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
Testing the performance and application of glaucoma risk score models on swept source optical coherence tomography data
Author Affiliations & Notes
  • Atsushi Kubota
    Topcon Healthcare, New Jersey, United States
  • Anya Guzman
    Topcon Healthcare, New Jersey, United States
  • Yi Sing Hsiao
    Topcon Healthcare, New Jersey, United States
  • Mary Durbin
    Topcon Healthcare, New Jersey, United States
  • Tony H Ko
    Topcon Healthcare, New Jersey, United States
  • Footnotes
    Commercial Relationships   Atsushi Kubota Topcon Healthcare, Code E (Employment); Anya Guzman Topcon Healthcare, Code E (Employment); Yi Sing Hsiao Topcon Healthcare, Code E (Employment); Mary Durbin Topcon Healthcare, Code E (Employment); Tony Ko Topcon Healthcare, Code E (Employment)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 4048. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Atsushi Kubota, Anya Guzman, Yi Sing Hsiao, Mary Durbin, Tony H Ko; Testing the performance and application of glaucoma risk score models on swept source optical coherence tomography data. Invest. Ophthalmol. Vis. Sci. 2024;65(7):4048.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To evaluate the diagnostic accuracy and applicability of four glaucoma risk score models, developed by Fukai et al. (2022), when applied to swept source optical coherence tomography (SS-OCT) scans of both healthy and diseased eyes. Comparative analysis was also conducted using SS-OCT scans and spectral domain optical coherence tomography (SD-OCT) scans acquired on the same eyes.

Methods : A cross-sectional study was conducted on 25 glaucoma and 25 healthy patients. Patients underwent an ocular examination to determine if they belonged in the healthy or glaucoma group. Each patient was scanned by the SS-OCT (Triton, Topcon Healthcare, Tokyo, Japan) and SD-OCT (Maestro, Topcon Healthcare, Tokyo, Japan) devices with the same eye using 12mm by 9mm widefield OCT scans. Scans were excluded from the dataset for the following reasons: blinks, motion artifacts, a TopQ score less than 25, segmentation errors, or a mispositioned optic disc. All scans from both devices were used to generate risk scores using all four models.
The performance of the models on the SS-OCT scans was compared against that on the SD-OCT scans through area under the receiver operating characteristic curves (AUROCs), sensitivity, and specificity metrics. The risk scores from both devices were independently compared within the healthy and glaucoma groups.

Results : The risk scores derived from SS-OCT scans aligned with the risk scores obtained from SD-OCT scans in both healthy and glaucoma groups (Figure 1). The devices demonstrated comparable performance, as indicated by their AUROC values ranging from 0.95 to 0.96 (Figure 2). Among the models, model 1 showed the most significant change in sensitivity between devices, with a difference of 0.12 at 95% specificity.

Conclusions : The performance of these models on the SS-OCT device closely resembled their performance on the SD-OCT device based on their AUROC values. The glaucoma risk score models, while originally developed using SD-OCT data, can be applied to SS-OCT scans to exhibit high performance distinguishing between healthy and glaucomatous eyes. This study indicates a promising potential for implementing the glaucoma risk score models on SS-OCT scans.

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

 

Figure 1. Mean and standard deviation of the glaucoma risk scores models for both groups.

Figure 1. Mean and standard deviation of the glaucoma risk scores models for both groups.

 

Figure 2. AUROC and sensitivity values of the glaucoma risk scores models for both groups.

Figure 2. AUROC and sensitivity values of the glaucoma risk scores models for both groups.

×
×

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.

×