDR or higher on the ICDR scale or “no refer” otherwise. It also reports DR severity and offers a score from 0-5, with higher scores signifying higher DR severity levels. Both sets of images were also manually analyzed for total number of lesions, further differentiated by type: dot, flame, and intraretinal microvascular abnormalities (IrMAs). A board certified ophthalmologist reviewed each set of images. An analysis comparing the impact of the OS on the detection of DR in automated and manual screening is reported.

Results : Software analysis of the original and enhanced images is detailed in Table 1. DR severity score did show variation between the two sets of images, however OS did not change management as referral was recommended in 10/10 encounters with both sets of images. Manual analysis of both sets of images is detailed in Table 2. OS increased visibility of dot hemorrhages but had limited effect on visibility of flame hemorrhages and IRMAs.

Conclusions : The OS filter tool significantly improved image quality, having the most notable effect on manual reading as dot hemorrhages had increased visibility. The filter showed limited benefit with automated analysis as there was some variation in DR severity scores but overall management (refer vs no refer) did not change. A limitation is the presence of a retinal reflex, found in young eyes, that could lessen the filter's utility. Future studies will assess the OS tool's use in assessing DR in type 2 DM in a greater age distribution.

This is an abstract that was submitted for the 2017 ARVO Annual Meeting, held in Baltimore, MD, May 7-11, 2017.

 

Table 1: EyeArt Analysis

Table 1: EyeArt Analysis

 

Table 2: Manual Analysis

Table 2: Manual Analysis

×
×

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.

×