June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Anterior Eye Segment Imaging System for Teleophthalmology
Author Affiliations & Notes
  • Ana Diego
    Ophthalmology, University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
    Biomedical Engineering, University of Miami, Coral Gables, Florida, United States
  • Mohamed Abou Shousha
    Ophthalmology, University of Miami Health System Bascom Palmer Eye Institute, Miami, Florida, United States
  • Footnotes
    Commercial Relationships   Ana Diego None; Mohamed Abou Shousha Heru, Inc. , Code I (Personal Financial Interest)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 1399 – A0095. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ana Diego, Mohamed Abou Shousha; Anterior Eye Segment Imaging System for Teleophthalmology. Invest. Ophthalmol. Vis. Sci. 2022;63(7):1399 – A0095.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Teleophthalmology increases access to ophthalmic care, lowers screening barriers, and facilitates follow-ups. However, there is a need to develop better systems to evaluate diverse conditions remotely. This study aims to compare a portable anterior eye segment imaging system with the current standards method for ophthalmology examination.

Methods : The new imaging system consisted of two IMX219 Arducam autofocus sensors (Arducam, China, Nanjing) for Raspberry Pi V2 camera module connected to a Raspberry Pi Zero W (Raspberry Pi Foundation, UK, Cambridge) that clips to a HoloLens 2 (Microsoft, Redmond, WA). Twenty subjects from the Bascom Palmer Eye Institute clinic participated in the study. Anterior eye segment videos were recorded with the new system and a 720p FaceTime HD camera (Apple, Cupertino, CA). Afterward, an ophthalmologist evaluated the videos using a clinical eye examination form. This questionnaire assessed the presence of pathologies for the different eye structures and graded video quality based on identifying emergent findings. The video evaluations were compared with the standard slit-lamp clinical evaluation performed during the patient’s visit.

Results : Thirty-five eyes were evaluated. The percentage sensitivity and specificity were 31.4% and 81.1%, respectively, for the HoloLens-RBPi videos and 13.7% and 39.9% for the web camera videos. Ocular structures such as the cornea, anterior chamber, iris, and lens were better evaluated with the HoloLens-RBPi videos (specificity 50%-88.5%, sensitivity 18.2%-40%). Conjunctiva and sclera had the highest sensitivity percentage for both modalities (73.3% HoloLens-RBPi and 66.7% Web Camera). The average grade for the HoloLens-RBPi videos was 3.17, and the web camera videos averaged 1.35 out of a 5 point scale.

Conclusions : Specificity percentages were higher than sensitivity percentages in both imaging modalities, indicating that video evaluations are less accurate for pathologies screening. Nevertheless, HoloLens-RBPi evaluations were statistically significantly better than the webcam evaluations. This study presented an alternative system to assess eye conditions for telemedicine, a system that provides more details than the current standard for eye evaluation performed through a webcam. Further developments will include improving camera and illumination quality, obtaining fundus images, automating camera positioning, and creating a program to access livestream images.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

×
×

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.

×