Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
In-Vivo Confocal Microscopy Deep-Learning Based Analysis of the Subbasal Corneal Nerve Parameters of the Inferior Whorl in Dry Eye Disease, Neuropathic Corneal Pain, and Controls.
Author Affiliations & Notes
  • Raul E. Ruiz Lozano
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Zane Zemborain
    Biomedical Engineering, Duke University, Durham, North Carolina, United States
  • Nadim Azar
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Matias Soifer
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Manuel Emiliano Quiroga Garza
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Symon Ma
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
  • Seitaro Komai
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Ali Khodor
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
  • Luis A. Rodriguez-Gutierrez
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
  • Sandra S. Stinnett
    Associate Professor of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina, United States
  • Sina Farsiu
    Biomedical Engineering, Duke University, Durham, North Carolina, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Victor L Perez
    Bascom, University of Miami Miller School of Medicine, Miami, Florida, United States
    Ophthalmology, Duke University School of Medicine, Durham, North Carolina, United States
  • Footnotes
    Commercial Relationships   Raul Ruiz Lozano None; Zane Zemborain None; Nadim Azar None; Matias Soifer None; Manuel Quiroga Garza None; Symon Ma None; Seitaro Komai Japan Eye Bank Association, Code F (Financial Support); Ali Khodor None; Luis Rodriguez-Gutierrez None; Sandra Stinnett None; Sina Farsiu None; Victor Perez Brill Pharma, Claris Biotherapeutics, Dompé, Kala, Nicox, Novartis, Thea, Trefoil, Code C (Consultant/Contractor), Novartis, NIH, Code F (Financial Support)
  • Footnotes
    Support  This work was supported in part by the National Institutes of Health (U01 EY034687, P30 EY005722, R01EY030283, and R01EY024484), and Research to Prevent Blindness Unrestricted Grant to Duke University
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5485. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Raul E. Ruiz Lozano, Zane Zemborain, Nadim Azar, Matias Soifer, Manuel Emiliano Quiroga Garza, Symon Ma, Seitaro Komai, Ali Khodor, Luis A. Rodriguez-Gutierrez, Sandra S. Stinnett, Sina Farsiu, Victor L Perez; In-Vivo Confocal Microscopy Deep-Learning Based Analysis of the Subbasal Corneal Nerve Parameters of the Inferior Whorl in Dry Eye Disease, Neuropathic Corneal Pain, and Controls.. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5485.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Use of a novel machine learning algorithm for the un-biased evaluation of in-vivo confocal microscopy (IVCM) images of corneal nerves in patients with dry eye disease (DED) and neuropathic corneal pain (NCP).

Methods : Corneal subbasal nerve plexus (SNP) images of the inferior whorl of patients with DED (n = 49, 77 eyes), NCP (n = 14, 24 eyes), and controls (n = 41, 59 eyes) were taken with in-vivo confocal microscopy (IVCM). The images were analyzed using an artificial intelligence (AI)-based algorithm previously developed by our group (Zemborain ZZ, et al. 2023). This is a two-step algorithm that (1) segments and removes applanation artifacts and (2) segments nerves, immune cells, and neuromas in the SNP. The following parameters were compared between groups: nerve density, average nerve thickness, average nerve segment tortuosity, junction point density, neuroma density, and immune cell density.

Results : 160 eyes of 104 patients (63% females), were included. The mean age at presentation was 57 + 15 years. Fourteen (14%) patients had Sjögren syndrome (SS) and 15 (14%) ocular graft-versus-host disease (oGVHD). While the mean nerve density of the control group was significantly higher compared with the DED (P = 0.012) and NCP (P < 0.001) groups, the junction point density was lower in the NP group compared to the DED (P = 0.004) and control (P = 0.001) group. The immune cell density was higher in the DED group compared with controls (P < 0.001). Sub-analysis showed that eyes with oGVHD- and SS-associated DED had a higher immune cell density compared to those with idiopathic DED (P = 0.006 and P = 0.054, respectively).

Conclusions : Deep-learning based analysis of IVCM images of the corneal SNP inferior whorl distinguished a decrease mean nerve density in patients with DED and NCP compared with controls, and an increase immune cell density in patients with oGVHD- and SS-associated DED. These findings suggest that the inferior whorl could be used as a landmark to distinguish between patients with DED and NCP.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

×
×

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.

×